Advanced search in Research products
Research products
arrow_drop_down
Searching FieldsTerms
Any field
arrow_drop_down
includes
arrow_drop_down
The following results are related to Digital Humanities and Cultural Heritage. Are you interested to view more results? Visit OpenAIRE - Explore.

  • Digital Humanities and Cultural Heritage
  • 2012-2021
  • Publications
  • Research data
  • Other research products
  • CA
  • LV
  • English

Date (most recent)
arrow_drop_down
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Kudashkina, Ekaterina (Katya);

    Intelligent assistants could benefit humans and the environment in many ways: they could help make predictions about the future, enhance productivity, optimize work, and make improvements not only in daily tasks but on a global level. Intelligent assistants are a challenge to develop. In particular, conversational intelligent assistants are still a subject of artificial intelligence (AI) research. The challenge of conversational AI requires a domain that is tightly scoped so that the intelligent assistant can learn and understand it. In this thesis, I propose a voice document-editing domain, argue that the proposed domain is particularly promising for conducting research in conversational AI, and present its primary advantages. Further, I present suitable methods for developing intelligent assistants that are designed to learn from interaction without explicit instruction. I show that model-based reinforcement learning is a particularly appropriate class of methods to pursue. Next, I provide a sample-efficient model-based reinforcement learning method: soft-planner policy optimization. In this method, we introduce a novel soft-planner policy and present a new update in which the soft-planner policy is used to fine-tune a model-free policy and value function. Using a specific deletion task within the proposed domain, I demonstrate that the soft-planner policy optimization method allows the agent to efficiently learn. I compare the method to the current state-of-the-art implementations for such systems: model-free actor-critic methods and supervised methods. Finally, within model-based reinforcement learning methods, I focus on methods that use expectation models and linear value functions. I show that planning with an expectation model must update a state-value function, not an action-value function as previously suggested in the literature. I then demonstrate three methods in which actions can be selected when planning with state-value functions and present general model-based reinforcement learning algorithms for each. I present the practical application of these methods on our proposed voice document-editing domain. Altogether, this thesis combines deep learning, natural language processing, and reinforcement learning in the context of intelligent assistants, in particular, conversational AI. We focus on model-based reinforcement learning methods that solve control problems and combine the settings of online learning, function approximation, and stochastic environments.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ DSpace at the Univer...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ DSpace at the Univer...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Voege, Peter;

    The field of authentication has a lot of room to develop in the age of big data and machine learning. Conventional high-accessibility authentication mechanisms including passwords or security questions struggle with critical vulnerabilities, creating a need for alternative authentication mechanisms able to cover said weaknesses. We sought to create an authentication mechanism that creates dynamic, ever-changing security questions only the user can answer while remaining intuitive to use and as accessible as typical security questions by creating an authentication chatbot that leverages big data and natural language processing to pose dynamic authentication challenges. We tested the components of our design in simulated scenarios to prove their efficacy, and found that all critical elements of the design can satisfactorily complete the tasks set for them. Thus we believe this design offers a useful supplement or alternative to password or security question-based authentication, improving the security of user data in our society.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Scholarship@Western
    Other literature type . 2021
    License: CC BY
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      Scholarship@Western
      Other literature type . 2021
      License: CC BY
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Tratch, Maiah;

    The Cabeço da Arruda archaeological site, located in the Muge Valley (Central Portugal), is a shell-midden burial site situated in the Mesolithic period (8,500 to 6,900 cal BP). Previous research on the valley has neglected to properly document and systematize the roughly 150 burials recovered from this site which have been curated in the Museo Geológico Museum in Lisbon since the 1930s. My research focused on systematizing the burials at this museum, identifying the individuals whose boney segments preserved in a mud-based cement (breccia), and reconstructing the burial rituals associated with body position and grave environment features using an archaeothanatological method. This allowed me to address the questions: (1) Are there identifiable burial dispositional patterns at Cabeço da Arruda?; and (2) Through comparison of the similarities and differences in dispositional patterns and mortuary practices between the three main sites in the valley (Cabeço da Arruda, Cabeço da Amoreira, and Moita do Sebastião), are there identifiable characteristics throughout the entirety of the Muge Mesolithic? I determined that the most common burial disposition at Cabeço da Arruda was dorsal decubitus with a hyper-flexed lower limb which was positioned over the thorax. The most common grave features were for the body to be interred in an oval, concave pit with lateral space and external wrappings constricting the upper limb and thorax. These patterns constitute burial rituals because their repetition, with minimal individual variation, is indicative of prescribed behaviours occurring during the internment phase. When including osteobiographical data into these interpretations, no statistical pattern was identified for age (neonates, nonadults, adults) or sex (female or male) across the burial ritual data. These interpretations were consistent with the frequencies of previous burial dispositional patterns from the valley indicating that there were consistent rituals within the valley during the Mesolithic.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ MSpace at the Univer...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ MSpace at the Univer...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Nesca, Marcello;

