Elamur Research⌕
☰
home / papers / 2021 / Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis

Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis

Paper · 2021 · Ruifan Li, Hao Chen, Fangxiang Feng et al.

Summary

Aspect-based sentiment analysis (ABSA) assigns a polarity to each aspect mentioned in a sentence. A review such as one praising a restaurant's price but criticizing its service needs a separate judgment for each aspect. Graph networks built on dependency trees link aspects to opinion words, but parser errors and the informal, messy style of online reviews limit how much they help. The authors propose DualGCN, which combines two graph convolutional branches:

  • SynGCN works on the full probability matrix of dependency arcs instead of a single discrete parse, so it keeps more syntactic information.
  • SemGCN builds its graph from self-attention scores to capture semantic links between words.

A BiAffine module exchanges information between the branches. Two regularizers shape the attention graph. An orthogonal one reduces overlap among the words each token attends to. A differential one pushes semantic features away from the syntactic ones. With BiLSTM or BERT encoders, the model is tested on SemEval 2014 Restaurant and Laptop and on Twitter. It beats prior GCN/GAT baselines on most metrics, which suggests syntax and semantics are complementary signals for ABSA.

Key points

  • BiLSTM results (Accuracy / Macro-F1):
    • Restaurant: 84.27 / 78.08
    • Laptop: 78.48 / 74.74
    • Twitter: 75.92 / 74.29
    • These beat baselines such as DGEDT, R-GAT, ASGCN and CDT.
  • DualGCN+BERT results (Accuracy / Macro-F1):
    • Restaurant: 87.13 / 81.16
    • Laptop: 81.80 / 78.10
    • Twitter: 77.40 / 76.02
    • DGEDT+BERT still has higher Twitter accuracy (77.90), and R-GAT+BERT has slightly higher Restaurant Macro-F1 (81.35).
  • Ablation: each component adds value. Removing both regularizers lowers Laptop accuracy to 76.58. Removing BiAffine also hurts all datasets.
  • Depth: two DualGCN layers worked best among the 1–8 layers tested.
  • Code: source code and preprocessed data are released at github.com/CCChenhao997/DualGCN-ABSA.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Carnegie Mellon UniversityPittsburgh · United States365 works · 158,048 citations🎓Beijing University of Posts and TelecommunicationsBeijing · China22 works · 32,364 citations

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 1Research subjects and languages the work is about.Sentiment & emotion · 608 works

Cite

Cite as Ruifan Li, Hao Chen, Fangxiang Feng, Zhanyu Ma, Xiaojie Wang and Eduard Hovy. 2021. Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.acl-long.494

@inproceedings{li2021dual,
  title = {{Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis}},
  author = {Ruifan Li, Hao Chen, Fangxiang Feng, Zhanyu Ma, Xiaojie Wang and Eduard Hovy},
  booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  year = {2021},
  doi = {10.18653/v1/2021.acl-long.494},
  url = {https://doi.org/10.18653/v1/2021.acl-long.494}
}

