• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher:
    
    • Klubička, Filip (21)
    • Ljubešić, Nikola (17)
    • Toral, Antonio (7)
    • Erjavec, Tomaž (5)
    • Esplà-Gomis, Miquel (5)
    • Farkaš, Daša (4)
    • Miličević, Maja (4)
    • Ortiz Rojas, Sergio (4)
    • Boras, Damir (2)
    • Dujmić, Barbara (2)
    • Filko, Matea (2)
    • Kelleher, John D. (2)
    • Kranjčić, Denis (2)
    • Sánchez-Cartagena, Víctor M. (2)
    • Vuković, Teodora (2)
    • Agić, Željko (1)
    • Batanović, Vuk (1)
    • Nedumpozhimana, Vasudevan (1)
    • Papavassiliou, Vassilis (1)
    • Prokopidis, Prokopis (1)
    •   more
  • 
    Year:
    
    • 2022 (1)
    • 2018 (3)
    • 2017 (5)
    • 2016 (12)
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access

Search in the Catalogues and Directories

All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year Sort by creator [A → Z]' creator [Z → A]' publishing year ↑ (asc)' publishing year ↓ (desc)' title [A → Z]' title [Z → A]' Simple Search Page: 1 2 Hits 1 – 20 of 21 1 Shapley Idioms: Analysing BERT Sentence Embeddings for General Idiom Token Identification Nedumpozhimana, Vasudevan; Klubička, Filip; Kelleher, John D. In: Front Artif Intell (2022) Abstract: This article examines the basis of Natural Language Understanding of transformer based language models, such as BERT. It does this through a case study on idiom token classification. We use idiom token identification as a basis for our analysis because of the variety of information types that have previously been explored in the literature for this task, including: topic, lexical, and syntactic features. This variety of relevant information types means that the task of idiom token identification enables us to explore the forms of linguistic information that a BERT language model captures and encodes in its representations. The core of this article presents three experiments. The first experiment analyzes the effectiveness of BERT sentence embeddings for creating a general idiom token identification model and the results indicate that the BERT sentence embeddings outperform Skip-Thought. In the second and third experiment we use the game theory concept of Shapley Values to rank the usefulness of individual idiomatic expressions for model training and use this ranking to analyse the type of information that the model finds useful. We find that a combination of idiom-intrinsic and topic-based properties contribute to an expression's usefulness in idiom token identification. Overall our results indicate that BERT efficiently encodes a variety of information from topic, through lexical and syntactic information. Based on these results we argue that notwithstanding recent criticisms of language model based semantics, the ability of BERT to efficiently encode a variety of linguistic information types does represent a significant step forward in natural language understanding. Keyword: Artificial Intelligence URL: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8964145/ https://doi.org/10.3389/frai.2022.813967 BASE Hide details 2 Training corpus hr500k 1.0 Ljubešić, Nikola; Agić, Željko; Klubička, Filip. - : Jožef Stefan Institute, 2018 BASE Show details 3 Quantitative Fine-Grained Human Evaluation of Machine Translation Systems: a Case Study on English to Croatian ... Klubička, Filip; Toral, Antonio; Sánchez-Cartagena, Víctor M.. - : arXiv, 2018 BASE Show details 4 Is it worth it? Budget-related evaluation metrics for model selection ... Klubička, Filip; Salton, Giancarlo D.; Kelleher, John D.. - : arXiv, 2018 BASE Show details 5 Croatian Twitter training corpus ReLDI-NormTag-hr 1.1 Ljubešić, Nikola; Farkaš, Daša; Klubička, Filip. - : Jožef Stefan Institute, 2017 BASE Show details 6 Serbian Twitter training corpus ReLDI-NormTag-sr 1.0 Ljubešić, Nikola; Farkaš, Daša; Klubička, Filip. - : Jožef Stefan Institute, 2017 BASE Show details 7 Croatian Twitter training corpus ReLDI-NormTag-hr 1.0 Ljubešić, Nikola; Farkaš, Daša; Klubička, Filip. - : Jožef Stefan Institute, 2017 BASE Show details 8 Serbian Twitter training corpus ReLDI-NormTag-sr 1.1 Ljubešić, Nikola; Farkaš, Daša; Klubička, Filip. - : Jožef Stefan Institute, 2017 BASE Show details 9 Fine-grained human evaluation of neural versus phrase-based machine translation ... Klubička, Filip; Toral, Antonio; Sánchez-Cartagena, Víctor M.. - : arXiv, 2017 BASE Show details 10 Serbian-English parallel corpus srenWaC 1.0 Ljubešić, Nikola; Esplà-Gomis, Miquel; Ortiz Rojas, Sergio. - : Jožef Stefan Institute, 2016 BASE Show details 11 Finnish-English parallel corpus fienWaC 1.0 Ljubešić, Nikola; Esplà-Gomis, Miquel; Ortiz Rojas, Sergio. - : Jožef Stefan Institute, 2016 BASE Show details 12 Serbian web corpus srWaC 1.1 Ljubešić, Nikola; Klubička, Filip. - : Jožef Stefan Institute, 2016 BASE Show details 13 Inflectional lexicon hrLex 1.0 Ljubešić, Nikola; Klubička, Filip. - : Faculty of Humanities and Social Sciences, University of Zagreb, 2016 BASE Show details 14 Inflectional lexicon hrLex 1.2 Ljubešić, Nikola; Klubička, Filip; Boras, Damir. - : Faculty of Humanities and Social Sciences, University of Zagreb, 2016 BASE Show details 15 Tourism English-Croatian Parallel Corpus 2.0 Toral, Antonio; Esplà-Gomis, Miquel; Klubička, Filip. - : Abu-MaTran project, 2016 BASE Show details 16 Inflectional lexicon srLex 1.2 Ljubešić, Nikola; Klubička, Filip; Boras, Damir. - : Faculty of Humanities and Social Sciences, University of Zagreb, 2016 BASE Show details 17 Croatian-English parallel corpus hrenWaC 2.0 Ljubešić, Nikola; Esplà-Gomis, Miquel; Ortiz Rojas, Sergio. - : Jožef Stefan Institute, 2016 BASE Show details 18 Inflectional lexicon srLex 1.0 Ljubešić, Nikola; Klubička, Filip. - : Faculty of Humanities and Social Sciences, University of Zagreb, 2016 BASE Show details 19 Croatian web corpus hrWaC 2.1 Ljubešić, Nikola; Klubička, Filip. - : Jožef Stefan Institute, 2016 BASE Show details 20 Slovene-English parallel corpus slenWaC 1.0 Ljubešić, Nikola; Esplà-Gomis, Miquel; Ortiz Rojas, Sergio. - : Jožef Stefan Institute, 2016 BASE Show details Page: 1 2

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 0 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 0 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 0 BDSL 0 IDS Bibliografie zur deutschen Grammatik 0 IDS Bibliografie zur Gesprächsforschung 0 IDS Konnektoren im Deutschen 0 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 0 Linked Open Data catalogues Annohub 0 Online resources Link directory 0 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 21 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0