    Introduction: Routinely collected electronic health data (RCEHD), can be comprised of structured, semi-structured, or unstructured information. Electronic medical records (EMRs), one type of RCEHD, often contain unstructured text data (UTD), which are typically prepared for analysis (i.e., preprocessed) and analyzed using natural language processing (NLP) techniques. At present, there are few studies about the specific types of NLP methods used to preprocess UTD to address data quality issues prior to analysis or modelling. Purpose & Objectives: The purpose was to examine preprocessing methods for UTD and evaluate the quality of UTD in EMRs. The objectives were to: 1) systematically document current research and practices for preprocessing UTD to describe or improve its quality, and 2) apply data quality indicators identified from current research and practices to UTD in EMRs from the Manitoba Primary Care Research Network and describe the quality of these data. Methods: Objective 1 involved a scoping review. Scopus, Web of Science, ProQuest, and EBSCOhost were searched for literature on current research and practices to prepare UTD for analysis, up to and including 2021. For objective 2, a case study was undertaken where data quality indicators and preprocessing methods identified in the scoping review were applied to UTD from EMRs. Results: 41 articles were included in the scoping review for objective 1; over 50% were published between 2016 and 2021 and over 90% were empirical research articles. Data quality indicator topics for UTD in EMRs included misspelled words, security, word variability, sources of noise, quality of annotations, ambiguous abbreviations, and manual annotations. For objective 2, we selected 193,206 clinical encounter notes from EMRs between 1985 and 2020. Overall, the clinical encounter notes contained an average (standard deviation [SD]) of 27.3 (27.0) stop words, 25.7 (27.8) punctuation symbols, 12.1 (11.1) spelling errors, and 2.9 (2.6) special characters. The average (SD) length of a clinical encounter note was 555.8 (551.1) characters, and 71.5 (59.7) words. Lexical diversity, had a mean (SD) of 86.2 (11.9). Conclusion: This study identified multiple data quality indicators that have been used to preprocess UTD in published literature and demonstrated their application to real-world data.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ MSpace at the Univer...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ MSpace at the Univer...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Hoy, Declan;

    As contemporary art has expanded to encompass further disparate activities under its umbrella, the various institutions of art can be looked to as the only constant and defining characteristic of art. These institutions are often seen in sharp contrast to spontaneous collectivism, the real, and radical creativity—attributes deeply valued within contemporary art. This creates a troubling situation in which institutions are seen as limiting the possibility of what art could be, and artworks are perceived as needing to escape the very institutions which define them in order to be deemed worthy. In this structure, contemporary art follows and validates the logic of neoliberalism and its doctrine of anti-institutionalism, radical creativity, and hyper individualism. This text looks at a short overview of neoliberalism, the economic impact of neoliberalism on artists, and examines the work of artist Renzo Martins in relation to the issues of neoliberalism and institutionalism in art.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Scholarship@Western
    Other literature type . 2021
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      Scholarship@Western
      Other literature type . 2021
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Ansari Dezfuly, Niloufar;

    This study investigates the effects of language background (monolingual/bilingual and early/late bilingual exposure), knowledge of a tonal language and music experience on auditory discrimination by employing tone and vowel discrimination tasks. A total number of 8,769 observations were analyzed using logistic regression to answer the following questions: (1) Do vowel and tone discrimination abilities correlate with language background in diverse groups of speakers such as monolinguals and bilinguals of different types (early/late bilinguals)? (2) Does musical training affect tone and vowel discrimination? (3) Does knowledge of tonal language affect tone discrimination? The findings suggest that with regard to vowel discrimination, the only effective variable is early bilingual exposure. In the case of tone discrimination, early bilingual exposure, knowledge of a tonal language and music experience all have positive effects, while bilingualism (independent of early or late bilingual exposure) is associated with less accurate performance. The results suggest the positive impact of early bilingual exposure, knowledge of a tonal language and music experience on enhancing auditory discrimination and auditory sensory memory. Through its focus on the effects of language and music experience on auditory discrimination, this study contributes to the fields of linguistics and psycholinguistics.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Scholarship@Western
    Other literature type . 2021
    License: CC BY
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      Scholarship@Western
      Other literature type . 2021
      License: CC BY
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Priest, Allen G;

