Hinting Semantic Parsing with Statistical Word Sense Disambiguation

TL;DR

This paper proposes a method that integrates statistical word sense disambiguation hints into semantic parsing to improve semantic role assignment, achieving up to 10.5% F-score improvement but affecting parse structure.

Contribution

It introduces a novel approach combining statistical WSD hints with logical semantic parsing to enhance semantic role accuracy.

Findings

Up to 10.5% F-score improvement in semantic parsing

Improvement affects structural integrity of parses

Demonstrates benefit of combining statistical and logical methods

Abstract

The task of Semantic Parsing can be approximated as a transformation of an utterance into a logical form graph where edges represent semantic roles and nodes represent word senses. The resulting representation should be capture the meaning of the utterance and be suitable for reasoning. Word senses and semantic roles are interdependent, meaning errors in assigning word senses can cause errors in assigning semantic roles and vice versa. While statistical approaches to word sense disambiguation outperform logical, rule-based semantic parsers for raw word sense assignment, these statistical word sense disambiguation systems do not produce the rich role structure or detailed semantic representation of the input. In this work, we provide hints from a statistical WSD system to guide a logical semantic parser to produce better semantic type assignments while maintaining the soundness of the resulting logical forms. We observe an improvement of up to 10.5% in F-score, however we find that this improvement comes at a cost to the structural integrity of the parse