Year: 2017
Type: conference-paper
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-tosequence model over multiple KBs, when providing an encoding of the domain at decoding time.Our model achieves state-ofthe-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.
DOI: 10.18653/v1/p17-2098
Authors: Jonathan Herzig, Jonathan Berant
Institutions: Tel Aviv University, IBM Research - Haifa
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Israel Science Foundation
OpenAlex ID: W2587586352