CLApr 20, 2018

Acquisition of Phrase Correspondences using Natural Deduction Proofs

arXiv:1804.07656v11104 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of phrasal knowledge acquisition for RTE systems, but it appears incremental as it builds on existing proof-based methods.

The authors tackled the problem of identifying and extracting phrasal knowledge for Recognizing Textual Entailment (RTE) by proposing a method to detect paraphrases using natural deduction proofs of semantic relations between sentence pairs. The result showed that their method can automatically detect paraphrases absent from existing databases and improves RTE accuracy.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes