Abstract
In this paper we demonstrate that context free grammar (CFG) based methods for grammar induction benefit from modeling lexical dependencies. This contrasts to the most popular current methods for grammar induction, which focus on discovering either constituents or dependencies. Previous approaches to marry these two disparate syntactic formalisms (e.g., lexicalized PCFGs) have been plagued by sparsity, making them unsuitable for unsupervised grammar induction. However, in this work, we present novel neural models of lexicalized PCFGs that allow us to overcome sparsity problems and effectively induce both constituents and dependencies within a single model. Experiments demonstrate that this unified framework results in stronger results on both representations than achieved when modeling either formalism alone.1- Anthology ID:
- 2020.tacl-1.42
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 8
- Month:
- Year:
- 2020
- Address:
- Cambridge, MA
- Editors:
- Mark Johnson, Brian Roark, Ani Nenkova
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 647–661
- Language:
- URL:
- https://aclanthology.org/2020.tacl-1.42
- DOI:
- 10.1162/tacl_a_00337
- Cite (ACL):
- Hao Zhu, Yonatan Bisk, and Graham Neubig. 2020. The Return of Lexical Dependencies: Neural Lexicalized PCFGs. Transactions of the Association for Computational Linguistics, 8:647–661.
- Cite (Informal):
- The Return of Lexical Dependencies: Neural Lexicalized PCFGs (Zhu et al., TACL 2020)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2020.tacl-1.42.pdf