    This dissertation explores the impact of hegemonic masculinity, in the early Cold War era, on the electoral politics of Canada and the United States. It situates itself in the years between 1949 and 1963, arguably the height of nuclear fear, at a time when masculine ideals were adjusting to an uncertain postwar reality. Previous scholarship has established that the Cold War brought with it a retreat into domesticity, followed by an emergent “crisis” of masculinity. This monograph contributes to the historiography by demonstrating that the masculine architypes of the early Cold War are frequently reflected in electoral discourse. It also highlights how postwar fears about masculinity align closely to the evolution of public understanding, and growing anxiety, about nuclear weaponry. Early chapters, which follow the political tenures of Louis St. Laurent and Dwight Eisenhower, establish that their ability to project themselves as reassuring, paternalistic father-figures was crucial to their electoral success. When combined with the portrayal of opponents as outside the bounds of hegemonic masculinity, it was a strategy that won elections. However, as the 1950s progressed, concerns about nuclear weaponry and fears about eroding manhood entered the public discourse. These new anxieties quickly rendered the paternalistic approach to governance insufficient. In its place, a more forceful brand of leadership emerged. It was focused on countering the malaise of the late 1950s by utilizing the nostalgia of the “self-made man” and promising a return to the individualism of the frontier-era. The candidacies of both John Diefenbaker and John F. Kennedy benefitted greatly from this approach, as both men promised to push towards “new” frontiers.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Scholarship@Western
    Other literature type . 2021
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      Scholarship@Western
      Other literature type . 2021
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Subramanian, Sandeep;

    Cette thèse fait des petits pas dans la construction et la compréhension des systèmes d'apprentissage des représentations neuronales et des modèles génératifs pour le traitement du langage naturel. Il est présenté comme une thèse par article qui contient quatre travaux. Dans le premier article, nous montrons que l'apprentissage multi-tâches peut être utilisé pour combiner les biais inductifs de plusieurs tâches d'apprentissage auto-supervisées et supervisées pour apprendre des représentations de phrases distribuées de longueur fixe à usage général qui obtiennent des résultats solides sur les tâches d'apprentissage par transfert en aval sans tout modèle de réglage fin. Le deuxième article s'appuie sur le premier et présente un modèle génératif en deux étapes pour le texte qui modélise la distribution des représentations de phrases pour produire de nouveaux plongements de phrases qui servent de "contour neuronal" de haut niveau qui est reconstruit en mots avec un récurrent neuronal autorégressif conditionnel décodeur. Le troisième article étudie la nécessité de représentations démêlées pour la génération de texte contrôlable. Une grande partie des systèmes de génération de texte contrôlables reposent sur l'idée que le contrôle d'un attribut (ou d'un style) particulier nécessite la construction de représentations dissociées qui séparent le contenu et le style. Nous démontrons que les représentations produites dans des travaux antérieurs qui utilisent la formation contradictoire du domaine ne sont pas dissociées dans la pratique. Nous présentons ensuite une approche qui ne vise pas à apprendre des représentations démêlées et montrons qu'elle permet d'obtenir des résultats nettement meilleurs que les travaux antérieurs. Dans le quatrième article, nous concevons des modèles de langage de transformateur qui apprennent les représentations à plusieurs échelles de temps et montrent que ceux-ci peuvent aider à réduire l'empreinte mémoire importante de ces modèles. Il présente trois architectures multi-échelles différentes qui présentent des compromis favorables entre la perplexité et l'empreinte mémoire. This thesis takes baby steps in building and understanding neural representation learning systems and generative models for natural language processing. It is presented as a thesis by article that contains four pieces of work. In the first article, we show that multi-task learning can be used to combine the inductive biases of several self-supervised and supervised learning tasks to learn general-purpose fixed-length distributed sentence representations that achieve strong results on downstream transfer learning tasks without any model fine-tuning. The second article builds on the first and presents a two-step generative model for text that models the distribution of sentence representations to produce novel sentence embeddings that serves as a high level ``neural outline'' that is reconstructed to words with a conditional autoregressive RNN decoder. The third article studies the necessity of disentangled representations for controllable text generation. A large fraction of controllable text generation systems rely on the idea that control over a particular attribute (or style) requires building disentangled representations that separate content and style. We demonstrate that representations produced in previous work that uses domain adversarial training are not disentangled in practice. We then present an approach that does not aim to learn disentangled representations and show that it achieves significantly better results than prior work. In the fourth article, we design transformer language models that learn representations at multiple time scales and show that these can help address the large memory footprint these models typically have. It presents three different multi-scale architectures that exhibit favorable perplexity vs memory footprint trade-offs.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Papyrus : Dépôt inst...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Papyrus : Dépôt inst...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Chafouleas, Geneviève;

