Inferring Logical Forms From Denotations

Abstract

A core problem in learning semantic parsers from denotations is picking out consistent logical forms--those that yield the correct denotation--from a combinatorially large space. To control the search space, previous work relied on restricted set of rules, which limits expressivity. In this paper, we consider a much more expressive class of logical forms, and show how to use dynamic programming to efficiently represent the complete set of consistent logical forms. Expressivity also introduces many more spurious logical forms which are consistent with the correct denotation but do not represent the meaning of the utterance. To address this, we generate fictitious worlds and use crowdsourced denotations on these worlds to filter out spurious logical forms. On the WikiTableQuestions dataset, we increase the coverage of answerable questions from 53.5% to 76%, and the additional crowdsourced supervision lets us rule out 92.1% of spurious logical forms.

arXiv commentPublished at the Association for Computational Linguistics (ACL) conference, 2016

References in corpus (5)

• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Neural Programmer-Interpreters
• Traversing Knowledge Graphs in Vector Space
• Neural Enquirer: Learning to Query Tables with Natural Language
• Cornell SPF: Cornell Semantic Parsing Framework

Cited by in corpus (10)

• Learning to Generalize from Sparse and Underspecified Rewards
• From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
• Semantic Parsing with Syntax- and Table-Aware SQL Generation
• Toward Code Generation: A Survey and Lessons from Semantic Parsing
• It was the training data pruning too!
• Question Generation from SQL Queries Improves Neural Semantic Parsing
• Weakly-supervised Neural Semantic Parsing with a Generative Ranker
• Effective Search of Logical Forms for Weakly Supervised Knowledge-Based Question Answering
• Merging Weak and Active Supervision for Semantic Parsing
• Logical Parsing from Natural Language Based on a Neural Translation Model