Abstract
We extend a pair of continuous combinator-based constituency parsers (one binary and one multi-branching) into a discontinuous pair. Our parsers iteratively compose constituent vectors from word embeddings without any grammar constraints. Their empirical complexities are subquadratic. Our extension includes 1) a swap action for the orientation-based binary model and 2) biaffine attention for the chunker-based multi-branching model. In tests conducted with the Discontinuous Penn Treebank and TIGER Treebank, we achieved state-of-the-art discontinuous accuracy with a significant speed advantage.- Anthology ID:
- 2023.tacl-1.16
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 11
- Month:
- Year:
- 2023
- Address:
- Cambridge, MA
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 267–283
- Language:
- URL:
- https://aclanthology.org/2023.tacl-1.16
- DOI:
- 10.1162/tacl_a_00546
- Cite (ACL):
- Zhousi Chen and Mamoru Komachi. 2023. Discontinuous Combinatory Constituency Parsing. Transactions of the Association for Computational Linguistics, 11:267–283.
- Cite (Informal):
- Discontinuous Combinatory Constituency Parsing (Chen & Komachi, TACL 2023)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2023.tacl-1.16.pdf