Projekt

Zurück zur Übersicht

MODERN: Modeling discourse entities and relations for coherent machine translation

Titel Englisch MODERN: Modeling discourse entities and relations for coherent machine translation
Gesuchsteller/in Popescu-Belis Andrei
Nummer 147653
Förderungsinstrument Sinergia
Forschungseinrichtung IDIAP Institut de Recherche
Hochschule Idiap Research Institute - IDIAP
Hauptdisziplin Informatik
Beginn/Ende 01.08.2013 - 31.07.2017
Bewilligter Betrag 1'243'723.00
Alle Daten anzeigen

Alle Disziplinen (2)

Disziplin
Informatik
Weitere Sprachen

Keywords (5)

discourse; natural language processing; machine translation; pronominal anaphora; co-reference

Lay Summary (Französisch)

Lead
Les systèmes de traduction automatique actuels opèrent phrase après phrase et ne propagent pas les informations acquises plus tôt dans un texte vers la suite du texte. Pourtant, cela peut-être utile, et parfois indispensable, à la traduction correcte de certains mots ou expressions qui dépendent des précédents choix de traduction. Par exemple, les références aux entités (noms propres, noms communs, ou pronoms) doivent être traduites de manière cohérente tout au long d’un texte.
Lay summary

Le but du projet MODERN est de détecter automatiquement les relations de dépendance entre les éléments d’un texte et d’intégrer ces informations au sein de systèmes de traduction automatique, afin d’améliorer de façon mesurable la qualité des textes traduits.  MODERN étudiera plus particulièrement les expressions référentielles, telles les groupes nominaux et les pronoms, et les relations discursives entre phrases. Ces deux types d’informations sont reliés, et leur traduction cohérente est un élément important de la qualité d’une traduction. 

MODERN proposera des modèles formels combinant les entités et les relations discursives d’un texte, fondés sur des théories linguistiques et des observations expérimentales, et intégrant des informations sur les entités discursives provenant de ressources encyclopédiques externes.  Ces modèles seront implémentés dans un cadre statistique et seront intégrés aux deux principales approches utilisées actuellement en traduction automatique, à savoir les systèmes statistiques comme Moses, ou à base de règles comme Apertium. La mesure des améliorations apportées sera reliée aux effets sur les lecteurs humains des différents choix de traduction.

Le projet MODERN étudiera quatre langues : l’anglais, le français, l’allemand et le néerlandais, avec des textes issus de deux domaines : des textes sur les Alpes extraits du corpus Text+Berg et des textes législatifs européens portant sur l’environnement (JRC-Acquis et Europarl).

Le projet représente un effort collectif, avec la collaboration de chercheurs en traduction automatique, en linguistique et en traitement automatique des langues.  Cette collaboration conduira au développement de systèmes effectifs, qui seront évalués de manière objective et réaliste.  Grâce à sa nouvelle approche de la traduction globale d’un texte, MODERN sera à la pointe des recherches internationales visant la construction de systèmes de traduction automatique d’une qualité suffisante pour leur utilisation autonome.

