Publications

You may find complete information on my Semantic Scholar, ACL Anthology, or HAL pages.

PhD thesis (in French)

Shu Okabe. Modèles faiblement supervisés pour la documentation automatique des langues (Weakly Supervised Models for Computational Language Documentation in English). Informatique et langage [cs.CL]. Université Paris-Saclay, 2023.

Articles

• Sebastian Reichbauer, Shu Okabe, and Alexander Fraser. 2026. Evaluating Latin and Ancient Greek Sentence Alignment through Parallel Sentence Mining. In Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities, pages 106–120, San Diego, USA. Association for Computational Linguistics.
• Volkan Özer, Shu Okabe, and Alexander Fraser. 2026. Interlinear Glosses as a Multilingual Pivot for Machine Translation: An Updated Study on Turkish with Restricted Resources. In Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages, pages 183–197, Palma, Mallorca, Spain. ELRA Language Resources Association (ELRA).
• Ruiyang Jiang, Shu Okabe, and Alexander Fraser. 2026. Parallel Sentence Filtering for Low-Resource Language Pairs: A Case Study for Upper Sorbian, German, and Czech. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 8883–8896, Palma de Mallorca, Spain. ELRA Language Resource Association.
• Shu Okabe*, Dejvi Zelo*, and Alexander Fraser. 2026. Optical Character Recognition for the International Phonetic Alphabet. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 265–273, Rabat, Morocco. Association for Computational Linguistics.
• Shu Okabe, Daryna Dementieva, Marion Di Marco, Lukas Edman, Katharina Hämmerl, Marko Měškank, Anita Hendrichowa, and Alexander Fraser. 2025. Findings of the WMT 2025 Shared Task LLMs with Limited Resources for Slavic Languages: MT and QA. In Proceedings of the Tenth Conference on Machine Translation, pages 503–519, Suzhou, China. Association for Computational Linguistics.
• Hiwa Asadpour*, Shu Okabe*, and Alexander Fraser. 2025. A Practical Tool to Help Automate Interlinear Glossing: a Study on Mukrī Kurdish. In Proceedings of the Fourth Workshop on NLP Applications to Field Linguistics, pages 65–75, Vienna, Austria. Association for Computational Linguistics.
• Shu Okabe, Katharina Hämmerl, and Alexander Fraser. 2025. Improving Parallel Sentence Mining for Low-Resource and Endangered Languages. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 196–205, Vienna, Austria. Association for Computational Linguistics.
• Shu Okabe and Alexander Fraser. 2025. Bilingual Sentence Mining for Low-Resource Languages: a Case Study on Upper and Lower Sorbian. In Proceedings of the Eighth Workshop on the Use of Computational Methods in the Study of Endangered Languages, pages 11–19, Honolulu, Hawaii, USA. Association for Computational Linguistics.
• Shu Okabe and François Yvon. 2023. Towards multilingual interlinear morphological glossing. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5958–5971, Singapore. Association for Computational Linguistics.
• Shu Okabe and François Yvon. 2023. LISN @ SIGMORPHON 2023 Shared Task on Interlinear Glossing. In Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 202–208, Toronto, Canada. Association for Computational Linguistics.
• Shu Okabe and François Yvon. 2023. Production automatique de gloses interlinéaires à travers un modèle probabiliste exploitant des alignements. In Actes de CORIA-TALN 2023. Actes de la 30e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : travaux de recherche originaux – articles longs, pages 262–274, Paris, France. ATALA.
• Shu Okabe and François Yvon. 2023. Joint Word and Morpheme Segmentation with Bayesian Non-Parametric Models. In Findings of the Association for Computational Linguistics: EACL 2023, pages 640–654, Dubrovnik, Croatia. Association for Computational Linguistics.
• Shu Okabe and François Yvon. 2022. Vers la génération automatique de gloses pour la documentation automatique des langues. In Journées Jointes des Groupements de Recherche Linguistique Informatique, Formelle et de Terrain (LIFT) et Traitement Automatique des Langues (TAL), pages 198–203, Marseille, France. CNRS.
• Shu Okabe and François Yvon. 2022. Modèle-s bayés-ien-s pour la segment-ation à deux niveau-x faible-ment super-vis-é-e (Bayesian models for weakly supervised two-level segmentation). In Actes de la 29e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 1 : conférence principale, pages 174–182, Avignon, France. ATALA.
• Shu Okabe, Laurent Besacier, and François Yvon. 2022. Weakly Supervised Word Segmentation for Computational Language Documentation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7385–7398, Dublin, Ireland. Association for Computational Linguistics.
• Shu Okabe, François Yvon, and Laurent Besacier. 2021. Segmentation en mots faiblement supervisée pour la documentation automatique des langues. In Journées du Groupement de Recherche Linguistique Informatique, Formelle et de Terrain (LIFT), Grenoble, France. CNRS.
• Shu Okabe*, Frédéric Blain*, and Lucia Specia. 2020. Multimodal Quality Estimation for Machine Translation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1233–1240, Online. Association for Computational Linguistics.
• Arnaud Pincet, Shu Okabe, and Martin Pawelczyk. 2019. Linking Aid to the Sustainable Development Goals – a machine learning approach. OECD Development Co-operation Working Papers.