A New Representation for Span-based CCG Parsing

Yoshihide Kato, Shigeki Matsubara


Abstract
This paper proposes a new representation for CCG derivations. CCG derivations are represented as trees whose nodes are labeled with categories strictly restricted by CCG rule schemata. This characteristic is not suitable for span-based parsing models because they predict node labels independently. In other words, span-based models may generate invalid CCG derivations that violate the rule schemata. Our proposed representation decomposes CCG derivations into several independent pieces and prevents the span-based parsing models from violating the schemata. Our experimental result shows that an off-the-shelf span-based parser with our representation is comparable with previous CCG parsers.
Anthology ID:
2021.emnlp-main.826
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10579–10584
Language:
URL:
https://aclanthology.org/2021.emnlp-main.826
DOI:
10.18653/v1/2021.emnlp-main.826
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.826.pdf
Code
 yosihide/span-based-ccg-derivation