Abstract
Unsupervised dependency parsing, which tries to discover linguistic dependency structures from unannotated data, is a very challenging task. Almost all previous work on this task focuses on learning generative models. In this paper, we develop an unsupervised dependency parsing model based on the CRF autoencoder. The encoder part of our model is discriminative and globally normalized which allows us to use rich features as well as universal linguistic priors. We propose an exact algorithm for parsing as well as a tractable learning algorithm. We evaluated the performance of our model on eight multilingual treebanks and found that our model achieved comparable performance with state-of-the-art approaches.- Anthology ID:
- D17-1171
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1638–1643
- Language:
- URL:
- https://aclanthology.org/D17-1171
- DOI:
- 10.18653/v1/D17-1171
- Cite (ACL):
- Jiong Cai, Yong Jiang, and Kewei Tu. 2017. CRF Autoencoder for Unsupervised Dependency Parsing. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1638–1643, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- CRF Autoencoder for Unsupervised Dependency Parsing (Cai et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/D17-1171.pdf