Powered by OpenAIRE graph
Found an issue? Give us feedback

Institut National de lAudiovisuel

Institut National de lAudiovisuel

8 Projects, page 1 of 2
  • Funder: ANR Project Code: ANR-12-CORD-0012
    Funder Contribution: 793,423 EUR

    "Large catalogues are moving from the database metadata management age using specific Information Science and Libraries formats, to the Web age using Semantic Web standard languages (RDF / S, OWL). This development, bringing many advantages (better document availability, increased data exchange capabilities, creation of new search / use services for documents), raises important issues about the quality of document databases. This project aims to develop mechanisms to: • describe the quality of an existing document database; • maintain a given level of quality by controlling updates on such databases; • improve the quality of a database; • exploit these databases according to their level of quality (eg the search for documents or combination of bases). Representing data using Semantic Web standards allows for a Knowledge Representation approach to this problem. This approach will allow on one hand to give a logical semantics to the notion of quality and, on the other, to use reasoning mechanisms for dealing with various problems. This approach is rooted on the (i) formalization of knowledge found in document catalogues, (ii) the development of a quality model for the individual entities (named entities) identification problem, (iii) the definition of a trust model suitable for reconciliation and different source information fusion and (iv) the discovery of entity identification characteristics and their manipulation by different techniques (logical, numerical, probabilistic, etc.). A large part of the project is devoted to the evaluation of the proposed approach by experiments conducted on suitable test benchmarks and the development of demonstrators adapted to the two document databases owners involved in the project. The consortium brings together five complementary partners: two major national players of document catalogues and three research groups of computer scientists. The Bibliographic Agency for Higher Education (ABES) and the Institut National de l'Audiovisuel (INA) are managing very large document databases and are heavily involved, both at a national and international level, in the exposure, standardization, interconnection and use of their metadata. The teams of the LIG, LIRMM and LRI involved in this project have a strong expertise in databases, knowledge representation and semantic web. Furthermore, numerous research connections exist between the project partners. The skills of scientific partners and links forged between them as part of joint projects are very important to the success of this multidisciplinary project that involves both Information Science and Libraries as information technology, and should impact not only the field of document databases but also the Web of Data (""Linked Data"")."

    more_vert
  • Funder: ANR Project Code: ANR-23-IAS1-0001
    Funder Contribution: 599,997 EUR

    The Pantagruel project is an ambitious initiative that aims to develop and evaluate multimodal (written, spoken, pictograms) and inclusive linguistic models for French. The project draws on the expertise of researchers from different disciplines, including computer science, signal processing, sociology, and linguistics, to ensure diversity of perspectives, as well as the reliability and relevance of results. The main contributions of the project are the development of freely available self-supervised models for French, including one to three of the modalities for the general and clinical domains. The project will not only produce models but also design test benches to evaluate the generalization of such models, building on the experience gained in the FlauBERT and LeBenchmark projects. Part of the project will be devoted to the biases and stereotypes conveyed in the training corpora and in the downstream models. An ethics committee will help limit the amplification effect of bias within the training corpora, in particular by working on the demographic characteristics of the speakers (for audio or transcribed speech) and of the authors (for part of the written data). We will thus be able to compare the models learned on training corpora with variable proportions for these characteristics, such as gender. This study will quantify to what extent the predictions of the language models are reliable reflections of the upstream corpora and to better control the way in which they can be used as social scientific research tools. The project will develop software components that will facilitate the integration of language models into various applications and allow the development of innovative solutions that exploit the power of multimodal French language models. These tools are particularly intended for non-computer scientists such as those who are members of the consortium (sociologists, linguists, doctors, speech therapists), researchers from other fields, or artists. The Pantagruel project thus has the potential to significantly advance the state of the art in multimodal language models and to have disseminate the use of these models in a wide range of applied fields, ranging from healthcare to the humanities and the social sciences.

    more_vert
  • Funder: ANR Project Code: ANR-13-CORD-0016
    Funder Contribution: 1,008,420 EUR

    "The ARA CAMPUS project takes place in the context of the digital humanities. It is devoted to the central problem of the constitution and use of the scientific heritage of the social sciences and humanities (SSH) in form of digital audiovisual archives (AV). By adopting a cognitive and semiotic approach of AV archives (popularized through the slogan of the ""linguistic turn"" of archives), the ARA Campus project gives a full priority to the analysis of the specific structural (thematic, narrative, discursive, pragmatic, visual and acoustic , ...) characteristics of any AV media. The basic assumption here is that this approach is able to satisfy the multiple needs and expectations of each actor (teacher, researcher, student, doctoral, professional expert, ...) who wants to actively intervene on audiovisual media in order to “transform” it into an intellectual resource properly speaking - in an appropriate resource for specific contexts of use: teaching, research, development of a scientific heritage. With reference to this general framework, the partners of the consortium of the ARA Campus project intend to coordinate their efforts for 30 months of research and development around five major themes as follows: Priority 1: Development of a demonstrator of a software platform (called ARA Campus Studio) providing opportunities for (individual or collective) actors in the fields of SSH to achieve and maintain autonomously their personal archives of AV resources. Priority 2: Provision to any user of the ARA Campus platform with common meta-linguistic (terminological) resources ready for use for a personal archive project: 2.1) a core (“generic”) ontology for the SSH, a common thesaurus and basic models of description/indexing of AV resources; 2.2) work interface composed of interactive ""forms"" customizable to the specificities in the constitution, description and (re-)publishing of AV corpuses; 2.3) possibility of using common standards such as OAI, DC or LOM, languages and common thesauri (eg LCSH) to improve the usability of an archive based on an interoperable organization of knowledge through the implementation of SKOS. Priority 3: Provision to any user of the platform ARA Campus platform of a rich library of templates for the (automatic and / or ""author"") publication of audiovisual corpuses: customized templates for the publishing of AV portals, (semi- automatic) templates for the publishing of video-files, templates for different kinds of access to AV corpus, ... Priority 4: Implementation of (meta-) AAR Campus portal with: 4.1) a central access to all other portals based on the same technology and a research motor based on a simplified shared catalogue integrating OAI standard; 4.2) (for any identified and authorized user) a sustainable access to all applications of the ARA Campus platform and to all shareable resources. Priority 5: Close cooperation with main stakeholders in the field of digital humanities in France: 6.1) first category of stakeholders: the major French institutional programs: education, including the UNT UOH, the CERIMES and Canal-U; research including the CCSD (CNRS) and its Open Archives (MédiHal, Hal-Video), ISIDORE, the program IR Corpus and the TGE Adonis; governance: Athena Alliance, Campus Condorcet, PRS Hesam, UNPIDF, network of MSH, ...); 6.2) second category of stakeholders: individual actors (teachers, researchers, PhD students, ...) and collective actors (research laboratories, ...) involved in projects aiming at the constitution and exploitation of - personal - AV archives."

