Abstract
Measuring the semantic similarities between short texts is a critical and fundamental task because it is the basis for many applications. Although existing methods have explored this problem through enriching the short text representations based on the pre-trained word embeddings, the performance is still far from satisfaction because of the limited feature information. In this paper, we present an effective approach that combines convolutional neural network and long short-term memory to exploit from character-level to sentence-level features for performing the semantic matching of short texts. The proposed approach nicely models the feature information of sentences with the multiple representations and captures the rich matching patterns at different levels. Our model is rather generic and can hence be applied to matching tasks in different language. We use both paraphrase identification and semantic similarity tasks for evaluating our approach. The experimental results demonstrate that the proposed multiple-granularity neural sentence model obtains a significant improvement on measuring short texts similarity compared with the existing benchmark approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aliguliyev, R.M.: A new sentence similarity measure and sentence based extractive technique for automatic text summarization. Expert Syst. Appl. 36(4), 7764–7772 (2009)
Asli, E., Keller, B.: ASOBEK: twitter paraphrase identification with simple overlap features and SVMs. In: Proceedings of SemEval, pp. 64–69. ACL, Denver (2015)
Bertero, D., Fung, P.: HLTC-HKUST: a neural network paraphrase classifier using translation metrics, semantic roles and lexical similarity features. In: Proceedings of SemEval, pp. 23–28. ACL (2015)
Bicici, E.: RTM-DCU: predicting semantic similarity with referential translation machines. In: Proceedings of SemEval, pp. 56–63. ACL (2015)
Byeon, W., Breuel, T.M., Raue, F., Liwicki, M.: Scene labeling with LSTM recurrent neural networks. In: 2015 IEEE Conference on CVPR, pp. 3547–3555 (2015)
Das, D., Smith, N.A.: Paraphrase identification as probabilistic quasi-synchronous recognition. In: Proceedings of ACL and IJCNLP, pp. 468–476. ACL, Suntec, Singapore (2009)
Eyecioglu, A., Keller, B.: Twitter paraphrase identification with simple overlap features and SVMs. In: Proceedings of SemEval, pp. 64–69. ACL (2015)
Guo, W., Diab, M.: Modeling sentences in the latent space. In: Proceedings of ACL, pp. 864–872. ACL, Jeju Island (2012)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Hu, B., Lu, Z., Li, H., Chen, Q.: Convolutional neural network architectures for matching natural language sentences. In: Proceedings of NIPS, pp. 2042–2050. Curran Associates Inc. (2014)
Ji, Y., Eisenstein, J.: Discriminative improvements to distributional sentence similarity. In: Proceedings of EMNLP, pp. 891–896. ACL, Seattle (2013)
Huang, J., Ji, D., Yao, S., Huang, W.: Character-aware convolutional neural networks for paraphrase identification. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9948, pp. 177–184. Springer, Cham (2016). doi:10.1007/978-3-319-46672-9_21
Huang, J., Ji, D., Yao, S., Huang, W., Chen, B.: Learning phrase representations based on word and character embeddings. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9950, pp. 547–554. Springer, Cham (2016). doi:10.1007/978-3-319-46681-1_65
Kalchbrenner, N., Grefenstette, E., Blunsom, P.: A convolutional neural network for modelling sentences. In: Proceedings of ACL, pp. 655–665. ACL, Baltimore (2014)
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of EMNLP, pp. 1746–1751. ACL, Doha (2014)
Li, J., Luong, T., Jurafsky, D.: A hierarchical neural autoencoder for paragraphs and documents. In: Proceedings of ACL, pp. 1106–1115. ACL, Beijing (2015)
Lyu, C., Lu, Y., Ji, D., Chen, B.: Deep learning for textual entailment recognition. In: Tools with Artificial Intelligence (ICTAI), pp. 154–161. IEEE (2015)
Mihalcea, R., Corley, C.D., Strapparava, C.: Corpus-based and knowledge-based measures of text semantic similarity. In: Proceedings of AAAI, pp. 775–780 (2006)
Milajevs, D., Kartsaklis, D., Sadrzadeh, M., Purver, M.: Evaluating neural word representations in tensor-based compositional settings. In: Proceedings of EMNLP, pp. 708–719. ACL, Doha (2014)
Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Proceedings of EMNLP, pp. 1532–1543. ACL, Doha (2014)
Ronan, C., Jason, W.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of ICML, pp. 160–167 (2008)
Severyn, A., Moschitti, A.: Learning to rank short text pairs with convolutional deep neural networks. In: Proceedings of SIGIR, pp. 373–382 (2015)
Shengxian, W., Yanyan, L., Jiafeng, G., Jun, X., Liang, P., Xueqi, C.: A deep architecture for semantic matching with multiple positional sentence representations. In: Proceedings of AAAI, Phoenix, Arizona, pp. 2835–2841 (2016)
Socher, R., Huang, E.H., Pennin, J., Manning, C.D., Ng, A.Y.: Dynamic pooling and unfolding recursive autoencoders for paraphrase detection. In: Proceedings of NIPS, pp. 801–809. Curran Associates Inc. (2011)
Stefanescu, D., Rus, V., Niraula, N., Banjade, R.: Combining knowledge and corpus-based measures for word-to-word similarity. In: Proceedings of the Twenty-Seventh International Florida Artificial Intelligence Research Society Conference, pp. 87–90 (2014)
Tai, K.S., Socher, R., Manning, C.D.: Improved semantic representations from tree-structured long short-term memory networks. In: Proceedings of ACL. pp. 1556–1566. ACL, Beijing (2015)
Wei, X., Alan, R., Chris, C.B., William, B., Yangfeng, J.: Extracting lexically divergent paraphrases from twitter. TACL 2(1), 435–448 (2014)
Xiaodan, Z., Parinaz, S., Honhyu, G.: Long short-term memory over recursive structures. In: Proceedings of ICML, Beijing, China, pp. 1604–1612 (2015)
Xu, W., Callison-Burch, C., Dolan, B.: SemEval-2015 task 1: paraphrase and semantic similarity in twitter (PIT). In: Proceedings of SemEval, pp. 1–11. ACL (2015)
Yin, W., Schütze, H.: Convolutional neural network for paraphrase identification. In: Proceedings of NAACL, pp. 901–911. ACL (2015)
Yoon, K., Yacine, J., David, S., Alexander, M.: Character-aware neural language models. In: Proceedings of AAAI, pp. 2741–2749. AAAI (2016)
Zarrella, G., Henderson, J., Merkhofer, E.M., Strickhart, L.: MITRE: seven systems for semantic similarity in tweets. In: Proceedings of SemEval, pp. 12–17. ACL (2015)
Acknowledgments
This work was supported by the National Natural Science Foundation of China under grant 61133012 and 61373108, and supported by Humanities and Social Science Foundation of Ministry of Education of China (16YJCZH004).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Huang, J., Yao, S., Lyu, C., Ji, D. (2017). Multi-Granularity Neural Sentence Model for Measuring Short Text Similarity. In: Candan, S., Chen, L., Pedersen, T., Chang, L., Hua, W. (eds) Database Systems for Advanced Applications. DASFAA 2017. Lecture Notes in Computer Science(), vol 10177. Springer, Cham. https://doi.org/10.1007/978-3-319-55753-3_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-55753-3_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-55752-6
Online ISBN: 978-3-319-55753-3
eBook Packages: Computer ScienceComputer Science (R0)