Direktlink auf Lay Summary Letzte Aktualisierung: 24.07.2013

Verantw. Gesuchsteller/in und weitere Gesuchstellende

Mitarbeitende

Publikationen

Publikation
A quantitative approach to conceptual, procedural and pragmatic meaning: evidence from inter-annotator agreement
Grisot C. (2017), A quantitative approach to conceptual, procedural and pragmatic meaning: evidence from inter-annotator agreement, in Journal of Pragmatics, 117, 245-263.
Consistent Translation of Repeated Nouns using Syntactic and Semantic Cues
Pu X., Mascarell L., Popescu-Belis A. (2017), Consistent Translation of Repeated Nouns using Syntactic and Semantic Cues, in Proceedings of the 15th Conference of the European Chapter of the Association for Computational Ling, Valencia948-957, ACL, Philadelphia948-957.
Co-reference Resolution of Elided Subjects and Possessive Pronouns in Spanish-English Statistical Machine Translation
Rios A., Tuggener D. (2017), Co-reference Resolution of Elided Subjects and Possessive Pronouns in Spanish-English Statistical Machine Translation, in Proceedings of the 15th Conference of the European Chapter of the Association for Computational Ling, Valencia657-662, ACL, Philadelphia657-662.
Discourse connectives: theoretical models and empirical validations in humans and computers
Zufferey Sandrine, Popescu-Belis Andrei (2017), Discourse connectives: theoretical models and empirical validations in humans and computers, in Blochowiak Joanna (ed.), Springer, Berlin, -.
Evaluating discourse annotation: Some recent insights and new approaches
Hoek J., Scholman M. C. J. (2017), Evaluating discourse annotation: Some recent insights and new approaches, in Proceedings of the 13th Joint ACL�ISO Workshop on Interoperable Semantic Annotation (ISA-13), MontpellierACL, Philadelphia.
Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings
Rios A., Mascarell L., Sennrich R. (2017), Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings, in Proceedings of the 2nd Conference on Machine Translation (WMT 2017), Copenhagen11-19, ACL, Philadelphia11-19.
Lexical Chains meet Word Embeddings in Document-level Statistical Machine Translation
Mascarell L. (2017), Lexical Chains meet Word Embeddings in Document-level Statistical Machine Translation, in Proceedings of the 3rd Workshop on Discourse in Machine Translation (DiscoMT 2017), Copenhagen99-109, ACL, Philadelphia99-109.
Machine translation of Spanish personal and possessive pronouns using anaphora probabilities
Luong N. Q., Popescu-Belis A., Rios Gonzales A., Tuggener D. (2017), Machine translation of Spanish personal and possessive pronouns using anaphora probabilities, in Proceedings of the 15th Conference of the European Chapter of the Association for Computational Ling, Valencia631-636, ACL, Philadelphia631-636.
Methodological issues in the use of parallel directional corpora: A case study with English and French concessive connectives
Dupont M., Zufferey S. (2017), Methodological issues in the use of parallel directional corpora: A case study with English and French concessive connectives, in International Journal of Corpus Linguistics, 22(2), 270-297.
On temporality in discourse annotation: Theoretical and practical considerations
Evers-Vermeul Jacqueline, Hoek Jet, Scholman Merel (2017), On temporality in discourse annotation: Theoretical and practical considerations, in Second TextLink Action Conference, 8(2), 1-20.
Proceedings of the Third EMNLP Workshop on Discourse in Machine Translation (DiscoMT 2017)
Webber B., Popescu-Belis A., Tiedemann J. (ed.) (2017), Proceedings of the Third EMNLP Workshop on Discourse in Machine Translation (DiscoMT 2017), ACL, Philadelphia.
Processing connectives with a complex form-function mapping in L2: the case of French "en effet"
Zufferey S., Gygax P. M. (2017), Processing connectives with a complex form-function mapping in L2: the case of French "en effet", in Frontiers in Psychology: Language, 8, 1-11.
Segmenting discourse: Incorporating interpretation into segmentation?
Hoek J., Evers-Vermeul J., Sanders T. J. M. (2017), Segmenting discourse: Incorporating interpretation into segmentation?, in Corpus Linguistics and Linguistic Theory, 1.
Sense-Aware Statistical Machine Translation using Adaptive Context-Dependent Clustering
Pu X., Pappas N., Popescu-Belis A. (2017), Sense-Aware Statistical Machine Translation using Adaptive Context-Dependent Clustering, in Proceedings of the 2nd Conference on Machine Translation (WMT 2017), Copenhagen1-10, ACL, Philadelphia1-10.
Temporal coherence in discourse: theory and application for Machine Translation
Cristina Grisot (2017), Temporal coherence in discourse: theory and application for Machine Translation, in Blochowiak J. Grisot C. Durrelman-Tame S. and Laenzlinger C. (ed.), Springer, Berlin, 355-373.
Tense, Grammatical Aspect and Subjectivity: An Experimental Study Using Inter-Annotator Agreement Rates and Corpus-Based Data
Grisot C. (2017), Tense, Grammatical Aspect and Subjectivity: An Experimental Study Using Inter-Annotator Agreement Rates and Corpus-Based Data, in Corpus Pragmatics, 1.
Usage and processing of the French causal connectives 'car' and 'parce que'
Zufferey S., Mak W., Verbrugge S., Sanders T. (2017), Usage and processing of the French causal connectives 'car' and 'parce que', in Journal of French Language Studies, 1.
