COVER: Covering the Semantically Tractable Questions

Michael Minock


Abstract
In semantic parsing, natural language questions map to expressions in a meaning representation language (MRL) over some fixed vocabulary of predicates. To do this reliably, one must guarantee that for a wide class of natural language questions (the so called semantically tractable questions), correct interpretations are always in the mapped set of possibilities. In this demonstration, we introduce the system COVER which significantly clarifies, revises and extends the basic notion of semantic tractability. COVER achieves coverage of 89% while the earlier PRECISE system achieved coverage of 77% on the well known GeoQuery corpus. Like PRECISE, COVER requires only a simple domain lexicon and integrates off-the-shelf syntactic parsers. Beyond PRECISE, COVER also integrates off-the-shelf theorem provers to provide more accurate results. COVER is written in Python and uses the NLTK.
Anthology ID:
E17-3001
Volume:
Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
André Martins, Anselmo Peñas
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–4
Language:
URL:
https://aclanthology.org/E17-3001
DOI:
Bibkey:
Cite (ACL):
Michael Minock. 2017. COVER: Covering the Semantically Tractable Questions. In Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics, pages 1–4, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
COVER: Covering the Semantically Tractable Questions (Minock, EACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/E17-3001.pdf