Abstract
We propose a method for formulating CCG as a recursive composition in a continuous vector space. Recent CCG supertagging and parsing models generally demonstrate high performance, yet rely on black-box neural architectures to implicitly model phrase structure dependencies. Instead, we leverage the method of holographic embeddings as a compositional operator to explicitly model the dependencies between words and phrase structures in the embedding space. Experimental results revealed that holographic composition effectively improves the supertagging accuracy to achieve state-of-the-art parsing performance when using a C&C parser. The proposed span-based parsing algorithm using holographic composition achieves performance comparable to state-of-the-art neural parsing with Transformers. Furthermore, our model can semantically and syntactically infill text at the phrase level due to the decomposability of holographic composition.- Anthology ID:
- 2023.acl-long.15
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 262–276
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.15
- DOI:
- 10.18653/v1/2023.acl-long.15
- Cite (ACL):
- Ryosuke Yamaki, Tadahiro Taniguchi, and Daichi Mochihashi. 2023. Holographic CCG Parsing. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 262–276, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Holographic CCG Parsing (Yamaki et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2023.acl-long.15.pdf