Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning

TL;DR

This paper introduces a method to enhance CCG parsing consistency across multiple sentences using Markov Random Fields, leading to improved logical reasoning in text entailment tasks for English and Japanese.

Contribution

It presents a novel inter-sentence modeling approach with MRFs to ensure consistent CCG parsing, improving logical reasoning performance.

Findings

Improved RTE accuracy on English and Japanese datasets.

Consistent parsing reduces predicate argument inconsistencies.

Method integrates seamlessly with existing logic-based systems.

Abstract

In formal logic-based approaches to Recognizing Textual Entailment (RTE), a Combinatory Categorial Grammar (CCG) parser is used to parse input premises and hypotheses to obtain their logical formulas. Here, it is important that the parser processes the sentences consistently; failing to recognize a similar syntactic structure results in inconsistent predicate argument structures among them, in which case the succeeding theorem proving is doomed to failure. In this work, we present a simple method to extend an existing CCG parser to parse a set of sentences consistently, which is achieved with an inter-sentence modeling with Markov Random Fields (MRF). When combined with existing logic-based systems, our method always shows improvement in the RTE experiments on English and Japanese languages.