    more_vert
  • Funder: ANR Project Code: ANR-17-CE38-0010
    Funder Contribution: 565,947 EUR

    The general objective of the ANTRACT project is the analysis of the images and sounds produced weekly in the framework of an independent company created in 1945, les Actualités françaises (French News), over twenty five years. This major cinematographic vector, already partially worked, has never been the subject of a systematic analysis. Thanks to recent technological tools for the analysis of textual and audiovisual contents, image, video and sound analysis, automatic speech transcription and textometry in particular, the aim is to provide the scientific community with new analysis frameworks. Technological, historical, methodological and heritage issues are identified. The technological challenge lies in the improvement of the analysis technologies of speech and image modalities, in the joint exploitation of available modalities (image, text and speech) for qualitative and quantitative analysis, and in the specification and implementation of tools adapted to the documents treated and to the uses prescribed by the historical analysis of this corpus. The historical issue is divided into four orientations: 1) the evolution of France in its colonial, economic, social, political, cultural and international dimension; 2) the way in which media representations and social facts are articulated; 3) the memorial dimension and 4) the construction of an audiovisual history. The methodological challenge lies in the implementation of a coherent and comprehensive methodological approach and is the general objective of the project. The heritage issue lies in the importance of this corpus which the project proposes to enrich and make available to researchers and general public. The project presents both fundamental research dimensions for historical research and for its transdisciplinary approach, as well as the dimensions of experimental development for technological work, which largely involves adapting the tools of the partners to the uses and the data of the project. The choice is made to deposit it as an experimental development project. The project is coordinated by Pascale Goetschel, Director of the Center for Social History of the 20th Century (Paris 1). The consortium brings together academic, industrial and institutional partners, specialized and recognized in the fields of history, textometry, image and video analysis, speech processing and audiovisual archives management. The project is organized according to a principle that underpins the transdisciplinary aspect of the project. Sub-project 1 is reserved for the coordination of the project. Sub-project 2 groups together tasks related to corpus gathering, data management and technological research. Sub-project 3 is the main place for methodological and transdisciplinary reflection, following an iterative principle of successive phases of expressions of needs, experiments and feedback. Sub-project 4 regroups the tasks that produce the project's actual results in terms of science, technology, industry and heritage. At the end of the project, the results will be made available as widely as possible. The corpus enriched with data and metadata will be made available to the scientific and technological community. The software modules will be offered in open source whenever possible and a web portal will be opened. In addition, the Voxolab company will integrate the results of research carried out in speech transcription.

    more_vert
  • Funder: ANR Project Code: ANR-23-SSRP-0014
    Funder Contribution: 249,843 EUR

    Largely inspired by what we have been able to do for at least ten years, our TEMOINS3945 project is to construct together with structures from civil society a scientific program with a strong memorial and societal dimension. The originality of the project is to propose an unpublished volume of testimonies collected at various periods about the Resistance and what me name the deportation of repression, annotated and documented. As the last witnesses disappear, it is imperative to provide reference corpora. With TEMOINS3945, we shall put hundreds of written, audio and audiovisual testimonies online, accompanied by a presentation, a critical apparatus, keywords and additional documents (family archives and public archives). We touch on the heart of the scientific process with identification of sources and constitution of a critical apparatus, since we know that sources do not speak for themselves. The search for additional documents is also part of this heuristic approach. This work will be carried out jointly by academics and by networks of correspondents from “civil society”. These partners consider the transmission of memory to be one of their top priorities. The associated foundations, like the Memorial, have a scientific council. The partnership is long-standing, particularly within the MATRICE team (2011-2024), of which the Foundations and the Rivesaltes Camp Memorial are partners in a Consortium agreement.

    more_vert
Powered by OpenAIRE graph
Found an issue? Give us feedback

Do the share buttons not appear? Please make sure, any blocking addon is disabled, and then reload the page.

Content report
No reports available
Funder report
No option selected
arrow_drop_down

Do you wish to download a CSV file? Note that this process may take a while.

There was an error in csv downloading. Please try again later.