    Plusieurs avancées utilisant le discours obtenu de la tâche de description d’image ont été réalisées dans la détection de la maladie d’Alzheimer (AD). L’utilisation de caractéristiques linguistiques et acoustiques sélectionnées manuellement ainsi que l’utilisation de méthodologies d’apprentissage profond ont montré des résultats très prometteurs dans la classification des patients avec AD. Dans ce mémoire, nous comparons les deux méthodologies sur la scène Cookie Theft du Boston Aphasia Examination en entrainant des modèles avec des caractéristiques sélectionnées à partir des extraits textuels et audio ainsi que sur un modèle d’apprentissage profond BERT. Nos modèles sont entrainés sur l’ensemble de données ADReSS challenge plus récent et évaluées sur l’ensemble de données CCNA et vice versa pour mesurer la généralisation des modèles sur des exemples jamais vus dans des ensembles de données différents. Une évaluation détaillée de l’interprétabilité des modèles est effectuée pour déterminer si les modèles ont bien appris les représentations reliées à la maladie. Nous observons que les modèles ne performent pas bien lorsqu’ils sont évalués sur différents ensembles de données provenant du même domaine. Les représentations apprises des modèles entrainés sur les deux ensembles de données sont très différentes, ce qui pourrait expliquer le bas niveau de performance durant l’étape d’évaluation. Même si nous démontrons l’importance des caractéristiques linguistiques sur la classification des AD vs contrôle, nous observons que le meilleur modèle est BERT avec un niveau d’exactitude de 62.6% sur les données ADReSS challenge et 66.7% sur les données CCNA. Many advances have been made in the early diagnosis of Alzheimer’s Disease (AD) using connected speech elicited from a picture description task. The use of hand built linguistic and acoustic features as well as Deep Learning approaches have shown promising results in the classification of AD patients. In this research, we compare both approaches on the Cookie Theft scene from the Boston Aphasia Examination with models trained with features derived from the text and audio extracts as well as a Deep Learning approach using BERT. We train our models on the newer ADReSS challenge dataset and evaluate on the CCNA dataset and vice versa in order to asses the generalisation of the trained model on unseen examples from a different dataset. A thorough evaluation of the interpretability of the models is performed to see how well each of the models learn the representations related to the disease. It is observed that the models do not perform well when evaluated on a different dataset from the same domain. The selected and learned representations from the models trained on either dataset are very different and may explain the low performance in the evaluation step. While we demonstrate the importance of linguistic features in the classification of AD vs non-AD, we find the best overall model is BERT which achieves a test accuracy of 62.6% on the ADRess challenge dataset and 66.7% on the CCNA dataset. co-direction : Simona Brambati

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Papyrus : Dépôt inst...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Papyrus : Dépôt inst...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Galic, Slavena;

    Clastic, upper Albian-lower Cenomanian strata were deposited in a low-accommodation backbulge depozone of the Western Canada Foreland Basin in SW Alberta. These strata are lithologically very heterogeneous and encompass a spectrum of depositional environments along an alluvial to offshore transect. These rocks are assigned, in subsurface, to the Lower Colorado Group, and in outcrop to the upper Blairmore Group. Lithological heterogeneity, as a result of rapid lateral facies changes, resulted in diverse nomenclature that obscured genetic relationships between time-equivalent strata. The present study integrates wireline log, core, and outcrop data to establish a high-resolution allostratigraphic framework which allowed recognition of the Basal Colorado, Joli Fou, Viking and Westgate alloformations, in ascending order. Each alloformation comprises several allomembers and parasequences. The Basal Colorado alloformation is a NE thinning wedge that progressively onlaps lower Albian Mannville Group strata. Deposition took place in a brackish-water embayment open to the south. Basal Colorado strata correlate with the Lynx Creek Member of the Mill Creek Formation in outcrop. The Joli Fou and Viking alloformations have a broadly sheet-like geometry. Both alloformations comprise three allomembers, composed of a complex array of river-dominated and mixed-influence deltaic successions. The location of successive deltas was strongly influenced by differential compaction of underlying deltas. Sandstone-rich Joli Fou rocks pass northward into offshore mudstone. To the south and west, marine Joli Fou and Viking deposits grade laterally into alluvial facies. Only the upper part of the Westgate alloformation extends into SW Alberta. Tectonic tilting is indicated by the lowermost (alluvial) and uppermost (marine) Westgate parasequences, which are SW and NE thickening wedges, respectively. Paleo-valleys, typically ~20 m deep, are incised into the top surface of most allomembers. Different examples of valley incision and fill can be attributed to both sea-level changes, and also to climatically-controlled changes in the sediment load to discharge ratio. Two pulses of thrust-induced loading and a long term (>1 myr) eustatic cycle provided the overall control on stratal architecture, whereas climate-controlled cycles in the ~400 and 100 kyr band exerted an important control on the development of allomembers and parasequences. Eustatic changes are estimated to have been ~20 – 30 m.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Scholarship@Western
    Other literature type . 2021
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      Scholarship@Western
      Other literature type . 2021
Advanced search in Research products
Research products
arrow_drop_down
Searching FieldsTerms
Any field
arrow_drop_down
includes
arrow_drop_down
The following results are related to Digital Humanities and Cultural Heritage. Are you interested to view more results? Visit OpenAIRE - Explore.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Kudashkina, Ekaterina (Katya);

