TY - GEN
T1 - Neural semantic parsing over multiple knowledge-bases
AU - Herzig, Jonathan
AU - Berant, Jonathan
N1 - Funding Information: We thank Shimi Salant and the anonymous reviewers for their constructive feedback. This work was partially supported by the Israel Science Foundation, grant 942/16. Publisher Copyright: © 2017 Association for Computational Linguistics.
PY - 2017
Y1 - 2017
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85040623686
U2 - 10.18653/v1/P17-2098
DO - 10.18653/v1/P17-2098
M3 - Conference contribution
T3 - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
SP - 623
EP - 628
BT - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
PB - Association for Computational Linguistics (ACL)
T2 - 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Y2 - 30 July 2017 through 4 August 2017
ER -