Quick search
Advanced search in
Research outcomes
Field to searchTerm
Add rule
Filters (6)
Filters
Clear All

Digital Humanities and Cultural Heritage Publications Research data Other research products Conference object Preprint EC|H2020 QA English Digital Humanities and Cultural He...

Filters
Clear All

Digital Humanities and Cultural Heritage Publications Research data Other research products Conference object Preprint EC|H2020 QA English Digital Humanities and Cultural He...

The following results are related to Digital Humanities and Cultural Heritage. Are you interested to view more results? Visit OpenAIRE - Explore.
Download Results
12 research outcomes, page 1 of 2
  • publication . Article . Conference object . Preprint . 2021
    The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing
    Open Access English
    Authors:
    Valentina Pyatkin; Shoval Sadde; Aynat Rubinstein; Paul Portner; Reut Tsarfaty;
    Persistent Identifiers

    doi: 10.18653/v1/2021.acl-long.77 , 10.48550/arxiv.2106.08037

    Project: EC | NLPRO (677352)

    Modality is the linguistic ability to describe events with added information such as how desirable, plausible, or feasible they are. Modality is important for many NLP downstream tasks such as the detection of hedging, uncertainty, speculation, and more. Previous studie...

    Add to ORCIDorcid
  • publication . Conference object . 2017
    Autonomous Crowdsourcing through Human-Machine Collaborative Learning
    Open Access English
    Authors:
    Azad Abad; Moin Nabi; Alessandro Moschitti;
    Persistent Identifiers

    doi: 10.1145/3077136.3080666

    Publisher: ACM
    Project: EC | CogNet (671625)

    In this paper, we introduce a general iterative human-machine collaborative method for training crowdsource workers: the classifier (i.e., the machine) selects the highest quality examples for training the crowdsource workers (i.e., the humans). Then, the latter annotat...

    Add to ORCIDorcid
  • publication . Conference object . Other literature type . 2017
    The SUMMA Platform Prototype
    Open Access English
    Authors:
    Renars Liepins; Ulrich Germann; Guntis Barzdins; Alexandra Birch; Steve Renals; Susanne Weber; Peggy van der Kreeft; Hervé Bourlard; João Prieto; Ondrej Klejch; ...
    Persistent Identifiers

    doi: 10.5281/zenodo.834348 , 10.5281/zenodo.834347 , 10.18653/v1/e17-3029

    Publisher: Association for Computational Linguistics
    Country: Switzerland
    Project: EC | SUMMA (688139)

    We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring. The platform contains a rich suite of low-level and high-level natural language processing technologies: automatic speech recognition of broadcast media, mach...

    Add to ORCIDorcid
  • publication . Conference object . Preprint . Contribution for newspaper or weekly magazine . Article . 2017
    Speech Recognition Challenge in the Wild: Arabic MGB-3
    Open Access English
    Authors:
    Ahmed Ali; Stephan Vogel; Steve Renals;
    Persistent Identifiers

    doi: 10.48550/arxiv.1709.07276 , 10.1109/asru.2017.8268952

    handle: 20.500.11820/58b2f0cb-7cce-471a-b0dd-5ead073a3034

    Country: United Kingdom
    Project: EC | SUMMA (688139)

    This paper describes the Arabic MGB-3 Challenge — Arabic Speech Recognition in the Wild. Unlike last year's Arabic MGB-2 Challenge, for which the recognition task was based on more than 1,200 hours broadcast TV news recordings from Aljazeera Arabic TV programs, MGB-3 em...

    Add to ORCIDorcid
  • publication . Article . Preprint . 2017
    An Empirical Analysis of NMT-Derived Interlingual Embeddings and their Use in Parallel Sentence Identification
    Open Access English
    Authors:
    Cristina España-Bonet; Adam Csaba Varga; Alberto Barrón-Cedeño; Josef van Genabith;
    Persistent Identifiers

    doi: 10.48550/arxiv.1704.05415 , 10.1109/jstsp.2017.2764273

    Country: Italy
    Project: EC | QT21 (645452)

    End-to-end neural machine translation has overtaken statistical machine translation in terms of translation quality for some language pairs, specially those with large amounts of parallel data. Besides this palpable improvement, neural networks provide several new prope...

    Add to ORCIDorcid
  • publication . Conference object . 2017
    RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations
    Open Access English
    Authors:
    Kateryna Tymoshenko; Alessandro Moschitti; Massimo Nicosia; Aliaksei Severyn;
    Persistent Identifiers

    doi: 10.18653/v1/p17-4014

    Publisher: Association for Computational Linguistics
    Project: EC | CogNet (671625)
    Add to ORCIDorcid
  • publication . Conference object . 2016
    Learning to Rank Non-Factoid Answers
    Open Access English
    Authors:
    Kateryna Tymoshenko; Daniele Bonadiman; Alessandro Moschitti;
    Persistent Identifiers

    doi: 10.1145/2983323.2983906

    Publisher: ACM Press
    Project: EC | CogNet (671625)

    Recent initiatives in IR community have shown the importance of going beyond factoid Question Answering (QA) in order to design useful real-world applications. Questions asking for descriptions or explanations are much more difficult to be solved, e.g., the machine lear...

    Add to ORCIDorcid
  • publication . Conference object . Preprint . Contribution for newspaper or weekly magazine . Article . 2016
    The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition
    Open Access English
    Authors:
    Ahmed Ali; Peter Bell; James Glass; Yacine Messaoui; Hamdy Mubarak; Steve Renals; Yifan Zhang;
    Persistent Identifiers

    doi: 10.48550/arxiv.1609.05625 , 10.1109/slt.2016.7846277

    handle: 20.500.11820/41f930a7-0ccc-4fae-a443-b94a9196e105

    Country: United Kingdom
    Project: EC | SUMMA (688139)

    This paper describes the Arabic Multi-Genre Broadcast (MGB-2) Challenge for SLT-2016. Unlike last year's English MGB Challenge, which focused on recognition of diverse TV genres, this year, the challenge has an emphasis on handling the diversity in dialect in Arabic spe...

    Add to ORCIDorcid
  • publication . Conference object . 2016
    ConvKN at SemEval-2016 Task 3: Answer and Question Selection for Question Answering on Arabic and English Fora
    Open Access English
    Authors:
    Alberto Barrón-Cedeño; Giovanni Da San Martino; Shafiq Joty; Alessandro Moschitti; Fahad Al-Obaidli; Salvatore Romeo; Kateryna Tymoshenko; Antonio Uva;
    Persistent Identifiers

    doi: 10.18653/v1/s16-1138

    Publisher: Association for Computational Linguistics
    Project: EC | CogNet (671625)
    Add to ORCIDorcid
  • publication . Conference object . 2015
    Assessing the Impact of Syntactic and Semantic Structures for Answer Passages Reranking
    Closed Access English
    Authors:
    Kateryna Tymoshenko; Alessandro Moschitti;
    Persistent Identifiers

    doi: 10.1145/2806416.2806490

    Publisher: ACM
    Project: EC | CogNet (671625)

    In this paper, we extensively study the use of syntactic and semantic structures obtained with shallow and deeper syntactic parsers in the answer passage reranking task. We propose several dependency-based structures enriched with Linked Open Data (LD) knowledge for rep...

    Add to ORCIDorcid
12 research outcomes, page 1 of 2