Convolutional Network-Based Semantic Similarity Model of Sentences

被引：2
|
作者：
Huang J.-P. [1 ]
Ji D.-H. [1 ]
机构：
[1] Computer School, Wuhan University, Wuhan, 430072, Hubei
来源：
| 2017年 / South China University of Technology卷 / 45期
基金：
中国国家自然科学基金;
关键词：
Convolutional network; Paraphrase identification; Semantic similarity; Sentence model;
D O I：
10.3969/j.issn.1000-565X.2017.03.010
中图分类号：
学科分类号：
摘要：
Computing the semantic similarity between two sentences is an important research issue in natural language processing field, and, constructing an effective semantic model of sentences is the core task of natural language processing for paraphrase identification, textual similarity computation, question/answer and textual entailment. In this paper, a parallel convolutional neural network model is proposed to represent sentences with fixed-length vectors, and a similarity layer is used to measure the similarity of sentence pairs. Then, two tasks, namely paraphrase identification and textual similarity test, are used to evaluate the performance of the proposed model. Experimental results show that the proposed model can capture sentence's semantic information effectively; and that, in comparison with the state-of-the-art baseline, the proposed model improves the F1-score in paraphrase identification by 7.4 percentage points, while in comparison with the logistic regression method, it improves the Pearson correlation coefficient in semantic similarity by 7.1 percentage points. © 2017, Editorial Department, Journal of South China University of Technology. All right reserved.
引用
收藏
页码：68 / 75
页数：7
相关论文
共 21 条
  • [1] Kalchbrenner N., Grefenstette E., Blunsom P., A convolutional neural network for modelling sentences, Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pp. 655-665, (2014)
  • [2] Jeff M., Mirella L., Composition in distributional mo-dels of semantics, Cognitive Science, 34, 8, pp. 1388-1429, (2010)
  • [3] William B., Mirella L., A comparison of vector-based representations for semantic composition, Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 546-556, (2012)
  • [4] Fabio M.Z., Ioannis K., Francesca F., Et al., Estimating linear models for compositional distributional semantics, Proceedings of the 23rd International Conference on Computational Linguistics, pp. 1263-1271, (2010)
  • [5] Dimitri K., Mehrnoosh S., Prior disambiguation of word tensor for constructing sentence vectors, Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1590-1601, (2013)
  • [6] Yoon K., Convolutional neural networks for sentence classification, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp. 1746-1751, (2014)
  • [7] Yoshua B., Rejean D., Pascal V., Et al., A neural probabilistic language model, Journal of Machine Learning Research, 3, 6, pp. 1137-1155, (2003)
  • [8] Richard S., Cliff C.-Y.L., Andrew Y.N., Et al., Parsing natural scenes and natural language with recursive neural networks, Proceedings of the 28th International Conference on Machine Learning, (2011)
  • [9] Richard S., Eric H.H., Jeffrey P., Et al., Dynamic pooling and unfolding recursive autoencoders for paraphrase detection, Proceedings of the Advances in Neural Information Processing Systems, pp. 801-809, (2011)
  • [10] Kai S.T., Richard S., Christopher D.M., Improved semantic representations from tree-structured long short-term memory networks, Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, pp. 1556-1566, (2015)
123