Tutkimus ja julkaisut

Translatedilla on aktiivinen rooli keinoälyn ja erityisesti luonnollisen kielen prosessoinnin tutkimuksessa. Olemme tehneet yhteistyötä huippuyliopistojen ja tutkimuskeskusten kanssa vuodesta 2008 lähtien mm. sponsoroimalla niitä ja kirjoittamalla yhteistyössä useita tieteellisiä artikkeleita. Kumppaneihimme kuuluvat Fondazione Bruno Kessler, Edinburghin yliopisto ja Université du Maine. Alta löydät luettelon uusimmista julkaisuistamme, jotka ovat pääosin peräisin Matecat- ja ModernMT-tutkimusprojekteista.

• ModernMT production-ready engine ranks among the top research systems

  O. Bojar, C. Federmann, M. Fishel, Y. Graham, B. Haddow, M. Huck, P. Koehn, C. Monz, Findings of the 2018 Conference on Machine Translation (WMT18), 1.11.2018.

• FBK's Multilingual Machine Translation System for IWSLT 2017

  S. M. Lakew, Q. F. Lotito, M. Turchi, M. Negri, M. Federico, Proceedings of the 14th International Workshop on Spoken Language Translation, 14.–15.12.2017.

• Monolingual Embeddings for Low Resourced Neural Machine Translation

  M. A. Di Gangi, M. Federico, Proceedings of the 14th International Workshop on Spoken Language Translation, 14.–15.12.2017.

• Improving Zero-Shot Translation for Low-Resourced Languages

  S. M. Lakew, Q. F. Lotito, M. Negri, M. Turchi, M. Federico, Proceedings of the 14th International Workshop on Spoken Language Translation, 14.–15.12.2017.

• Multilingual Neural Machine Translation for Low Resource Languages

  S. M. Lakew, M. A. Di Gangi, M. Federico, Proceedings of the 4th Italian Conference on Computational Linguistics (CLIC-IT), 11.–13.12.2017.

• Can Monolingual Embeddings Improve Neural Machine Translation?

  M.A. Di Gangi ja M. Federico, Proceedings of the 4th Italian Conference on Computational Linguistics (CLIC-IT), 11.–13.12.2017.

• FBK’s Participation to the English-to-German News Translation Task of WMT 2017

  M.A. Di Gangi, N. Bertoldi ja M. Federico, Proceedings of the Second Conference on Machine Translation, syyskuu 2017, s. 271–275.

• Multi-Domain Neural Machine Translation through Unsupervised Adaptation

  M.A. Farajian, M. Turchi, M. Negri ja M. Federico, Proceedings of the Second Conference on Machine Translation, syyskuu 2017, s. 127–137.

• Guiding Neural Machine Translation Decoding with External Knowledge

  R. Chatterjee, M. Negri, M. Turchi, M. Federico, L. Specia ja F. Blain, Proceedings of the Second Conference on Machine Translation, syyskuu 2017, s. 157–168.

• Continuous Learning from Human Post-edits for Neural Machine Translation

  M. Turchi, M. Negri, A. Farajian ja M. Federico, Proceedings of the 20th Annual Conference of the European Association for Machine Translation, numero 108, kesäkuu 2017

• Linguistically Motivated Vocabulary Reduction for Neural Machine Translation

  D. Ataman, M. Negri ja M. Federico: Proceedings of the 20th Annual Conference of the European Association for Machine Translation, numero 108, kesäkuu 2017.

• MMT: New Open Source MT for the Translation Industry

  N. Bertoldi, R. Cattoni, M. Cettolo, A. F., M. Federico, D. Caroselli, L. Mastrostefano, A. Rossi, M. Trombetti, U. Germann, D. Madl: Proceedings of the 20th Annual Conference of the EAMT, 2017.

• Neural vs. Phrase-Based Machine Translation in Multi-Domain Scenario

  M.A. Farajian, M. Turchi, M. Negri, N. Bertoldi ja M. Federico, Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, osa 2, 2017.

• Neural versus Phrase-Based MT Quality: an In-Depth Analysis on English-German and English-French

  L. Bentivogli, A. Bisazza, M. Cettolo, M. Federico, Computer Speech and Language, osa 49, toukokuu 2018, 2017.

• The first Automatic Memory Clearning Shared Task

  E. Barbu, C. Parra Escartín, L. Bentivogli, M. Negri, M. Turchi, C. Orasan, M. Federico, Machine Translation, tammikuu 2017.