Using Coreference Links to Improve Spanish-to-English Machine Translation
Miculicich Werlen L., Popescu-Belis A. (2017), Using Coreference Links to Improve Spanish-to-English Machine Translation, in Proceedings of the EACL Workshop on Coreference Resolution beyond OntoNotes (CORBON), Valencia30-40, ACL, Philadelphia30-40.
Validation of an Automatic Metric for the Accuracy of Pronoun Translation (APT)
Miculicich Werlen L., Popescu-Belis A. (2017), Validation of an Automatic Metric for the Accuracy of Pronoun Translation (APT), in Proceedings of the EMNLP 3rd Workshop on Discourse in Machine Translation (DiscoMT), Copenhagen17-25, ACL, Philadelphia17-25.
A Contextual Language Model to Improve Machine Translation of Pronouns by Re-ranking Translation Hypotheses
Luong Ngoc Quang, Popescu-Belis Andrei (2016), A Contextual Language Model to Improve Machine Translation of Pronouns by Re-ranking Translation Hypotheses, in EAMT 2016 (19th Annual Conference of the European Association for Machine Translation), Riga, Latviax, x.
Categories of coherence relations in discourse annotation: Towards a reliable categorization of coherence relations
Scholman M.C.J., Evers-Vermeul J., Sanders T.J.M. (2016), Categories of coherence relations in discourse annotation: Towards a reliable categorization of coherence relations, in Dialogue and Discourse, 7(2), 1-28.
Crossing Sentence Boundaries in Statistical Machine Translation
Mascarell L., Rios A., Volk M. (2016), Crossing Sentence Boundaries in Statistical Machine Translation, MultiLingual Magazine, x.
Discourse connectives across languages: Factors influencing their explicit or implicit translation
Zufferey Sandrine (2016), Discourse connectives across languages: Factors influencing their explicit or implicit translation, in Languages in Contrast, 16(2), 264-279.
Discourse connectives across languages: Factors influencing their explicit or implicit translation
Zufferey Sandrine (2016), Discourse connectives across languages: Factors influencing their explicit or implicit translation, in Languages in Contrast, 16(2), 264-279.
Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction
Guillou L., Hardmeier C., Nakov P., Stymne S., Tiedemann J., Versley Y., Cettolo M., Webber B., Popescu-Belis A. (2016), Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction, in Proceedings of WMT 2016 (First Conference on Machine Translation), Berlin525-542, ACL, Philadelphia525-542.
Improving Pronoun Translation by Modeling Coreference Uncertainty
Luong Ngoc Quang, Popescu-Belis Andrei (2016), Improving Pronoun Translation by Modeling Coreference Uncertainty, in Proceedings of WMT16 (First Conference on Machine Translation), BerlinACL, Philadelphia.
On the subjectivity of Mandarin reason connectives: Robust profiles or genre-sensitivity?
Li F., Sanders T.J.M., Evers-Vermeul J. (2016), On the subjectivity of Mandarin reason connectives: Robust profiles or genre-sensitivity?, in Stukker N., Steen G., Spooren W. (ed.), Mouton De Gruyter, Berlin, 15-50.
Predicting and Using a Pragmatic Component of Lexical Aspect
Loaiciga S., Grisot C. (2016), Predicting and Using a Pragmatic Component of Lexical Aspect, in Linguistic Issues in Language Technology, 13, 3.
Pronoun Language Model and Grammatical Heuristics for Aiding Pronoun Prediction
Luong Ngoc Quang, Popescu-Belis Andrei (2016), Pronoun Language Model and Grammatical Heuristics for Aiding Pronoun Prediction, in Proceedings of WMT 2016 (First Conference on Machine Translation), System Papers, Pronoun Prediction, BerlinACL, Philadelphia.
The role of perspective shifts for processing and translating discourse relations
Zufferey S., Gygax P.M. (2016), The role of perspective shifts for processing and translating discourse relations, in Discourse Processes, 53(7), 532-555.
Using the TED Talks to Evaluate Spoken Post-editing of Machine Translation
Liyanapathirana J., Popescu-Belis A. (2016), Using the TED Talks to Evaluate Spoken Post-editing of Machine Translation, in LREC 2016 (10th International Conference on Language Resources and Evaluation), Portoroz, CroatiaELRA, Paris.
Wiki-LDA: A Mixed-Method Approach for Effective Interest Mining on Twitter Data
Pu X., Chatti M.A., Thüs H., Schroeder U. (2016), Wiki-LDA: A Mixed-Method Approach for Effective Interest Mining on Twitter Data, in CSEDU 2016 (8th International Conference on Computer Supported Education), Rome, Italyx, x.
A cross-linguistic perspective on the acquisition of causal connectives and relations
Zufferey S., Mak W., Sanders T.J.M. (2015), A cross-linguistic perspective on the acquisition of causal connectives and relations, in International Review of Pragmatics, vol. 7, 22-39.
Advanced learners’ comprehension of discourse connectives: The role of L1 transfer across on-line and off-line tasks
Zufferey S., Mak W., Degand L., Sanders T.J.M. (2015), Advanced learners’ comprehension of discourse connectives: The role of L1 transfer across on-line and off-line tasks, in Second Language Research, vol. 31, 389-411.
Causality and subjectivity in discourse: The meaning and use of causal connectives in spontaneous conversation, chat interactions and written text
