Task-Specific Attentive Pooling of Phrase Alignments Contributes to Sentence Matching

Abstract

This work studies comparatively two typical sentence matching tasks: textual entailment (TE) and answer selection (AS), observing that weaker phrase alignments are more critical in TE, while stronger phrase alignments deserve more attention in AS. The key to reach this observation lies in phrase detection, phrase representation, phrase alignment, and more importantly how to connect those aligned phrases of different matching degrees with the final classifier. Prior work (i) has limitations in phrase generation and representation, or (ii) conducts alignment at word and phrase levels by handcrafted features or (iii) utilizes a single framework of alignment without considering the characteristics of specific tasks, which limits the framework's effectiveness across tasks. We propose an architecture based on Gated Recurrent Unit that supports (i) representation learning of phrases of arbitrary granularity and (ii) task-specific attentive pooling of phrase alignments between two sentences. Experimental results on TE and AS match our observation and show the effectiveness of our approach.

arXiv commentEACL'2017 long paper. arXiv admin note: substantial text overlap with arXiv:1604.06896

Cited by in corpus (6)

• MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity
• NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning
• Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference
• REGMAPR - Text Matching Made Easy
• End-Task Oriented Textual Entailment via Deep Explorations of Inter-Sentence Interactions
• Acquisition of Phrase Correspondences using Natural Deduction Proofs