Nothing Special   »   [go: up one dir, main page]

Parsing into Variable-in-situ Logico-Semantic Graphs

Yufei Chen, Weiwei Sun


Abstract
We propose variable-in-situ logico-semantic graphs to bridge the gap between semantic graph and logical form parsing. The new type of graph-based meaning representation allows us to include analysis for scope-related phenomena, such as quantification, negation and modality, in a way that is consistent with the state-of-the-art underspecification approach. Moreover, the well-formedness of such a graph is clear, since model-theoretic interpretation is available. We demonstrate the effectiveness of this new perspective by developing a new state-of-the-art semantic parser for English Resource Semantics. At the core of this parser is a novel neural graph rewriting system which combines the strengths of Hyperedge Replacement Grammar, a knowledge-intensive model, and Graph Neural Networks, a data-intensive model. Our parser achieves an accuracy of 92.39% in terms of elementary dependency match, which is a 2.88 point improvement over the best data-driven model in the literature. The output of our parser is highly coherent: at least 91% graphs are valid, in that they allow at least one sound scope-resolved logical form.
Anthology ID:
2020.acl-main.605
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6772–6782
Language:
URL:
https://aclanthology.org/2020.acl-main.605
DOI:
10.18653/v1/2020.acl-main.605
Bibkey:
Cite (ACL):
Yufei Chen and Weiwei Sun. 2020. Parsing into Variable-in-situ Logico-Semantic Graphs. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6772–6782, Online. Association for Computational Linguistics.
Cite (Informal):
Parsing into Variable-in-situ Logico-Semantic Graphs (Chen & Sun, ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.605.pdf
Software:
 2020.acl-main.605.Software.tgz
Video:
 http://slideslive.com/38929396