Machine Translation

Vision

Our research unit focuses on machine translation technology that supports both human translators and multilingual communication applications.

We are a bunch of computer scientists, mathematicians, linguists and engineers that try to teach computers how to bridge languages that, in the best case, we barely understand.

If you are fascinated by languages, machine learning, and compute-intensive processing of large linguistic corpora, you are very welcome to check out our Join Us page!

People

Publications

Most recent papers (2022-2021)

  • Gaido, Marco; Negri, Matteo; Turchi, Marco, Direct Speech-to-Text Translation Models as Students of Text-to-Text Models, in «IJCOL», vol. 8, 2022
  • Savoldi, Beatrice; Gaido, Marco; Bentivogli, Luisa; Negri, Matteo; Turchi, Marco, Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL-2022, 2022
  • Papi, Sara; Gaido, Marco; Negri, Matteo; Turchi, Marco, Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation, Proceedings of the Third Workshop on Automatic Simultaneous Translation, AutoSimTrans-2022, 2022
  • Karakanta, Alina; Bentivogli, Luisa; Cettolo, Mauro; Negri, Matteo; Turchi, Marco, Post-editing in Automatic Subtitling: A Subtitlers’ perspective, Proceedings of the 23rd Annual Conference of the European Association for Machine Translation, EAMT-2022, 2022
  • Papi, Sara; Karakanta, Alina; Negri, Matteo; Turchi, Marco, Dodging the Data Bottleneck: Automatic Subtitling with Automatically Segmented ST Corpora, Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), AACL-2022, 2022
  • Savoldi, Beatrice; Gaido, Marco; Bentivogli, Luisa; Negri, Matteo; Turchi, Marco, On the Dynamics of Gender Learning in Speech Translation, Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing, GeBNLP-2022, 2022
  • Gaido, Marco; Papi, Sara; Fucci, Dennis; Fiameni, Giuseppe; Negri, Matteo; Turchi, Marco, Efficient yet Competitive Speech Translation: [email protected], Proceedings of the 19th International Conference on Spoken Language Translation, IWSLT-2022, 2022
  • Gaido, Marco; Negri, Matteo; Turchi, Marco, Who Are We Talking About? Handling Person Names in Speech Translation, Proceedings of the 19th International Conference on Spoken Language Translation, IWSLT2022, 2022
  • Bentivogli, Luisa; Cettolo, Mauro; Gaido, Marco; Karakanta, Alina; Negri, Matteo; Turchi, Marco, Extending the MuST-C Corpus for a Comparative Evaluation of Speech Translation Technology, Proceedings of the 23rd Annual Conference of the European Association for Machine Translation, EAMT-2022, 2022
  • Karakanta, Alina; Bentivogli, Luisa; Cettolo, Mauro; Negri, Matteo; Turchi, Marco, Towards a methodology for evaluating automatic subtitling, Proceedings of the 23rd Annual Conference of the European Association for Machine Translation, EAMT-2022, 2022
  • Papi, Sara; Gaido, Marco; Negri, Matteo; Turchi, Marco, Does Simultaneous Speech Translation need Simultaneous Models?, Findings of the Association for Computational Linguistics, EMNLP-2022, 2022
  • Anastasopoulos, Antonios; Barrault, Loc; Bentivogli, Luisa; Zanon Boito, Marcely; Bojar, Ondřej; Cattoni, Roldano; Currey, Anna; Dinu, Georgiana; Duh, Kevin; Elbayad, Maha; Emmanuel, Clara; Estève, Yannick; Federico, Marcello; Federmann, Christian; Gahbiche, Souhir; Gong, Hongyu; Grundkiewicz, Roman; Haddow, Barry; Hsu, Benjamin; Javorský, Dávid; Kloudová, Vĕra; Lakew, Surafel Melaku; Xutai, Ma; Mathur, Prashant; Mcnamee, Paul; Murray, Kenton; Nǎdejde, Maria; Nakamura, Satoshi; Negri, Matteo; Niehues, Jan; Niu, Xing; John, Ortega; Pino, Juan; Salesky, Elizabeth; Shi, Jiatong; Sperber, Matthias; Stüker, Sebastian; Sudoh, Katsuhito; Turchi, Marco; Virkar, Yogesh; Waibel, Alexander; Wang, Changhan; Watanabe, Shinji, Findings of the IWSLT 2022 Evaluation Campaign , Proceedings of the 19th International Conference on Spoken Language Translation, IWSLT-2022, 2022
  • Cattoni, Roldano; Di Gangi, Mattia Antonino; Bentivogli, Luisa; Negri, Matteo; Turchi, Marco, MuST-C: A multilingual corpus for end-to-end speech translation, in «Computer Speech and Language», vol. 66, 2021
  • Karakanta, Alina; Papi, Sara; Negri, Matteo; Turchi, Marco, Simultaneous speech translation for live subtitling: From delay to display, Proceedings of MT Summit 2021, 2021
  • Consoli, Sergio; Negri, Matteo; Tebbifakhr, Amirhossein; Tosetti, Elisa; Turchi, Marco, On Neural Forecasting and News Emotions: The Case of the Spanish Stock Market, Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML-PKDD-2021, 2021