Sanders T.J.M., Spooren W.P.M. (2015), Causality and subjectivity in discourse: The meaning and use of causal connectives in spontaneous conversation, chat interactions and written text, in Linguistics, vol. 53(n. 1), 53-92.
Connectives as processing signals: How students benefit in processing narrative and expository texts
van Silfhout G., Evers-Vermeul J., Sanders T.J.M. (2015), Connectives as processing signals: How students benefit in processing narrative and expository texts, in Discourse Processes, vol. 52(n. 1), 47-76.
Detecting Code-Switching in a Multilingual Alpine Heritage Corpus
Volk M., Clematide S. (2015), Detecting Code-Switching in a Multilingual Alpine Heritage Corpus, in Proceedings of the First Workshop on Computational Approaches to Code Switching (at EMNLP 2014), Dohax, x.
Detecting document-level context triggers to resolve translation ambiguity
Mascarell L., Fishel M., Volk M. (2015), Detecting document-level context triggers to resolve translation ambiguity, in Proceedings of the Second Workshop on Discourse in Machine Translation, LisbonACL, Philadelphia.
Disambiguating discourse connectives for statistical machine translation
Meyer Thomas, Hajlaoui Najeh, Popescu-Belis Andrei (2015), Disambiguating discourse connectives for statistical machine translation, in IEEE Transactions on Audio, Speech and Language Processing, 23(7), 1184-1197.
Factors influencing the implicitation of discourse relations across languages
Hoek J., Zufferey S. (2015), Factors influencing the implicitation of discourse relations across languages, in Proceedings of the 11th Joint ACL-ISO Workshop on Interoperable Semantic Annotation (ISA-11), LondonACL, Philadelphia.
French connectives
Degand L., Zufferey S. (2015), French connectives, in C. Chapelle (ed.), Oxford: Wiley-Blackwell, Oxford, xxx.
Leveraging Compounds to Improve Noun Phrase Translation from Chinese and German
Pu X., Mascarell L., Popescu-Belis A., Fishel M., Luong N.Q., Volk M. (2015), Leveraging Compounds to Improve Noun Phrase Translation from Chinese and German, in Proceedings of the ACL-IJCNLP 2015 Student Research Workshop, BeijingACL, Philadelphia.
Proceedings of the EMNLP Workshop on Discourse in Machine Translation
Webber B., Carpuat M., Popescu-Belis A., Hardmeier C. (2015), Proceedings of the EMNLP Workshop on Discourse in Machine Translation, in DiscoMT (ed.), DiscoMT , Lisbon, xx.
Pronoun translation and prediction with or without coreference links
Luong N.Q., Miculicich Werlen L., Popescu-Belis A. (2015), Pronoun translation and prediction with or without coreference links, in Proceedings of the Second Workshop on Discourse in Machine Translation, LisbonACL, Philadelphia.
The role of expectedness in the implicitation and explicitation of discourse relations
Hoek J., Evers-Vermeul J., Sanders T.J.M (2015), The role of expectedness in the implicitation and explicitation of discourse relations, in Proceedings of the Second Workshop on Discourse in Machine Translation, LisbonACL, Philadelphia.
Using a unified taxonomy to annotate discourse markers in speech and writing
Crible L., Zufferey S. (2015), Using a unified taxonomy to annotate discourse markers in speech and writing, in Proceedings of the 11th Joint ISO-ACL/SIGSEM Workshop on Interoperable Semantic Annotation, LondonACL, Philadelphia.
A multifactorial analysis of explicitation in translation
Zufferey S., Cartoni B. (2014), A multifactorial analysis of explicitation in translation, in Target, vol. 26(3), 361-384.
Cross-Linguistic Annotation of Narrativity for English/French Verb Tense Disambiguation
Cristina Grisot and Thomas Meyer (2014), Cross-Linguistic Annotation of Narrativity for English/French Verb Tense Disambiguation, in Proceedings of LREC 2014 , Reykjavikx, x.
Enforcing Consistent Translation of German Compound Coreferences
Mascarell Laura, Fishel Mark, Korchagina Natalia, Volk Martin (2014), Enforcing Consistent Translation of German Compound Coreferences, in Proceedings of KONVENS, Hildesheimx, x.
English-French Verb Phrase Alignment in Europarl for Tense Translation Modeling
Loaiciga Sharid, Meyer Thomas and Popescu-Belis Andrei (2014), English-French Verb Phrase Alignment in Europarl for Tense Translation Modeling, in Proceedings of LREC 2014 , ReykjavikELRA, Paris.
Givenness, procedural meaning and connectives: The case of French ‘puisque’.
Zufferey Sandrine (2014), Givenness, procedural meaning and connectives: The case of French ‘puisque’., in Journal of Pragmatics, 62(1), 121-135.
How do empirical methods interact with theoretical pragmatics? The conceptual and procedural contents of the English Simple Past and its translation into French
Cristina Grisot and Moeschler Jaques (2014), How do empirical methods interact with theoretical pragmatics? The conceptual and procedural contents of the English Simple Past and its translation into French, in Romero-Trillo Jesús (ed.), Springer, Dordrecht, 7-34.
The influence of linguistic and cognitive factors on the time course of verb-based implicit causality
Koornneef A.W., Dotlacil J., van den Broek P., Sanders T.J.M., The influence of linguistic and cognitive factors on the time course of verb-based implicit causality, in Quarterly Journal of Experimental Psychology, 69(3), 455-481.

