Acquisition of Phrase Correspondences using Natural Deduction Proofs

TL;DR

This paper introduces a novel method for detecting paraphrases through natural deduction proofs, enhancing the recognition of textual entailment by leveraging proof-based semantic relations and subgraph alignments.

Contribution

The paper presents a new proof-based approach for paraphrase detection that improves RTE accuracy and identifies paraphrases not present in existing databases.

Findings

Automatically detects paraphrases absent from current databases

Improves RTE accuracy using proof information

Uses graph reformulation and subgraph alignment techniques

Abstract

How to identify, extract, and use phrasal knowledge is a crucial problem for the task of Recognizing Textual Entailment (RTE). To solve this problem, we propose a method for detecting paraphrases via natural deduction proofs of semantic relations between sentence pairs. Our solution relies on a graph reformulation of partial variable unifications and an algorithm that induces subgraph alignments between meaning representations. Experiments show that our method can automatically detect various paraphrases that are absent from existing paraphrase databases. In addition, the detection of paraphrases using proof information improves the accuracy of RTE tasks.