Abstract
This paper describes the HEL-LJU submissions to the MultiLexNorm shared task on multilingual lexical normalization. Our system is based on a BERT token classification preprocessing step, where for each token the type of the necessary transformation is predicted (none, uppercase, lowercase, capitalize, modify), and a character-level SMT step where the text is translated from original to normalized given the BERT-predicted transformation constraints. For some languages, depending on the results on development data, the training data was extended by back-translating OpenSubtitles data. In the final ordering of the ten participating teams, the HEL-LJU team has taken the second place, scoring better than the previous state-of-the-art.- Anthology ID:
- 2021.wnut-1.52
- Volume:
- Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Editors:
- Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
- Venue:
- WNUT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 465–472
- Language:
- URL:
- https://aclanthology.org/2021.wnut-1.52
- DOI:
- 10.18653/v1/2021.wnut-1.52
- Cite (ACL):
- Yves Scherrer and Nikola Ljubešić. 2021. Sesame Street to Mount Sinai: BERT-constrained character-level Moses models for multilingual lexical normalization. In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pages 465–472, Online. Association for Computational Linguistics.
- Cite (Informal):
- Sesame Street to Mount Sinai: BERT-constrained character-level Moses models for multilingual lexical normalization (Scherrer & Ljubešić, WNUT 2021)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2021.wnut-1.52.pdf