    Intelligent assistants could benefit humans and the environment in many ways: they could help make predictions about the future, enhance productivity, optimize work, and make improvements not only in daily tasks but on a global level. Intelligent assistants are a challenge to develop. In particular, conversational intelligent assistants are still a subject of artificial intelligence (AI) research. The challenge of conversational AI requires a domain that is tightly scoped so that the intelligent assistant can learn and understand it. In this thesis, I propose a voice document-editing domain, argue that the proposed domain is particularly promising for conducting research in conversational AI, and present its primary advantages. Further, I present suitable methods for developing intelligent assistants that are designed to learn from interaction without explicit instruction. I show that model-based reinforcement learning is a particularly appropriate class of methods to pursue. Next, I provide a sample-efficient model-based reinforcement learning method: soft-planner policy optimization. In this method, we introduce a novel soft-planner policy and present a new update in which the soft-planner policy is used to fine-tune a model-free policy and value function. Using a specific deletion task within the proposed domain, I demonstrate that the soft-planner policy optimization method allows the agent to efficiently learn. I compare the method to the current state-of-the-art implementations for such systems: model-free actor-critic methods and supervised methods. Finally, within model-based reinforcement learning methods, I focus on methods that use expectation models and linear value functions. I show that planning with an expectation model must update a state-value function, not an action-value function as previously suggested in the literature. I then demonstrate three methods in which actions can be selected when planning with state-value functions and present general model-based reinforcement learning algorithms for each. I present the practical application of these methods on our proposed voice document-editing domain. Altogether, this thesis combines deep learning, natural language processing, and reinforcement learning in the context of intelligent assistants, in particular, conversational AI. We focus on model-based reinforcement learning methods that solve control problems and combine the settings of online learning, function approximation, and stochastic environments.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ DSpace at the Univer...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ DSpace at the Univer...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Voege, Peter;

    The field of authentication has a lot of room to develop in the age of big data and machine learning. Conventional high-accessibility authentication mechanisms including passwords or security questions struggle with critical vulnerabilities, creating a need for alternative authentication mechanisms able to cover said weaknesses. We sought to create an authentication mechanism that creates dynamic, ever-changing security questions only the user can answer while remaining intuitive to use and as accessible as typical security questions by creating an authentication chatbot that leverages big data and natural language processing to pose dynamic authentication challenges. We tested the components of our design in simulated scenarios to prove their efficacy, and found that all critical elements of the design can satisfactorily complete the tasks set for them. Thus we believe this design offers a useful supplement or alternative to password or security question-based authentication, improving the security of user data in our society.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Scholarship@Western
    Other literature type . 2021
    License: CC BY
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      Scholarship@Western
      Other literature type . 2021
      License: CC BY
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Tratch, Maiah;

    The Cabeço da Arruda archaeological site, located in the Muge Valley (Central Portugal), is a shell-midden burial site situated in the Mesolithic period (8,500 to 6,900 cal BP). Previous research on the valley has neglected to properly document and systematize the roughly 150 burials recovered from this site which have been curated in the Museo Geológico Museum in Lisbon since the 1930s. My research focused on systematizing the burials at this museum, identifying the individuals whose boney segments preserved in a mud-based cement (breccia), and reconstructing the burial rituals associated with body position and grave environment features using an archaeothanatological method. This allowed me to address the questions: (1) Are there identifiable burial dispositional patterns at Cabeço da Arruda?; and (2) Through comparison of the similarities and differences in dispositional patterns and mortuary practices between the three main sites in the valley (Cabeço da Arruda, Cabeço da Amoreira, and Moita do Sebastião), are there identifiable characteristics throughout the entirety of the Muge Mesolithic? I determined that the most common burial disposition at Cabeço da Arruda was dorsal decubitus with a hyper-flexed lower limb which was positioned over the thorax. The most common grave features were for the body to be interred in an oval, concave pit with lateral space and external wrappings constricting the upper limb and thorax. These patterns constitute burial rituals because their repetition, with minimal individual variation, is indicative of prescribed behaviours occurring during the internment phase. When including osteobiographical data into these interpretations, no statistical pattern was identified for age (neonates, nonadults, adults) or sex (female or male) across the burial ritual data. These interpretations were consistent with the frequencies of previous burial dispositional patterns from the valley indicating that there were consistent rituals within the valley during the Mesolithic.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ MSpace at the Univer...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ MSpace at the Univer...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Nesca, Marcello;

