Neural Semantic Parsing over Multiple Knowledge-bases

Jonathan Herzig, Jonathan Berant


Abstract
A fundamental challenge in developing semantic parsers is the paucity of strong supervision in the form of language utterances annotated with logical form. In this paper, we propose to exploit structural regularities in language in different domains, and train semantic parsers over multiple knowledge-bases (KBs), while sharing information across datasets. We find that we can substantially improve parsing accuracy by training a single sequence-to-sequence model over multiple KBs, when providing an encoding of the domain at decoding time. Our model achieves state-of-the-art performance on the Overnight dataset (containing eight domains), improves performance over a single KB baseline from 75.6% to 79.6%, while obtaining a 7x reduction in the number of model parameters.
Anthology ID:
P17-2098
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
623–628
Language:
URL:
https://aclanthology.org/P17-2098
DOI:
10.18653/v1/P17-2098
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/P17-2098.pdf
Code
 worksheets/0xdec998f5