Advertisement

Syntax-Aware Representation for Aspect Term Extraction

  • Jingyuan Zhang
  • Guangluan Xu
  • Xinyi Wang
  • Xian Sun
  • Tinglei HuangEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11439)

Abstract

Aspect Term Extraction (ATE) plays an important role in aspect-based sentiment analysis. Syntax-based neural models that learn rich linguistic knowledge have proven their effectiveness on ATE. However, previous approaches mainly focus on modeling syntactic structure, neglecting rich interactions along dependency arcs. Besides, these methods highly rely on results of dependency parsing and are sensitive to parsing noise. In this work, we introduce a syntax-directed attention network and a contextual gating mechanism to tackle these issues. Specifically, a graphical neural network is utilized to model interactions along dependency arcs. With the help of syntax-directed self-attention, it could directly operate on syntactic graph and obtain structural information. We further introduce a gating mechanism to synthesize syntactic information with structure-free features. This gate is utilized to reduce the effects of parsing noise. Experimental results demonstrate that the proposed method achieves state-of-the-art performance on three widely used benchmark datasets.

Keywords

Aspect term extraction Syntactic information Gating mechanism 

Notes

Acknowledgements

We thank Xiao Liang, Hongzhi Zhang, Yunyan Zhang, Wenkai Zhang and Hongfeng Yu, and the anonymous reviewers for their thoughtful comments and suggestions.

References

  1. 1.
    Chen, K., Wang, R., Utiyama, M., Sumita, E., Zhao1, T.: Syntax-directed attention for neural machine translation. In: AAAI, pp. 4792–4799 (2018)Google Scholar
  2. 2.
    Chen, Z., Mukherjee, A., Liu, B.: Aspect extraction with automated prior knowledge learning. In: ACL, pp. 347–358 (2014)Google Scholar
  3. 3.
    Chernyshevich, M.: IHS R&D belarus: cross-domain extraction of product features using CRF. In: SemEval@COLING, pp. 309–313 (2014)Google Scholar
  4. 4.
    Choi, Y., Cardie, C., Riloff, E., Patwardhan, S.: Identifying sources of opinions with conditional random fields and extraction patterns. In: HLT/EMNLP, pp. 355–362 (2005)Google Scholar
  5. 5.
    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)zbMATHGoogle Scholar
  6. 6.
    Hu, M., Liu, B.: Mining opinion features in customer reviews. In: AAAI, pp. 775–760 (2004)Google Scholar
  7. 7.
    Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. CoRR abs/1508.01991 (2015)Google Scholar
  8. 8.
    Irsoy, O., Cardie, C.: Opinion mining with deep recurrent neural networks. In: EMNLP, pp. 720–728 (2014)Google Scholar
  9. 9.
    Li, F., et al.: Structure-aware review mining and summarization. In: COLING, pp. 653–661 (2010)Google Scholar
  10. 10.
    Li, X., Lam, W.: Deep multi-task learning for aspect term extraction with memory interaction. In: EMNLP, pp. 2886–2892 (2017)Google Scholar
  11. 11.
    Luo, H., Li, T., Liu, B., Wang, B., Unger, H.: Improving aspect term extraction with bidirectional dependency tree representation. CoRR abs/1805.07889 (2018)Google Scholar
  12. 12.
    Ma, X., Hovy, E.H.: End-to-end sequence labeling via bi-directional LSTM-CNNS-CRF. CoRR abs/1603.01354 (2016)Google Scholar
  13. 13.
    Marcheggiani, D., Titov, I.: Encoding sentences with graph convolutional networks for semantic role labeling. In: EMNLP, pp. 1506–1515 (2017)Google Scholar
  14. 14.
    Toh, Z., Wang, W.: DLIREC: aspect term extraction and term polarity classification system. In: SemEval@COLING, pp. 235–240 (2014)Google Scholar
  15. 15.
    Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)Google Scholar
  16. 16.
    Vicente, I.S., Saralegi, X., Agerri, R.: EliXa: a modular and flexible ABSA platform. In: SemEval@NAACL-HLT, pp. 748–752 (2015)Google Scholar
  17. 17.
    Wang, W., Pan, S.J., Dahlmeier, D., Xiao, X.: Recursive neural conditional random fields for aspect-based sentiment analysis. In: EMNLP, pp. 616–626 (2016)Google Scholar
  18. 18.
    Wang, W., Pan, S.J., Dahlmeier, D., Xiao, X.: Coupled multi-layer attentions for co-extraction of aspect and opinion terms. In: AAAI, pp. 3316–3322 (2017)Google Scholar
  19. 19.
    Ye, H., Yan, Z., Luo, Z., Chao, W.: Dependency-tree based convolutional neural networks for aspect term extraction. In: Kim, J., Shim, K., Cao, L., Lee, J.-G., Lin, X., Moon, Y.-S. (eds.) PAKDD 2017. LNCS (LNAI), vol. 10235, pp. 350–362. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-57529-2_28CrossRefGoogle Scholar
  20. 20.
    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)Google Scholar
  21. 21.
    Zhang, Y., Qi, P., Manning, C.D.: Graph convolution over pruned dependency trees improves relation extraction. CoRR abs/1809.10185 (2018)Google Scholar
  22. 22.
    Zhuang, L., Jing, F., Zhu, X.: Movie review mining and summarization. In: CIKM, pp. 43–50 (2006)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Jingyuan Zhang
    • 1
    • 2
  • Guangluan Xu
    • 1
  • Xinyi Wang
    • 1
    • 2
  • Xian Sun
    • 1
  • Tinglei Huang
    • 1
    Email author
  1. 1.Key Laboratory of Network Information System Technology (NIST), Institute of ElectronicsChinese Academy of SciencesBeijingChina
  2. 2.University of Chinese Academy of SciencesBeijingChina

Personalised recommendations