Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing

Jonathan Herzig, Jonathan Berant


Abstract
Building a semantic parser quickly in a new domain is a fundamental challenge for conversational interfaces, as current semantic parsers require expensive supervision and lack the ability to generalize to new domains. In this paper, we introduce a zero-shot approach to semantic parsing that can parse utterances in unseen domains while only being trained on examples in other source domains. First, we map an utterance to an abstract, domain independent, logical form that represents the structure of the logical form, but contains slots instead of KB constants. Then, we replace slots with KB constants via lexical alignment scores and global inference. Our model reaches an average accuracy of 53.4% on 7 domains in the OVERNIGHT dataset, substantially better than other zero-shot baselines, and performs as good as a parser trained on over 30% of the target domain examples.
Anthology ID:
D18-1190
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1619–1629
Language:
URL:
https://aclanthology.org/D18-1190
DOI:
10.18653/v1/D18-1190
Bibkey:
Cite (ACL):
Jonathan Herzig and Jonathan Berant. 2018. Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1619–1629, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing (Herzig & Berant, EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ml4al-ingestion/D18-1190.pdf
Code
 jonathanherzig/zero-shot-semantic-parsing