• Automatic translation memory cleaning

  M. Negri, D. Ataman, M.J. Sabet, M. Turchi ja M. Federico, Machine Translation, helmikuu 2017.

• The IWSLT 2016 Evaluation Campaign

  M. Cettolo, J. Niehues, S. Stüker, L. Bentivogli, M. Federico, Proceedings of the 13th International Workshop on Spoken Language Translation, 8.–9.12.2016.

• FBK's Neural Machine Translation Systems for IWSLT 2016

  M. A. Farajian, R. Chatterjee, C. Conforti, S. Jalalvand, V. Balaraman, M. A. Di Gangi, D. Ataman, M. Turchi, M. Negri, M. Federico, Proceedings of the 13th International Workshop on Spoken Language Translation, 8.–9.12.2016.

• Neural versus Phrase-Based Machine Translation Quality: a Case Study

  L. Bentivogli, A. Bisazza, M. Cettolo, M. Federico, Proceedings of Conference on Empirical Methods in Natural Language Processing, 1.–5.11.2016.

• The Reasonable Effectiveness of Data

  A. Ruopp, Proceedings of 12th Conference of the Association for Machine Translation in the Americas, osa 2: MT Users' Track, s. 123–142.

• MT Adaptation from TMs in ModernMT

  M. Federico, Proceedings of 12th Conference of the Association for Machine Translation in the Americas, osa 2: MT Users' Track, s. 19–57.

• Findings of the WMT 2016 Bilingual Document Alignment Shared Task

  C. Buck, P. Koehn, Proceedings of the First Conference on Machine Translation, osa 2: Shared Task Papers , 11.–12.8.2016, s. 554–563.

• An Unsupervised Method for Automatic Translation Memory Cleaning

  M. J. Sabet, M. Negri, Marco Turchi, E. Barbu, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 7.–12.8.2016, s. 287–292.

• TMOP: A Tool for Unsupervised Translation Memory Cleaning

  M.J. Sabet, M. Negri, M. Turchi, J.G.C. de Souza, M. Federico, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 7.–12.8.2016.

• Sampling Phrase Tables for the Moses Statistical Machine Translation System

  U. Germann, The Prague Bulletin of Mathematical Linguistics, nro 104, lokakuu 2015, s. 39–50

• MT Quality Estimation for E-Commerce Data

  J. G. C. de Souza, M. Federico, H. Sawaf, Proceedings of MT Summit XV (AMTA 2015), 30.10.–3.11.2015, s. 20–29.

• Topic Adaptation for Machine Translation of E-Commerce Content

  P. Mathur, M. Federico, S. Köprü, S. Khadivi, H. Sawaf, Proceedings of MT Summit XV (AMTA 2015), 30.10.–3.11.2015, s. 270–281.

• Project Adaptation over Several Days

  F. Blain, A. Hazem, F. Bougares, L. Barrault ja H. Schwenk, 2nd Translation in Transition Conference, 29.–30.1.2015.

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

  K. Cho, B. van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk ja Y. Bengio: Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), 25.–29.10.2014, s. 1724–1734.

• Online and Multitask learning for Machine Translation Quality Estimation in Real-world scenarios

  J.G.C. de Souza, M. Turchi, M. Negri, A. Anastasopoulos, Italian Computational Linguistics Conference (CLIC-it 2014), 9.–10.12.2014.

• Adattamento al Progetto dei Modelli di Traduzione Automatica nella Traduzione Assistita

  M. Cettolo, N. Bertoldi, ja M. Federico, Italian Computational Linguistics Conference (CLIC-it 2014), 9.–10.12.2014.

• Assessing the Impact of Translation Errors on Machine Translation Quality with Mixed-effects Models

  M. Federico, M. Negri, L. Bentivogli, M. Turchi, Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), 25.–29.10.2014, s. 1643–1653.

• Dynamic Phrase Tables for Statistical Machine Translation in an Interactive Post-editing Scenario

  U. Germann, AMTA 2014 Workshop on Interactive and Adaptive Machine Translation (IAMT 2014), 22.10.2014, s. 20–3

• Optimized MT Online Learning in Computer Assisted Translation

  P. Mathur ja M. Cettolo, AMTA 2014 Workshop on Interactive and Adaptive Machine Translation (IAMT 2014), 22.10.2014, s. 32–41.

