Recognizing Entailment and Contradiction by Tree-based Convolution
作者： Ge Li , Lili Mou , Rui Men , Rui Yan , Zhi Jin
DOI:
关键词:
摘要: In this paper, we propose the TBCNN-pair model to recognize entailment and contradiction between two sentences. our model, a tree-based convolutional neural network (TBCNN) captures sentence-level semantics; then heuristic matching layers like concatenation, element-wise product/difference combine information in individual Experimental results show that outperforms existing sentence encoding-based approaches by large margin.
arxiv.org
researchgate.net 参考文章(20)
Richard Socher, Andrew Y. Ng, Eric H. Huang, Christopher D. Manning, Jeffrey Pennington, Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions empirical methods in natural language processing. pp. 151- 161 ,(2011)
Bill MacCartney, Marie-Catherine de Marneffe, Christopher D. Manning, Generating Typed Dependency Parses from Phrase Structure Parses language resources and evaluation. pp. 449- 454 ,(2006)
Finley Lacatusu, Andrew Hickl, Sanda Harabagiu, Negation, contrast and contradiction in text processing national conference on artificial intelligence. pp. 755- 762 ,(2006)
Leon Bottou, Leon Bottou, V. Vapnik, Yann Lecun, I. Guyon, Eduard Sackinger, Corinna Cortes, Corinna Cortes, U.A. Muller, Patrice Simard, Patrice Simard, A. Brunot, Harris Drucker, Harris Drucker, L.D. Jackel, J. S. Denker, J. S. Denker, Comparison of learning algorithms for handwritten digit recognition EC2 & Cie. pp. 53- 60 ,(1995)
Lu Zhang, Ge Li, Zhi Jin, Lili Mou, Hao Peng, Yan Xu, Discriminative Neural Sentence Modeling by Tree-Based Convolution arXiv: Computation and Language. ,(2015)
Samuel R. Bowman, Gabor Angeli, Christopher Potts, Christopher D. Manning, A large annotated corpus for learning natural language inference empirical methods in natural language processing. pp. 632- 642 ,(2015) , 10.18653/V1/D15-1075
Bill MacCartney, Trond Grenager, Marie-Catherine de Marneffe, Daniel Cer, Christopher D. Manning, Learning to recognize features of valid textual entailments language and technology conference. pp. 41- 48 ,(2006) , 10.3115/1220835.1220841
Richard Socher, Andrew Y. Ng, Eric H. Huang, Christopher D Manning, Jeffrey Pennin, Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection neural information processing systems. ,vol. 24, pp. 801- 809 ,(2011)
Sanda Harabagiu, Andrew Hickl, Methods for Using Textual Entailment in Open-Domain Question Answering meeting of the association for computational linguistics. pp. 905- 912 ,(2006) , 10.3115/1220175.1220289
Ronan Collobert, Jason Weston, A unified architecture for natural language processing Proceedings of the 25th international conference on Machine learning - ICML '08. pp. 160- 167 ,(2008) , 10.1145/1390156.1390177