Abstract
Historical text normalization, the task of mapping historical word forms to their modern counterparts, has recently attracted a lot of interest (Bollmann, 2019; Tang et al., 2018; Lusetti et al., 2018; Bollmann et al., 2018;Robertson and Goldwater, 2018; Bollmannet al., 2017; Korchagina, 2017). Yet, virtually all approaches suffer from the two limitations: 1) They consider a fully supervised setup, often with impractically large manually normalized datasets; 2) Normalization happens on words in isolation. By utilizing a simple generative normalization model and obtaining powerful contextualization from the target-side language model, we train accurate models with unlabeled historical data. In realistic training scenarios, our approach often leads to reduction in manually normalized data at the same accuracy levels.- Anthology ID:
- 2020.acl-main.650
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7284–7295
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.650
- DOI:
- 10.18653/v1/2020.acl-main.650
- Cite (ACL):
- Peter Makarov and Simon Clematide. 2020. Semi-supervised Contextual Historical Text Normalization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7284–7295, Online. Association for Computational Linguistics.
- Cite (Informal):
- Semi-supervised Contextual Historical Text Normalization (Makarov & Clematide, ACL 2020)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/2020.acl-main.650.pdf