Abstract
Aspect term extraction is one of the fundamental subtasks in aspect-based sentiment analysis. Previous work has shown that sentences’ dependency information is critical and has been widely used for opinion mining. With recent success of deep learning in natural language processing (NLP), recurrent neural network (RNN) has been proposed for aspect term extraction and shows the superiority over feature-rich CRFs based models. However, because RNN is a sequential model, it can not effectively capture tree-based dependency information of sentences thus limiting its practicability. In order to effectively exploit sentences’ dependency information and leverage the effectiveness of deep learning, we propose a novel dependency-tree based convolutional stacked neural network (DTBCSNN) for aspect term extraction, in which tree-based convolution is introduced over sentences’ dependency parse trees to capture syntactic features. Our model is an end-to-end deep learning based model and it does not need any human-crafted features. Furthermore, our model is flexible to incorporate extra linguistic features to further boost the model performance. To substantiate, results from experiments on SemEval2014 Task4 datasets (reviews on restaurant and laptop domain) show that our model achieves outstanding performance and outperforms the RNN and CRF baselines.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In this paper, RNN refers to recurrent neural network.
- 2.
In order to simplify the description of our model, we define the several hidden neural networks being stacked together as SNN.
- 3.
- 4.
- 5.
- 6.
- 7.
References
Liu, B., Hu, M., Cheng, J.: Opinion observer: analyzing and comparing opinions on the web. In: WWW, pp. 342–351 (2005)
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493–2537 (2011)
Liu, P., Joty, S.R., Meng, H.M.: Fine-grained opinion mining with recurrent neural networks and word embeddings. In: EMNLP, pp. 1433–1443 (2015)
Jakob, N., Gurevych, I.: Extracting opinion targets in a single and cross-domain setting with conditional random fields. In: EMNLP, pp. 1035–1045 (2010)
Johansson, R., Moschitti, A.: Syntactic and semantic structure for opinion expression detection. In: CoNLL, pp. 67–76 (2010)
Johansson, R., Moschitti, A.: Extracting opinion expressions and their polarities-exploration of pipelines and joint models. In: ACL, pp. 101–106 (2011)
Li, F., Han, C., Huang, M., Zhu, X., Xia, Y., Zhang, S., Yu, H.: Structure-aware review mining and summarization. In: COLING, pp. 653–661 (2010)
Yin, Y., Wei, F., Dong, L., Xu, K., Zhang, M., Zhou, M.: Unsupervised word and dependency path embeddings for aspect term extraction. In: IJCAI, pp. 2979–2985 (2016)
Mou, L., Peng, H., Li, G., Xu, Y., Zhang, L., Jin, Z.: Discriminative neural sentence modeling by treebased convolution. In: EMNLP, pp. 2315–2325 (2015)
Mou, L., Li, G., Zhang, L., Wang, T., Jin, Z.: Convolutional neural networks over tree structures for programming language processing. In: AAAI, pp. 1287–1293 (2016)
Ma, M., Huang, L., Zhou, B., Xiang, B.: Dependency-based convolutional neural networks for sentence embedding. In: ACL, pp. 174–179 (2015)
Hu, M., Liu, B.: Mining and summarizing customer reviews. In: KDD, pp. 168–177 (2004)
Qiu, G., Liu, B., Bu, J., Chen, C.: Opinion word expansion and target extraction through double propagation. Comput. Linguist. 37(1), 9–27 (2011)
Jin, W., Ho, H.H.: A novel lexicalized hmm-based learning framework for web opinion mining. In: ICML, pp. 465–472. ACM (2009)
Yang, B., Cardie, C.: Extracting opinion expressions with semi-Markov conditional random fields. In: EMNLP, pp. 1335–1345 (2012)
Toh, Z., Wang, W.: DLIREC: aspect term extraction and term polarity classification system. In: SemEval, pp. 235–240 (2014)
Chernyshevich, M.: IHS R&D Belarus: cross-domain extraction of product features using CRF. In: SemEval, pp. 309–313 (2014)
Titov, I., McDonald, R.T.: Modeling online reviews with multi-grain topic models. In: WWW, pp. 111–120 (2008)
Moghaddam, S., Ester, M.: On the design of LDA models for aspect-based opinion mining. In: CIKM, pp. 803–812 (2012)
Irsoy, O., Cardie, C.: Opinion mining with deep recurrent neural networks. In: EMNLP, pp. 720–728 (2014)
Socher, R., Perelygin, A., Wu, J.Y., Chuang, J., Manning, C.D., Ng, A.Y., Potts, C.: Recursive deep models for semantic compositionality over a sentiment treebank. In: EMNLP, pp. 1631–1642 (2013)
Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP, pp. 1746–1751 (2014)
Klein, D., Manning, C.D.: Accurate unlexicalized parsing. In: ACL, pp. 423–430 (2003)
Acknowledgements
This work was supported by National Natural Science Foundation of China (No. 61602490) and the National High-tech Research and Development Program (863 Program) (No. 2014AA015105). Thanks for the anonymous reviewers for their valuable comments.
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
Ye, H., Yan, Z., Luo, Z., Chao, W. (2017). Dependency-Tree Based Convolutional Neural Networks for Aspect Term Extraction. In: Kim, J., Shim, K., Cao, L., Lee, JG., Lin, X., Moon, YS. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2017. Lecture Notes in Computer Science(), vol 10235. Springer, Cham. https://doi.org/10.1007/978-3-319-57529-2_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-57529-2_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-57528-5
Online ISBN: 978-3-319-57529-2
eBook Packages: Computer ScienceComputer Science (R0)