  • Papi, Sara; Negri, Matteo; Turchi, Marco, Visualization: The missing factor in simultaneous speech translation, Proceedings of the Eighth Italian Conference on Computational Linguistics, CLiC-it 2021, 2021
  • Bertoldi, Nicola; Caroselli, Davide; Farajian, Amin; Federico, Marcello; Negri, Matteo; Trombetti, Marco; Turchi, Marco, Translation system and method, 2021
  • Papi, Sara; Gaido, Marco; Negri, Matteo; Turchi, Marco, Speechformer: Reducing Information Loss in Direct Speech Translation, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP-2021, 2021
  • Karakanta, Alina; Gaido, Marco; Negri, Matteo; Turchi, Marco, Between Flexibility and Consistency: Joint Generation of Captions and Subtitles, Proceedings of the 18th International Conference on Spoken Language Translation, IWSLT -2021, 2021
  • Savoldi, Beatrice; Gaido, Marco; Bentivogli, Luisa; Negri, Matteo; Turchi, Marco, Gender bias in machine translation, in «TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS», vol. 9, 2021
  • Papi, Sara; Gaido, Marco; Negri, Matteo; Turchi, Marco, Dealing with training and test segmentation mismatch: [email protected] 2021, Proceedings of the 18th International Conference on Spoken Language Translation, IWSLT -2021, 2021
  • Gaido, Marco; Negri, Matteo; Cettolo, Mauro; Turchi, Marco, Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translation, Proceedings of the Fourth International Conference on Natural Language and Speech Processing, ICNLSP-2021, 2021
  • Akhbardeh, Farhad; Arkhangorodsky, Arkady; Biesialska, Magdalena; Bojar, Ondřej; Chatterjee, Rajen; Chaudhary, Vishrav; Costa-jussa, Marta R.; España-Bonet, Cristina; Fan, Angela; Federmann, Christian; Freitag, Markus; Graham, Yvette; Grundkiewicz, Roman; Haddow, Barry; Harter, Leonie; Heafield, Kenneth; Homan, Christopher; Huck, Matthias; Amponsah-Kaakyire, Kwabena; Kasai, Jungo; Khashabi, Daniel; Knight, Kevin; Kocmi, Tom; Koehn, Philipp; Lourie, Nicholas; Monz, Christof; Morishita, Makoto; Nagata, Masaaki; Nagesh, Ajay; Nakazawa, Toshiaki; Negri, Matteo; Pal, Santanu; Auguste Tapo, Allahsera; Turchi, Marco; Vydrin, Valentin; Zampieri, Marcos, Findings of the 2021 Conference on Machine Translation, Proceedings of the Sixth Conference on Machine Translation, WMT-21, 2021
  • Gaido, Marco; Savoldi, Beatrice; Bentivolig, Luisa; Negri, Matteo; Turchi, Marco, How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation, Findings of the Association for Computational Linguistics, ACL-IJCNLP-2021, 2021
  • Martucci, Giuseppe; Cettolo, Mauro; Negri, Matteo; Turchi, Marco, Lexical Modeling of ASR Errors for Robust Speech Translation, Proceedings of Interspeech 2021, Interspeech-2021, 2021
  • Anastasopoulos, Antonios; Bojar, Ondřej; Bremerman, Jacob; Cattoni, Roldano; Elbayad, Maha; Federico, Marcello; Xutai, Ma; Nakamura, Satoshi; Negri, Matteo; Niehues, Jan; Pino, Juan; Salesky, Elizabeth; Stüker, Sebastian; Sudoh, Katsuhito; Turchi, Marco; Waibel, Alexander; Wang, Changhan; Wiesner, Matthew, Findings of the IWSLT 2021 Evaluation Campaign , Proceedings of the 18th International Conference on Spoken Language Translation, IWSLT-2021, 2021
  • Lakew, Surafel M.; Negri, Matteo; Turchi, Marco, Zero-Shot Neural Machine Translation with Self-Learning Cycle, Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages at the 18th Biennial Machine Translation Summit Interspeech 2021, LoResMT-2021, 2021
  •  Salesky, Elizabeth; Wiesner, Matthew; Bremerman, Jacob; Cattoni, Roldano; Negri, Matteo; Turchi, Marco; Oard, Douglas W.; Post, Matt, Lexical Modeling of ASR Errors for Robust Speech Translation, Proceedings of Interspeech 2021, Interspeech-2021, 2021
  • Bentivogli, Luisa; Cettolo, Mauro; Gaido, Marco; Karakanta, Alina; Martinelli, Alberto; Negri, Matteo; Turchi, Marco, Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?, Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), ACL-2021, 2021
  • Consoli, Sergio; Negri, Matteo; Tebbifakhr, Amirhossein; Tosetti, Elisa; Turchi, Marco, Forecasting the IBEX-35 stock index using deep learning and news emotions, Proceedings of the 7th International Conference on Machine Learning, Optimization and Data Science, LOD-2021, 2021
  • Gaido, Marco; Rodríguez, Susana; Negri, Matteo; Bentivogli, Luisa; Turchi, Marco, Is “moby dick” a Whale or a Bird? Named Entities and Terminology in Speech Translation, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP-2021, 2021
  • Gaido, Marco; Cettolo, Mauro; Negri, Matteo; Turchi, Marco, CTC-based Compression for Direct Speech Translation, Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, EACL-2021, 2021