Zusammenarbeit

Gruppe / Person Land
Formen der Zusammenarbeit
Uppsala University, Dpt. of Linguistics and Philology, Prof. Jörg Tiedemann Schweden (Europa)
- vertiefter/weiterführender Austausch von Ansätzen, Methoden oder Resultaten
University of Edinburgh, School of Informatics, Prof. Bonnie Webber Grossbritannien und Nordirland (Europa)
- vertiefter/weiterführender Austausch von Ansätzen, Methoden oder Resultaten
- Publikation
Université Catholique de Louvain, Prof. Liesbeth Degand Belgien (Europa)
- vertiefter/weiterführender Austausch von Ansätzen, Methoden oder Resultaten
- Publikation
Radboud University Nijmegen, Centre for Language Studies, Prof. Dr. W. Spooren Niederlande (Europa)
- vertiefter/weiterführender Austausch von Ansätzen, Methoden oder Resultaten
- Publikation
Université de Fribourg, Faculté des Lettres, Dr. Sandrine Zufferey Schweiz (Europa)
- vertiefter/weiterführender Austausch von Ansätzen, Methoden oder Resultaten
- Publikation
University of Sheffield, NLP group, Dr. Lucia Specia Grossbritannien und Nordirland (Europa)
- vertiefter/weiterführender Austausch von Ansätzen, Methoden oder Resultaten
Vicomtech, Ms. Arantza del Pozo Spanien (Europa)
- vertiefter/weiterführender Austausch von Ansätzen, Methoden oder Resultaten
- Publikation
- Industrie/Wirtschaft/weitere anwendungs-orientierte Zusammenarbeit
Université catholique de Louvain, Valibel, Prof. Liesbeth Degand Belgien (Europa)
- vertiefter/weiterführender Austausch von Ansätzen, Methoden oder Resultaten
- Publikation
Vytautas Magnus University, Kaunas Litauen (Europa)
- vertiefter/weiterführender Austausch von Ansätzen, Methoden oder Resultaten

