Abstract
Neural lexicalized PCFGs (L-PCFGs) have been shown effective in grammar induction. However, to reduce computational complexity, they make a strong independence assumption on the generation of the child word and thus bilexical dependencies are ignored. In this paper, we propose an approach to parameterize L-PCFGs without making implausible independence assumptions. Our approach directly models bilexical dependencies and meanwhile reduces both learning and representation complexities of L-PCFGs. Experimental results on the English WSJ dataset confirm the effectiveness of our approach in improving both running speed and unsupervised parsing performance.- Anthology ID:
- 2021.acl-long.209
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2688–2699
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.209
- DOI:
- 10.18653/v1/2021.acl-long.209
- Cite (ACL):
- Songlin Yang, Yanpeng Zhao, and Kewei Tu. 2021. Neural Bi-Lexicalized PCFG Induction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2688–2699, Online. Association for Computational Linguistics.
- Cite (Informal):
- Neural Bi-Lexicalized PCFG Induction (Yang et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2021.acl-long.209.pdf
- Code
- sustcsonglin/TN-PCFG
- Data
- PTB Diagnostic ECG Database