Abstract
Character-level models of tokens have been shown to be effective at dealing with within-token noise and out-of-vocabulary words. However, they often still rely on correct token boundaries. In this paper, we propose to eliminate the need for tokenizers with an end-to-end character-level semi-Markov conditional random field. It uses neural networks for its character and segment representations. We demonstrate its effectiveness in multilingual settings and when token boundaries are noisy: It matches state-of-the-art part-of-speech taggers for various languages and significantly outperforms them on a noisy English version of a benchmark dataset. Our code and the noisy dataset are publicly available at http://cistern.cis.lmu.de/semiCRF.- Anthology ID:
- N19-1280
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2736–2743
- Language:
- URL:
- https://aclanthology.org/N19-1280
- DOI:
- 10.18653/v1/N19-1280
- Cite (ACL):
- Apostolos Kemos, Heike Adel, and Hinrich Schütze. 2019. Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2736–2743, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging (Kemos et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/N19-1280.pdf