Wissenschaftliche Veranstaltungen

Aktiver Beitrag

Titel Art des Beitrags Titel des Artikels oder Beitrages Datum Ort Beteiligte Personen
50th Annual Meeting of the Societas Linguistica Europaea (SLE2017) Vortrag im Rahmen einer Tagung Restrictive relative clause constructions as implicit coherence relations 01.09.2017 Zurich, Schweiz Hoek Jet;
27th Annual Meeting of the Society of Text and Discourse (ST&D) Vortrag im Rahmen einer Tagung Coherence-driven discourse expectations from restrictive relative clauses 31.07.2017 Philadelphia, Vereinigte Staaten von Amerika Evers-Vermeul Jacqueline; Sanders Ted; Hoek Jet;
DETEC 2017 - Discourse Expectations: Theoretical, Experimental and Computational perspectives Vortrag im Rahmen einer Tagung Shaping discourse expectations by restricting referents 26.06.2017 Nijmegen, Niederlande Hoek Jet; Evers-Vermeul Jacqueline; Sanders Ted;
Time in Translation Workshop Vortrag im Rahmen einer Tagung Coherence relations in (Machine) Translation 23.06.2017 Utrecht, Niederlande Hoek Jet;
SwissText 2017 (2nd Swiss Text Analytics Conference) Vortrag im Rahmen einer Tagung Using context to improve the machine translation of nouns and pronouns 09.06.2017 Winterthur, Schweiz Popescu-Belis Andrei; Mascarell Laura; Xiao Pu;
Workshop on "Machine Translation meets Translators" Vortrag im Rahmen einer Tagung Document-level Statistical MT: from Connectives to Pronouns 16.05.2017 Zurich, Schweiz Popescu-Belis Andrei;
Information structuring in discourse (Workshop at DGFS2017) Vortrag im Rahmen einer Tagung Complete and independent? Reconsidering discourse segmentation basics 08.03.2017 Saarbrücken, Deutschland Sanders Ted; Hoek Jet; Evers-Vermeul Jacqueline;
FEAST Vortrag im Rahmen einer Tagung nter-coder agreement for annotation tasks: AC1 as an alternative to Kappa 06.03.2017 Saarbrücken, Deutschland Hoek Jet;
CogLing 7 Vortrag im Rahmen einer Tagung Discourse connectives in translation 05.01.2017 Nijmegen, Niederlande Sanders Ted; Hoek Jet; Evers-Vermeul Jacqueline;
Language Sciences Day Poster Discourse relations and Statistical Machine Translation 04.01.2017 Utrecht, Niederlande Hoek Jet;
26th Annual Meeting of the Society for Text and Discourse Vortrag im Rahmen einer Tagung When do we need a connective? Cognitive complexity and the linguistic marking of coherence relations 18.07.2016 Kassel, Deutschland Sanders Ted; Evers-Vermeul Jacqueline; Hoek Jet;
Critical Link 8 - Future proofing interpreting and translating Vortrag im Rahmen einer Tagung Keynote talk on Machine Translation for Media Accessibility - Subtitles, Sign Languages and Beyond 01.07.2016 Edinburgh, Grossbritannien und Nordirland Volk Martin;
Forum on Cognitive Linguistics and Symposium on Eye-Tracking Vortrag im Rahmen einer Tagung Establishing coherence: how research on discourse representation and processing contributes to more comprehensible texts 15.06.2016 Beijing, China Sanders Ted;
SwissText 2016 (1st Swiss Text Analytics Conference) Poster MODERN: Modeling Discourse Entities and Relations for Coherent Machine Translation 06.06.2016 Winterthur, Schweiz Mascarell Laura; Popescu-Belis Andrei;
Second TextLink Action Conference Vortrag im Rahmen einer Tagung On temporality in discourse annotation 14.04.2016 Budapest, Ungarn Evers-Vermeul Jacqueline; Hoek Jet;
Second TextLink Action Conference Vortrag im Rahmen einer Tagung How can we relate various annotation schemes?: Unifying dimensions in discourse relations. 14.04.2016 Budapest, Ungarn Hoek Jet; Sanders Ted; Evers-Vermeul Jacqueline;
TextLink Second Action Conference Vortrag im Rahmen einer Tagung Manual and Automatic Labeling of Discourse Connectives for Machine Translation 14.04.2016 Budapest, Ungarn Popescu-Belis Andrei;
Second TextLink Action Conference Vortrag im Rahmen einer Tagung Discourse segmentation and ambiguity in discourse 14.04.2016 Budapest, Ungarn Sanders Ted; Hoek Jet; Evers-Vermeul Jacqueline;
LPTS16 (3rd International Conference on Linguistic and Psycholinguistic Approaches to Text Structuring) Vortrag im Rahmen einer Tagung Unifying dimensions in discourse relations: how various annotation schemes are related. 24.01.2016 Valencia, Spanien Hoek Jet; Evers-Vermeul Jacqueline; Sanders Ted;
LPTS16 (3rd International Conference on Linguistic and Psycholinguistic Approaches to Text Structuring) Vortrag im Rahmen einer Tagung Segmenting discourse units: Incorporating interpretation into decision rules? 24.01.2016 Valencia, Spanien Hoek Jet; Evers-Vermeul Jacqueline; Sanders Ted;
48th Annual Meeting of the Societas Linguistica Europea (SLE 2015) Vortrag im Rahmen einer Tagung - Validating categories of causal relations: Converging evidence from corpus-based research and experiments 02.09.2015 Leiden, Niederlande Sanders Ted; Evers-Vermeul Jacqueline;
14th International Pragmatics Conference (IPrA) Vortrag im Rahmen einer Tagung Cognitive factors influencing the implicit vs. explicit communication of discourse relations across languages 30.07.2015 Antwerp, Belgien Evers-Vermeul Jacqueline; Hoek Jet; Sanders Ted;
14th International Pragmatics Conference (IPrA) Vortrag im Rahmen einer Tagung Causality and Subjectivity in discourse and cognition 28.07.2015 Antwerp, Belgien Sanders Ted;
"Why Linguistics?" Conference Einzelvortrag Putting Text-Level Linguistics into Statistical Machine Translation 06.05.2015 University of Tartu, Estland Popescu-Belis Andrei;
Textlink WG2/WG3 meeting Vortrag im Rahmen einer Tagung Let's try to make annotation systems communicate - towards a systematic approach of coherence relations 21.04.2015 Fribourg, Schweiz Sanders Ted;
Parseme COST Action Meeting Poster Compounds, Coreferences and Multiword Translations 18.03.2015 Malta, Malta Mascarell Laura; Fishel Mark; Volk Martin;
the First TextLink Action Conference Poster Discourse relation annotations, their annotators and how to deal with systematic dependence and response bias 26.01.2015 Louvain-la-Neuve, Belgien Groen Martin;
the First TextLink Action Conference Poster Annotating implicit coherence relations in parallel corpora 26.01.2015 Louvain-la-Neuve, Belgien Hoek Jet;
13th International Congress for the Study of Child Language (IASCL) Vortrag im Rahmen einer Tagung The acquisition of objective and subjective causality 14.07.2014 Amsterdam, Niederlande Sanders Ted;
Chronos 11 Vortrag im Rahmen einer Tagung What do translation corpora tell us about the semantics and pragmatics of tense? The case of the English preterit 16.06.2014 Pisa, Italien Grisot Cristina;
The 6th International Conference on Intercultural Pragmatics and Communication Vortrag im Rahmen einer Tagung The conceptual/procedural distinction: empirical perspectives and quantitative measures 30.05.2014 La Valette, Malta Grisot Cristina;
23rd Conference of the European Second Language Association (EUROSLA) Vortrag im Rahmen einer Tagung Advanced learners’ sensitivity to misuses of connectives during on-ling processing: The role of L1 transfer 28.08.2013 Amsterdam, Niederlande Sanders Ted;


