Integrating Multiple Knowledge Sources for Robust Semantic Parsing

TL;DR

This paper presents a robust semantic parsing method that integrates multiple knowledge sources using a consistent labelling framework, achieving high accuracy in model identification and case-role filling.

Contribution

It introduces a novel approach that combines syntactic and semantic knowledge from various sources within a consistent labelling framework for semantic parsing.

Findings

95% accuracy in model identification

72% accuracy in case-role filling

Effective integration of linguistic and statistical knowledge

Abstract

This work explores a new robust approach for Semantic Parsing of unrestricted texts. Our approach considers Semantic Parsing as a Consistent Labelling Problem (CLP), allowing the integration of several knowledge types (syntactic and semantic) obtained from different sources (linguistic and statistic). The current implementation obtains 95% accuracy in model identification and 72% in case-role filling.