    Introduction: Routinely collected electronic health data (RCEHD), can be comprised of structured, semi-structured, or unstructured information. Electronic medical records (EMRs), one type of RCEHD, often contain unstructured text data (UTD), which are typically prepared for analysis (i.e., preprocessed) and analyzed using natural language processing (NLP) techniques. At present, there are few studies about the specific types of NLP methods used to preprocess UTD to address data quality issues prior to analysis or modelling. Purpose & Objectives: The purpose was to examine preprocessing methods for UTD and evaluate the quality of UTD in EMRs. The objectives were to: 1) systematically document current research and practices for preprocessing UTD to describe or improve its quality, and 2) apply data quality indicators identified from current research and practices to UTD in EMRs from the Manitoba Primary Care Research Network and describe the quality of these data. Methods: Objective 1 involved a scoping review. Scopus, Web of Science, ProQuest, and EBSCOhost were searched for literature on current research and practices to prepare UTD for analysis, up to and including 2021. For objective 2, a case study was undertaken where data quality indicators and preprocessing methods identified in the scoping review were applied to UTD from EMRs. Results: 41 articles were included in the scoping review for objective 1; over 50% were published between 2016 and 2021 and over 90% were empirical research articles. Data quality indicator topics for UTD in EMRs included misspelled words, security, word variability, sources of noise, quality of annotations, ambiguous abbreviations, and manual annotations. For objective 2, we selected 193,206 clinical encounter notes from EMRs between 1985 and 2020. Overall, the clinical encounter notes contained an average (standard deviation [SD]) of 27.3 (27.0) stop words, 25.7 (27.8) punctuation symbols, 12.1 (11.1) spelling errors, and 2.9 (2.6) special characters. The average (SD) length of a clinical encounter note was 555.8 (551.1) characters, and 71.5 (59.7) words. Lexical diversity, had a mean (SD) of 86.2 (11.9). Conclusion: This study identified multiple data quality indicators that have been used to preprocess UTD in published literature and demonstrated their application to real-world data.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ MSpace at the Univer...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ MSpace at the Univer...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Hoy, Declan;

    As contemporary art has expanded to encompass further disparate activities under its umbrella, the various institutions of art can be looked to as the only constant and defining characteristic of art. These institutions are often seen in sharp contrast to spontaneous collectivism, the real, and radical creativity—attributes deeply valued within contemporary art. This creates a troubling situation in which institutions are seen as limiting the possibility of what art could be, and artworks are perceived as needing to escape the very institutions which define them in order to be deemed worthy. In this structure, contemporary art follows and validates the logic of neoliberalism and its doctrine of anti-institutionalism, radical creativity, and hyper individualism. This text looks at a short overview of neoliberalism, the economic impact of neoliberalism on artists, and examines the work of artist Renzo Martins in relation to the issues of neoliberalism and institutionalism in art.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Scholarship@Western
    Other literature type . 2021
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      Scholarship@Western
      Other literature type . 2021
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Ansari Dezfuly, Niloufar;

    This study investigates the effects of language background (monolingual/bilingual and early/late bilingual exposure), knowledge of a tonal language and music experience on auditory discrimination by employing tone and vowel discrimination tasks. A total number of 8,769 observations were analyzed using logistic regression to answer the following questions: (1) Do vowel and tone discrimination abilities correlate with language background in diverse groups of speakers such as monolinguals and bilinguals of different types (early/late bilinguals)? (2) Does musical training affect tone and vowel discrimination? (3) Does knowledge of tonal language affect tone discrimination? The findings suggest that with regard to vowel discrimination, the only effective variable is early bilingual exposure. In the case of tone discrimination, early bilingual exposure, knowledge of a tonal language and music experience all have positive effects, while bilingualism (independent of early or late bilingual exposure) is associated with less accurate performance. The results suggest the positive impact of early bilingual exposure, knowledge of a tonal language and music experience on enhancing auditory discrimination and auditory sensory memory. Through its focus on the effects of language and music experience on auditory discrimination, this study contributes to the fields of linguistics and psycholinguistics.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Scholarship@Western
    Other literature type . 2021
    License: CC BY
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      Scholarship@Western
      Other literature type . 2021
      License: CC BY
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Priest, Allen G;