Veranstaltungen zum Wissenstransfer

Aktiver Beitrag

Titel Art des Beitrags Titel des Artikels oder Beitrages Datum Ort Beteiligte Personen
Transtech 2017 (3rd Summer School in Translation Technologies) Vortrag 04.09.2017 Ljubljana, Slowenien
SwissText 2017 - 2nd Swiss Text Analytics Conference Vortrag 09.06.2017 Winterthur, Schweiz
SwissText 2016 - 1st Swiss Text Analytics Conference Poster 08.06.2016 Winterthur, Schweiz


Kommunikation mit der Öffentlichkeit

Kommunikation Titel Medien Ort Jahr
Medienarbeit: Printmedien, Online-Medien «Google Translate» soll lernen, über einen Satz hinaus zu «denken» Deutschschweiz International 2017
Medienarbeit: Printmedien, Online-Medien Google Translate lernt Basler Zeitung International Westschweiz 2017
Medienarbeit: Printmedien, Online-Medien Google Translate soll Texte besser verstehen lernen Zofinger Tagblatt Deutschschweiz 2017
Medienarbeit: Printmedien, Online-Medien I traduttori automatici sono sempre più efficienti Corriere del Ticino Italienische Schweiz 2017
Medienarbeit: Printmedien, Online-Medien Software weil dolmetsch nicht gut kann Wiener Zeitung International 2017
Medienarbeit: Printmedien, Online-Medien Un nouvel outil pour aider les ordinateurs à traduire Tribune de Genève International Westschweiz 2017
Medienarbeit: Radio, Fernsehen Idiap: 25 ans de recherche en Valais. Et une reconnaissance internationale Canal 9 (Valais) Westschweiz 2016