• Towards a Combination of Online and Multitask Learning for MT Quality Estimation: a Preliminary Study

  J.G.C. de Souza, M. Turchi ja M. Negri, AMTA 2014 Workshop on Interactive and Adaptive Machine Translation (IAMT 2014), 22.10.2014, s. 9–19.

• The Repetition Rate of Text as a Predictor of the Effectiveness of Machine Translation Adaptation

  M. Cettolo, N. Bertoldi ja M. Federico, 11th biennial conference of the Association for Machine Translation in the Americas (AMTA 2014), 22.–26.10.2014, s. 166–179

• Enhancing Statistical Machine Translation with Bilingual Terminology in a CAT Environment

  M. Arcan, M. Turchi, S. Tonelli, P. Buitelaar, 11th biennial conference of the Association for Machine Translation in the Americas (AMTA 2014), 22.–26.10.2014, s. 54–68.

• Online Multi-User Adaptive Statistical Machine Translation

  P. Mathur, M. Cettolo, M. Federico, ja J.G.C. de Souza, 11th biennial conference of the Association for Machine Translation in the Americas (AMTA 2014), 22.–26.10.2014, s. 152–165.

• Machine Translation Quality Estimation Across Domains

  J.G.C. de Souza, M. Turchi ja M. Negri, 25th International Conference on Computational Linguistics (COLING 2014), 23.–29.8.2014, s. 409–420.

• MT-EQuAl: a Toolkit for Human Assessment of Machine Translation Output

  C. Girardi, L. Bentivogli, M.A. Farajian, M. Federico, 25th International Conference on Computational Linguistics (COLING 2014), 23.–29.8.2014, s. 120–123.

• The Matecat Tool

  M. Federico, N. Bertoldi, M. Cettolo, M. Negri, M. Turchi, M. Trombetti, A. Cattelan, A. Farina, D. Lupinetti, A. Martines, A. Massidda, H. Schwenk, L. Barrault, F. Blain, P. Koehn, C. Buck ja U. Germann: 25th International Conference on Computational Linguistics (COLING 2014), 23.–29.8.2014, s. 129–132.

• Identification of Bilingual Terms from Monolingual Documents for Statistical Machine Translation

  M. Arcan, C. Giuliano, M. Turchi ja P. Buitelaar, 4th COLING International Workshop on Computational Terminology (Computerm), 23.8.2014, s. 22–31.

• Online Adaptation to Post-edits for Phrase-Based Statistical Machine Translation

  N. Bertoldi, P. Simianer, M. Cettolo, K. Waeschle, M. Federico, S. Riezler, Machine Translation Journal, osa 28, joulukuu 2014, s. 127–150.

• Translation Project Adaptation for MT-Enhanced Computer Assisted Translation

  M. Cettolo, N. Bertoldi, M. Federico, H. Schwenk, L. Barrault ja C. Servan, Machine Translation Journal, osa 28, joulukuu 2014, s. 309–339.

• Data-driven Annotation of Binary MT Quality Estimation Corpora Based on Human Post-editions

  M. Turchi, M. Negri, M. Federico, Machine Translation, osa 28, numerot 3–4, joulukuu 2014, s. 281–30.

• FBK-UPV-UEdin participation in the WMT14 Quality Estimation shared-task

  J.G.C. de Souza, J. González-Rubio, C. Buck, M. Turchi ja M. Negri, 9th ACL Workshop on Statistical Machine Translation (WMT 2014), 26.–27.6.2014, s. 322–328.

• Adaptive Quality Estimation for Machine Translation

  M. Turchi, A. Anastasopoulos, J.G.C. de Souza ja M. Negri, 52nd Annual Meeting of the Association for Computational Linguistics (ACL 2014), 22.–27.6.2014, s. 710–720.

• Automatic Annotation of Machine Translation Datasets with Binary Quality Judgements

  M. Turchi ja M. Negri, 9th Language Resources and Evaluation Conference (LREC 2014), Reykjavik, Islanti, 26.–31.5.2014, s. 1788–1792.

• N–gram Counts and Language Models from the Common Crawl

  C. Buck, K. Heafield ja B. van Ooyen, 9th Language Resources and Evaluation Conference (LREC 2014), 26.–31.5.2014, s. 3579–3584.