    This dissertation explores the impact of hegemonic masculinity, in the early Cold War era, on the electoral politics of Canada and the United States. It situates itself in the years between 1949 and 1963, arguably the height of nuclear fear, at a time when masculine ideals were adjusting to an uncertain postwar reality. Previous scholarship has established that the Cold War brought with it a retreat into domesticity, followed by an emergent “crisis” of masculinity. This monograph contributes to the historiography by demonstrating that the masculine architypes of the early Cold War are frequently reflected in electoral discourse. It also highlights how postwar fears about masculinity align closely to the evolution of public understanding, and growing anxiety, about nuclear weaponry. Early chapters, which follow the political tenures of Louis St. Laurent and Dwight Eisenhower, establish that their ability to project themselves as reassuring, paternalistic father-figures was crucial to their electoral success. When combined with the portrayal of opponents as outside the bounds of hegemonic masculinity, it was a strategy that won elections. However, as the 1950s progressed, concerns about nuclear weaponry and fears about eroding manhood entered the public discourse. These new anxieties quickly rendered the paternalistic approach to governance insufficient. In its place, a more forceful brand of leadership emerged. It was focused on countering the malaise of the late 1950s by utilizing the nostalgia of the “self-made man” and promising a return to the individualism of the frontier-era. The candidacies of both John Diefenbaker and John F. Kennedy benefitted greatly from this approach, as both men promised to push towards “new” frontiers.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Scholarship@Western
    Other literature type . 2021
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      Scholarship@Western
      Other literature type . 2021
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Subramanian, Sandeep;

    Cette thèse fait des petits pas dans la construction et la compréhension des systèmes d'apprentissage des représentations neuronales et des modèles génératifs pour le traitement du langage naturel. Il est présenté comme une thèse par article qui contient quatre travaux. Dans le premier article, nous montrons que l'apprentissage multi-tâches peut être utilisé pour combiner les biais inductifs de plusieurs tâches d'apprentissage auto-supervisées et supervisées pour apprendre des représentations de phrases distribuées de longueur fixe à usage général qui obtiennent des résultats solides sur les tâches d'apprentissage par transfert en aval sans tout modèle de réglage fin. Le deuxième article s'appuie sur le premier et présente un modèle génératif en deux étapes pour le texte qui modélise la distribution des représentations de phrases pour produire de nouveaux plongements de phrases qui servent de "contour neuronal" de haut niveau qui est reconstruit en mots avec un récurrent neuronal autorégressif conditionnel décodeur. Le troisième article étudie la nécessité de représentations démêlées pour la génération de texte contrôlable. Une grande partie des systèmes de génération de texte contrôlables reposent sur l'idée que le contrôle d'un attribut (ou d'un style) particulier nécessite la construction de représentations dissociées qui séparent le contenu et le style. Nous démontrons que les représentations produites dans des travaux antérieurs qui utilisent la formation contradictoire du domaine ne sont pas dissociées dans la pratique. Nous présentons ensuite une approche qui ne vise pas à apprendre des représentations démêlées et montrons qu'elle permet d'obtenir des résultats nettement meilleurs que les travaux antérieurs. Dans le quatrième article, nous concevons des modèles de langage de transformateur qui apprennent les représentations à plusieurs échelles de temps et montrent que ceux-ci peuvent aider à réduire l'empreinte mémoire importante de ces modèles. Il présente trois architectures multi-échelles différentes qui présentent des compromis favorables entre la perplexité et l'empreinte mémoire. This thesis takes baby steps in building and understanding neural representation learning systems and generative models for natural language processing. It is presented as a thesis by article that contains four pieces of work. In the first article, we show that multi-task learning can be used to combine the inductive biases of several self-supervised and supervised learning tasks to learn general-purpose fixed-length distributed sentence representations that achieve strong results on downstream transfer learning tasks without any model fine-tuning. The second article builds on the first and presents a two-step generative model for text that models the distribution of sentence representations to produce novel sentence embeddings that serves as a high level ``neural outline'' that is reconstructed to words with a conditional autoregressive RNN decoder. The third article studies the necessity of disentangled representations for controllable text generation. A large fraction of controllable text generation systems rely on the idea that control over a particular attribute (or style) requires building disentangled representations that separate content and style. We demonstrate that representations produced in previous work that uses domain adversarial training are not disentangled in practice. We then present an approach that does not aim to learn disentangled representations and show that it achieves significantly better results than prior work. In the fourth article, we design transformer language models that learn representations at multiple time scales and show that these can help address the large memory footprint these models typically have. It presents three different multi-scale architectures that exhibit favorable perplexity vs memory footprint trade-offs.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Papyrus : Dépôt inst...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Papyrus : Dépôt inst...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Chafouleas, Geneviève;