Verbundene Projekte

Nummer Titel Start Förderungsinstrument
148024 MULDIS - Discourse Connectives: From Multiple Languages to Multilingual Minds 01.04.2014 Ambizione
126999 Domain-specific Statistical Machine Translation 01.01.2010 Resource not found: '3cfa3371-69b0-4730-9d42-150eea4471e1'
169888 Rich Context in Neural Machine Translation 01.01.2017 Resource not found: '3cfa3371-69b0-4730-9d42-150eea4471e1'
113382 Pragmatique lexicale et non-lexicale de la causalité en français: aspects descriptifs, théoriques et expérimentaux 01.04.2007 Projektförderung (Abt. I-III)
127510 Improving the coherence of machine translation output by modeling intersentential relations 01.03.2010 Sinergia
103318 Quality models and resources for the evaluation of machine translation 01.10.2004 Projektförderung (Abt. I-III)

Abstract

State-of-the-art machine translation (MT) systems, especially statistical but also rule-based ones, operate in a sentence-by-sentence mode, and do not propagate information through the series of sentences that constitute texts. Such a propagation is however helpful, and sometimes even indispensable, to make correct translation choices for words and phrases that depend on previous ones. The goal of MODERN is to model and automatically detect such dependencies, and to study their integration within MT, with the aim of demonstrating improvement in translation quality.The focus of MODERN is on the interplay between referring expressions such as noun phrases and pronouns, which must be coherently translated throughout a text, and discourse relations between sentences, which are often conveyed by explicit connectives that are notoriously difficult to translate. MODERN will study joint computational models of discourse entities and discourse relations in texts, based on linguistic theories and experimental grounding, and the inclusion in such models of automatically generated domain-knowledge related to the discourse entities. MODERN will design and implement these probabilistic models, and integrate them with operational MT systems, both rule-based (Apertium) and statistical (Moses). Particular attention will be paid to the evaluation of MT improvement, studying the effect on human readers of various translation options for discourse entities and connectives, and aiming to optimize MT output in this respect. The MODERN project will focus on four languages -- English, French, German and Dutch -- for which the partners have considerable expertise. Two domains will be used as case studies: Alpine texts from a multilingual corpus of Alpine Club yearbooks (Text+Berg) and texts on environmental legislation and debates extracted from the JRC-Acquis, DGT-Acquis, and Europarl parallel corpora.The MODERN project partially builds upon the COMTIS Sinergia project (2010-2013), which has mainly investigated the automatic translation of discourse connectives, using annotated corpora to train a connective disambiguation system and a connective-aware statistical MT system from English to French, Arabic, German and Italian. The improvement was demonstrated using new connective-specific metrics, and the method has also been tested on pronouns and verbs. Work in the MODERN project will be organized around the following four sub-projects, noted A through D, based respectively at each of the participating institutions: UiL/OTS, UniGe, Idiap, UniZh. These sub-projects are: (A) empirically-based linguistic modeling and psycholinguistic evaluation, focusing on the interface between referential and relational cohesion (3-year PhD), and performing a cognitive evaluation of human and MT output (2-year postdoc); (B) cross-linguistic modeling of EN/FR past tense (4th year PhD); (C) automatic multilingual extraction of discourse entities and relations, with four topics: automatic classification of inter-sentential dependencies for SMT (4th year PhD), joint probabilistic modeling of discourse entities and relations (DE&R, 2-year PhD), SMT decoder enhanced by a DE&R model (2-year postdoc), and evaluation methods for MT coherence (4-month finishing postdoc); (D) integrating domain-specific semantics with caching for text-level MT, focusing on automatically-built ontologies for MT (2-year postdoc) and implementing and evaluating caching for rule-based and statistical MT (3-year PhD).The Sinergia MODERN project involves researchers in natural language processing, MT, and linguistics, coming from four different groups with extensive contributions to the relevant fields. Their collaboration will lead to operational MT systems with concrete evaluation results. Thanks to MODERN, Swiss research in MT will continue to maintain a leading edge within the European and international community.
-