Paper Info
Title
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 frameworku0027s 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.
Year
Venue
Field
2017
conference of the european chapter of the association for computational linguistics
Phrase search,Computer science,Pooling,Phrase,Speech recognition,Phrase structure rules,Natural language processing,Artificial intelligence,Sentence
DocType
Volume
Citations 
Journal
abs/1701.02149
0
PageRank 
References 
Authors
0.34
30
2
Name
Order
Citations
PageRank
Wenpeng Yin138723.87
Hinrich Schütze22113362.21