Recognizing Entailment and Contradiction by Tree-based Convolution. (arXiv:1512.08422v1 [cs.CL])
Recognizing entailment and contradiction between two sentences has wide applications in NLP. Traditional methods include feature-rich classifiers or formal reasoning. However, they are usually limited in terms of accuracy and scope. Recently, the renewed prosperity neural networks has made many improvements in a variety of NLP tasks.