出版物
FormosanBank 的主要目標之一是提供全方位的語料，促進研究人員對臺灣南島語的研究工作。在此，提供我們利用 FormosanBank 語料所進行的研究成果。
Le Ferrand, É., Hauser, C. M. B., Hartshorne, J., & Prud’hommeaux, E. (2025). Faithful transcription: Leveraging Bible recordings to improve ASR for endangered languages. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 333–342.
Le Ferrand, É., Jiang, B., Hartshorne, J., & Prud’hommeaux, E. (2025). That doesn’t sound right: Evaluating speech transcription quality in field linguistics corpora. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 627–635.
Scheppat, H., Hartshorne, J., Leddy, D., Le Ferrand, E., & Prudhommeaux, E. (2025). Integrating diverse corpora for training an endangered language machine translation system. In Proceedings of the Eight Workshop on the Use of Computational Methods in the Study of Endangered Languages (ComputEL-8), 162–169.
Tall, O., Le Ferrand, É., Hartshorne, J., & Prud'hommeaux, E. (2024). Reclaiming Archival Texts with User-Friendly OCR. Poster presented at the 9th International Conference on Language Documentation & Conservation (ICLDC9), Miami, Florida.
Eric Le Ferrand, Zoey Liu, Antti Arppe, and Emily Prud'hommeaux. (2024). Are modern neural ASR architectures robust for polysynthetic languages?. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2953–2963, Miami, Florida, USA. Association for Computational Linguistics.
Last updated