    Plusieurs avancées utilisant le discours obtenu de la tâche de description d’image ont été réalisées dans la détection de la maladie d’Alzheimer (AD). L’utilisation de caractéristiques linguistiques et acoustiques sélectionnées manuellement ainsi que l’utilisation de méthodologies d’apprentissage profond ont montré des résultats très prometteurs dans la classification des patients avec AD. Dans ce mémoire, nous comparons les deux méthodologies sur la scène Cookie Theft du Boston Aphasia Examination en entrainant des modèles avec des caractéristiques sélectionnées à partir des extraits textuels et audio ainsi que sur un modèle d’apprentissage profond BERT. Nos modèles sont entrainés sur l’ensemble de données ADReSS challenge plus récent et évaluées sur l’ensemble de données CCNA et vice versa pour mesurer la généralisation des modèles sur des exemples jamais vus dans des ensembles de données différents. Une évaluation détaillée de l’interprétabilité des modèles est effectuée pour déterminer si les modèles ont bien appris les représentations reliées à la maladie. Nous observons que les modèles ne performent pas bien lorsqu’ils sont évalués sur différents ensembles de données provenant du même domaine. Les représentations apprises des modèles entrainés sur les deux ensembles de données sont très différentes, ce qui pourrait expliquer le bas niveau de performance durant l’étape d’évaluation. Même si nous démontrons l’importance des caractéristiques linguistiques sur la classification des AD vs contrôle, nous observons que le meilleur modèle est BERT avec un niveau d’exactitude de 62.6% sur les données ADReSS challenge et 66.7% sur les données CCNA. Many advances have been made in the early diagnosis of Alzheimer’s Disease (AD) using connected speech elicited from a picture description task. The use of hand built linguistic and acoustic features as well as Deep Learning approaches have shown promising results in the classification of AD patients. In this research, we compare both approaches on the Cookie Theft scene from the Boston Aphasia Examination with models trained with features derived from the text and audio extracts as well as a Deep Learning approach using BERT. We train our models on the newer ADReSS challenge dataset and evaluate on the CCNA dataset and vice versa in order to asses the generalisation of the trained model on unseen examples from a different dataset. A thorough evaluation of the interpretability of the models is performed to see how well each of the models learn the representations related to the disease. It is observed that the models do not perform well when evaluated on a different dataset from the same domain. The selected and learned representations from the models trained on either dataset are very different and may explain the low performance in the evaluation step. While we demonstrate the importance of linguistic features in the classification of AD vs non-AD, we find the best overall model is BERT which achieves a test accuracy of 62.6% on the ADRess challenge dataset and 66.7% on the CCNA dataset. co-direction : Simona Brambati

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Papyrus : Dépôt inst...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Papyrus : Dépôt inst...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Galic, Slavena;

    Clastic, upper Albian-lower Cenomanian strata were deposited in a low-accommodation backbulge depozone of the Western Canada Foreland Basin in SW Alberta. These strata are lithologically very heterogeneous and encompass a spectrum of depositional environments along an alluvial to offshore transect. These rocks are assigned, in subsurface, to the Lower Colorado Group, and in outcrop to the upper Blairmore Group. Lithological heterogeneity, as a result of rapid lateral facies changes, resulted in diverse nomenclature that obscured genetic relationships between time-equivalent strata. The present study integrates wireline log, core, and outcrop data to establish a high-resolution allostratigraphic framework which allowed recognition of the Basal Colorado, Joli Fou, Viking and Westgate alloformations, in ascending order. Each alloformation comprises several allomembers and parasequences. The Basal Colorado alloformation is a NE thinning wedge that progressively onlaps lower Albian Mannville Group strata. Deposition took place in a brackish-water embayment open to the south. Basal Colorado strata correlate with the Lynx Creek Member of the Mill Creek Formation in outcrop. The Joli Fou and Viking alloformations have a broadly sheet-like geometry. Both alloformations comprise three allomembers, composed of a complex array of river-dominated and mixed-influence deltaic successions. The location of successive deltas was strongly influenced by differential compaction of underlying deltas. Sandstone-rich Joli Fou rocks pass northward into offshore mudstone. To the south and west, marine Joli Fou and Viking deposits grade laterally into alluvial facies. Only the upper part of the Westgate alloformation extends into SW Alberta. Tectonic tilting is indicated by the lowermost (alluvial) and uppermost (marine) Westgate parasequences, which are SW and NE thickening wedges, respectively. Paleo-valleys, typically ~20 m deep, are incised into the top surface of most allomembers. Different examples of valley incision and fill can be attributed to both sea-level changes, and also to climatically-controlled changes in the sediment load to discharge ratio. Two pulses of thrust-induced loading and a long term (>1 myr) eustatic cycle provided the overall control on stratal architecture, whereas climate-controlled cycles in the ~400 and 100 kyr band exerted an important control on the development of allomembers and parasequences. Eustatic changes are estimated to have been ~20 – 30 m.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Scholarship@Western
    Other literature type . 2021
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Scholarship@Westernarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      Scholarship@Western
      Other literature type . 2021