@InProceedings{zhao-huang-ma:2016:COLING,
  author    = {Zhao, Kai  and  Huang, Liang  and  Ma, Mingbo},
  title     = {Textual Entailment with Structured Attentions and Composition},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {2248--2258},
  abstract  = {Deep learning techniques are increasingly popular in the textual entailment
	task, overcoming the fragility of traditional discrete models with hard
	alignments and logics. In particular, the recently proposed attention models
	(Rockta ̈schel et al., 2015; Wang and Jiang, 2015) achieves state-of-the-art
	accuracy by computing soft word alignments between the premise and hypothesis
	sentences. However, there remains a major limitation: this line of work
	completely ignores syntax and recursion, which is helpful in many traditional
	efforts. We show that it is beneficial to extend the attention model to tree
	nodes between premise and hypothesis. More importantly, this subtree-level
	attention reveals information about entailment relation. We study the recursive
	composition of this subtree-level entailment relation, which can be viewed as a
	soft version of the Natural Logic framework (MacCartney and Manning, 2009).
	Experiments show that our structured attention and entailment composition model
	can correctly identify and infer entailment relations from the bottom up, and
	bring significant improvements in accuracy.},
  url       = {http://aclweb.org/anthology/C16-1212}
}