• Online Word Alignment for Online Adaptive Machine Translation

  A. Farajian, N. Bertoldi, M. Federico, EACL2014 Workshop on Humans and Computer-assisted Translation, huhtikuu 2014.

• Dynamic Models in Moses for Online Adaptation

  N. Bertoldi, Prague Bulletin of Mathematical Linguistics, huhtikuu 2014.

• Recent Advancements in Human Language Technology in Italy

  B. Magnini, M. Baroni, M. Federico ja R. Navigli. Intelligenza artificiale 7, 2013, s. 91–100.

• XenC: An Open-Source Tool for Data Selection in Natural Language Processing

  A. Rousseau, Prague Bulletin of Mathematical Linguistics, nro 100, 2013, s. 73–82.

• Project Adaptation for MT Enhanced Computer Assisted Translation

  M. Cettolo, N. Bertoldi ja M. Federico, Proceedings of the XIV Machine Translation Summit, 2.–6.9.2013, s. 27–34.

• Cache-based Online Adaptation for Machine Translation Enhanced Computer Assisted Translation

  N. Bertoldi, M. Cettolo, M. Federico, Proceedings of the XIV Machine Translation Summit, 2.–6.9.2013, s. 35–42.

• Generative and Discriminative Methods for Online Adaptation in SMT

  K. Waeschle, P. Simianer, N. Bertoldi, S. Riezler, M. Federico, Proceedings of the XIV Machine Translation Summit, 2.–6.9.2013, s. 11–18.

• Issues in Incremental Adaptation of Statistical MT from Human Post-edits

  M. Cettolo, N. Bertoldi, M. Federico, C. Servan, L. Barrault ja H. Schwenk, Proceedings of MT Summit XIV Workshop on Post-editing Technology and Practice, 2.9.2013, s. 111–118.

• A modular Open-Source Continuous Space Language Modeling Toolkit

  H. Schwenk, Modeling Toolkit, Interspeech, 25.–29.8.2013.

• Findings of the 2013 Workshop on Statistical Machine Translation

  O. Bojar, C. Buck, C. Callison-Burch, C. Federmann, B. Haddow, P. Koehn, C. Monz, M. Post, R. Soricut ja L. Specia, Proceedings of the 8th Workshop on SMT, 8.–9.8.2013, s. 1–44.

• FBK-UEdin Participation to the WMT13 Quality Estimation Shared Task

  J.G.C. de Souza, C. Buck, M. Turchi ja M. Negri, Proceedings of the 8th Workshop on SMT, 8.–9.8.2013, s. 352–358.

• Online Learning Approaches in Computer Assisted Translation

  P. Mathur, M. Cettolo ja M. Federico, Proceedings of the 8th Workshop on SMT, 8.–9.8.2013, s. 301–308.

• Coping with the Subjectivity of Human Judgements in MT Quality Estimation

  M. Turchi, M. Negri ja M. Federico, Proceedings of the 8th Workshop on SMT, 8.–9.8.2013, s. 240–251.

• Exploiting Qualitative Information from Automatic Word Alignment for Cross-lingual NLP Tasks

  J.G.C. de Souza, M. Esplà-Gomis, M. Turchi ja M. Negri, Proceedings of ACL 2013, 4.–9.8.2013

• A Multi-Domain Translation Model Framework for Statistical Machine Translation

  R. Sennrich, H. Schwenk ja W. Aransa, Proceedings of ACL, 4.–9.8.2013, s. 832–840.

• Incremental Adaptation Using Translation Information and Post-editing Analysis

  F. Blain, H. Schwenk ja J. Senellart, IWSLT’12, 6.–7.12.2012

• Continuous Space Translation Models for Phrase-Based Statistical Machine Translation

  H. Schwenk, Proceedings of Coling, 10.–14.12.2012

• Measuring User Productivity in MT Enhanced Computer Assisted Translation

  M. Federico, A. Cattelan, M. Trombetti, Proceedings of the tenth biennial conference of the Association for Machine Translation in the Americas (AMTA2012), 28.10.–1.11.2012.

• Evaluating the Learning Curve of Domain Adaptive Statistical Machine Translation Systems

  N. Bertoldi, M. Cettolo, M. Federico, C. Buck, Proceedings of the Seventh Workshop on Statistical Machine Translation (WMT), 7.–8.6.2012.

• Black box features for the WMT 2012 quality estimation shared task

  C. Buck, Proceedings of the Seventh Workshop on Statistical Machine Translation (WMT), 7.–8.6.2012.

• Matecat: Machine Translation Enhanced Computer Assisted Translation

  Project Presentation, Proceedings of the European Conference on Machine Translation (EAMT), 28.–30.5.2012.