@InProceedings{yin-schutze:2017:EACLlong,
  author    = {Yin, Wenpeng  and  Sch\"{u}tze, Hinrich},
  title     = {Task-Specific Attentive Pooling of Phrase Alignments Contributes to Sentence Matching},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {699--709},
  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.},
  url       = {http://www.aclweb.org/anthology/E17-1066}
}