Abstract
We address part-of-speech (POS) induction by maximizing the mutual information between the induced label and its context. We focus on two training objectives that are amenable to stochastic gradient descent (SGD): a novel generalization of the classical Brown clustering objective and a recently proposed variational lower bound. While both objectives are subject to noise in gradient updates, we show through analysis and experiments that the variational lower bound is robust whereas the generalized Brown objective is vulnerable. We obtain strong performance on a multitude of datasets and languages with a simple architecture that encodes morphology and context.- Anthology ID:
- N19-1113
- 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
- Editors:
- Jill Burstein, Christy Doran, Thamar Solorio
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1095–1104
- Language:
- URL:
- https://aclanthology.org/N19-1113
- DOI:
- 10.18653/v1/N19-1113
- Cite (ACL):
- Karl Stratos. 2019. Mutual Information Maximization for Simple and Accurate Part-Of-Speech Induction. 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 1095–1104, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Mutual Information Maximization for Simple and Accurate Part-Of-Speech Induction (Stratos, NAACL 2019)
- PDF:
- https://preview.aclanthology.org/naacl24-info/N19-1113.pdf
- Code
- karlstratos/mmi-tagger