References

37 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Chenhua Chen, Zhiyang Teng, and Yue Zhang. 2020. Inducing target-specific latent structures for aspect sentiment classification. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5596–5607, Online. Association for Computational Linguistics. find
  2. Peng Chen, Zhongqian Sun, Lidong Bing, and Wei Yang. 2017. Recurrent attention network on memory for aspect sentiment analysis. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 452–461, Copenhagen, Denmark. Association for Computational Linguistics.
  3. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
  4. Li Dong, Furu Wei, Chuanqi Tan, Duyu Tang, Ming Zhou, and Ke Xu. 2014. Adaptive recursive neural network for target-dependent Twitter sentiment classification. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2), pages 49–54, Baltimore, Maryland. Ass…
  5. Feifan Fan, Yansong Feng, and Dongyan Zhao. 2018. Multi-grained attention network for aspect-level sentiment classification. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3433–3442, Brussels, Belgium. Association for Computational Linguistics.
  6. Shuqin Gu, Lipeng Zhang, Yuexian Hou, and Yin Song. 2018. A position-aware bidirectional attention network for aspect-level sentiment analysis. In Proceedings of the 27th International Conference on Computational Linguistics, pages 774–784, Santa Fe, New Mexico, USA. Association for Computational Li… find
  7. Ruidan He, Wee Sun Lee, Hwee Tou Ng, and Daniel Dahlmeier. 2018. Effective attention modeling for aspect-level sentiment classification. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1121–1131, Santa Fe, New Mexico, USA. Association for Computational Linguis… find
  8. Binxuan Huang and Kathleen Carley. 2019. Syntax-aware aspect level sentiment classification with graph attention networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP…
  9. Binxuan Huang, Yanglan Ou, and Kathleen M. Carley. 2018. Aspect level sentiment classification with attention-over-attention neural networks. CoRR, abs/1804.06536. — [arXiv:1804.06536](https://arxiv.org/abs/1804.06536) find
  10. Long Jiang, Mo Yu, Ming Zhou, Xiaohua Liu, and Tiejun Zhao. 2011. Target-dependent Twitter sentiment classification. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 151–160, Portland, Oregon, USA. Association for Computat… find
  11. Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017.
  12. Svetlana Kiritchenko, Xiaodan Zhu, Colin Cherry, and Saif Mohammad. 2014. NRC-Canada-2014: Detecting aspects and sentiment in customer reviews. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 437– 442, Dublin, Ireland. Association for Computational Lingu…
  13. Jiwei Li and Eduard Hovy. 2017. Reflections on sentiment/opinion analysis. In A Practical Guide to Sentiment Analysis, pages 41–59, Cham. Springer International Publishing. find
  14. Lishuang Li, Yang Liu, and AnQiao Zhou. 2018a. Hierarchical attention based position-aware network for aspect-level sentiment analysis. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 181–189, Brussels, Belgium. Association for Computational Linguistics. find
  15. Xin Li, Lidong Bing, Wai Lam, and Bei Shi. 2018b. Transformation networks for target-oriented sentiment classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 946– 956, Melbourne, Australia. Association for Computatio…
  16. Bin Liang, Rongdi Yin, Lin Gui, Jiachen Du, and Ruifeng Xu. 2020. Jointly learning aspect-focused and inter-aspect relations with graph convolutional networks for aspect sentiment analysis. In Proceedings of the 28th International Conference on Computational Linguistics, pages 150–161, Barcelona, Sp… find
  17. Bing Liu. 2012. Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 5(1):1–167. find
  18. Dehong Ma, Sujian Li, Xiaodong Zhang, and Houfeng Wang. 2017. Interactive attention networks for aspect-level sentiment classification. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, IJCAI’17, page 4068–4074. AAAI Press. find
  19. Diego Marcheggiani and Ivan Titov. 2017. Encoding sentences with graph convolutional networks for semantic role labeling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1506–1515, Copenhagen, Denmark. Association for Computational Linguistics.
  20. Khalil Mrini, Franck Dernoncourt, Trung Bui, Walter Chang, and Ndapa Nakashole. 2019. Rethinking self-attention: An interpretable self-attentive encoder-decoder parser. arXiv preprint arXiv:1911.03875. — [arXiv:1911.03875](https://arxiv.org/abs/1911.03875) find
  21. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. GloVe: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543, Doha, Qatar. Association for Computational Linguistics.
  22. Hao Tang, Donghong Ji, Chenliang Li, and Qiji Zhou. 2020. Dependency graph enhanced dual-transformer structure for aspect-based sentiment classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6578–6588, Online. Association for Computational…
  23. Minh Hieu Phan and Philip O. Ogunbona. 2020. Modelling context and syntactical features for aspect-based sentiment analysis. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3211–3220, Online. Association for Computational Linguistics. find
  24. Ivan Titov and Ryan McDonald. 2008. Modeling online reviews with multi-grain topic models. In Proceedings of the 17th International Conference on World Wide Web, page 111–120, New York, NY, USA. Association for Computing Machinery. find
  25. Maria Pontiki, Dimitris Galanis, John Pavlopoulos, Harris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. 2014. SemEval-2014 task 4: Aspect based sentiment analysis. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 27–35, Dublin, Ireland. Associa…
  26. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Proces…
  27. Chi Sun, Luyao Huang, and Xipeng Qiu. 2019a. Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1, pages 380–…
  28. Kai Sun, Richong Zhang, Samuel Mensah, Yongyi Mao, and Xudong Liu. 2019b. Aspect-level sentiment analysis via convolution over dependency tree. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Pro…
  29. Xingwei Tan, Yi Cai, and Changxi Zhu. 2019. Recognizing conflict opinions in aspect-level sentiment classification with dual attention networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Pr… find
  30. Duyu Tang, Bing Qin, and Ting Liu. 2016a. Aspect level sentiment classification with deep memory network. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 214–224, Austin, Texas. Association for Computational Linguistics.
  31. Duyu Tang, Bing Qin, and Ting Liu. 2016b. Aspect level sentiment classification with deep memory network. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 214–224, Austin, Texas. Association for Computational Linguistics.
  32. Duy-Tin Vo and Yue Zhang. 2015. Deep learning for event-driven stock prediction. In Proceedings of IJ-CAI, BueNos Aires, Argentina. find
  33. Kai Wang, Weizhou Shen, Yunyi Yang, Xiaojun Quan, and Rui Wang. 2020. Relational graph attention network for aspect-based sentiment analysis. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3229– 3238, Online. Association for Computational Linguistic…
  34. Yequan Wang, Minlie Huang, Xiaoyan Zhu, and Li Zhao. 2016. Attention-based LSTM for aspect-level sentiment classification. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 606–615, Austin, Texas. Association for Computational Linguistics.
  35. Hu Xu, Bing Liu, Lei Shu, and Philip Yu. 2019. BERT post-training for review reading comprehension and aspect-based sentiment analysis. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1, pages 2…
  36. Chen Zhang, Qiuchi Li, and Dawei Song. 2019. Aspect-based sentiment classification with aspect-specific graph convolutional networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, p…
  37. Mi Zhang and Tieyun Qian. 2020. Convolution over hierarchical syntactic and lexical graphs for aspect level sentiment analysis. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3540–3549, Online. Association for Computational Linguistics. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/li-2021-dual-graph-convolutional-networks-aspect/