Neural symbolic machines: Learning semantic parsers on freebase with weak supervision

Chen Liang, Jonathan Berant, Quoc Le, Kenneth D. Forbus, Ni Lao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

88 Scopus citations

Abstract

Harnessing the statistical power of neural networks to perform language understanding and symbolic reasoning is difficult, when it requires executing efficient discrete operations against a large knowledge-base. In this work, we introduce a Neural Symbolic Machine (NSM), which contains (a) a neural "programmer", i.e., a sequence-to-sequence model that maps language utterances to programs and utilizes a key-variable memory to handle compositionality (b) a symbolic "computer", i.e., a Lisp interpreter that performs program execution, and helps find good programs by pruning the search space. We apply REINFORCE to directly optimize the task reward of this structured prediction problem. To train with weak supervision and improve the stability of REINFORCE we augment it with an iterative maximum-likelihood training process. NSM outperforms the state-of-the-art on the WEBQUESTIONSSP dataset when trained from question-answer pairs only, without requiring any feature engineering or domain-specific knowledge.

Original languageEnglish (US)
Title of host publicationACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages23-33
Number of pages11
ISBN (Electronic)9781945626753
DOIs
StatePublished - 2017
Event55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
Duration: Jul 30 2017Aug 4 2017

Publication series

NameACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume1

Other

Other55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/TerritoryCanada
CityVancouver
Period7/30/178/4/17

ASJC Scopus subject areas

  • Language and Linguistics
  • Artificial Intelligence
  • Software
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Neural symbolic machines: Learning semantic parsers on freebase with weak supervision'. Together they form a unique fingerprint.

Cite this