Abstract
Aspect-based sentiment classification aims to predict the sentiment polarity of specific aspects appeared in a sentence. Nowadays, most current methods mainly focus on the semantic information by exploiting traditional attention mechanisms combined with recurrent neural networks to capture the interaction between the contexts and the targets. However, these models did not consider the importance of the relevant syntactical constraints. In this paper, we propose to employ a novel gated graph convolutional networks on the dependency tree to encode syntactical information, and we design a Syntax-aware Context Dynamic Weighted layer to guide our model to pay more attention to the local syntax-aware context. Moreover, Multi-head Attention is utilized for capturing both semantic information and interactive information between semantics and syntax. We conducted experiments on five datasets and the results demonstrate the effectiveness of the proposed model.
Similar content being viewed by others
References
Bo P, Lee L (2008) Opinion mining and sentiment analysis. Found Trends Inf Ret 2:1–135
Bo P, Lee L et al (2008) Opinion mining and sentiment analysis. Found Trends Inf Ret 2(1–2):1–135
Bruna J, Zaremba W, Szlam A, LeCun Y (2014) Spectral networks and locally connected networks on graphs. In: Proceedings of the 2nd international conference on learning representations
Chen Z, Qian T (2019) Transfer capsule network for aspect level sentiment classification. In: Proceedings of ACL-2019, pp 547–556
Collobert R, Weston J, Bottou L, Karlen M, Kavukcuoglu K, Kuksa PP (2011) Natural language processing (almost) from scratch. J Mach Learn Res 12:2493–2537
Conneau A, Schwenk H, Barrault L, LeCun Y (2016) Very deep convolutional networks for text classification. In: EACL, pp 1107–1116
Devlin J, Chang M, Lee K, Toutanova K (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, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pp 4171–4186
Dong X, Shen J, Wang W et al (2018) Hyperparameter optimization for tracking with continuous deep q-learning[C]. In: Computer Vision and Pattern Recognition, pp 518–527
Dong X, Shen J, Wang W et al (2019) Dynamical hyperparameter optimization via deep reinforcement learning in tracking[J]. IEEE Trans Pattern Anal Mach Intell
Dong L, Wei F, Tan C, Tang D, Zhou M, Xu K (2014) Adaptive recursive neural network for target-dependent twitter sentiment classification. In: Proceedings of the 52nd annual meeting of the association for computational linguistics, vol 2, pp 49–54
Dong L, Wei F, Tan C, Tang D, Zhou M, Xu K (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: Short Papers), Baltimore, MD, USA, 23–25, pp 49–54
He R, Lee WS, Ng HT, Dahlmeier D (2018) Effective attention modeling for aspect-level sentiment classification. In: Proceedings of the 27th international conference on computational linguistics, pp 1121–1131
Hu J, Shen J, Yang B et al (2020) Infinitely wide graph convolutional networks: semi-supervised learning via gaussian processes[J]. arXiv:Learning
Huang B, Carley K (2018) Parameterized convolutional neural networks for aspect level sentiment classification. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 1091–1096
Huang B, Ou Y, Carley K (2018) Aspect level sentiment classification with attention-over-attention neural networks. In: International conference on social computing, behavioral-cultural modeling and prediction and behavior representation in modeling and simulation. Springer, pp 197– 206
Kalchbrenner N, Grefenstette E, Blunsom P (2014) A convolutional neural network for modelling sentences. In: ACL, pp 655–665
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907
Kiritchenko S, Zhu X, Cherry C, Mohammad S (2014) Nrc-canada-2014: Detecting aspects and sentiment in customer reviews. In: Proceedings of the 8th international workshop on semantic evaluation (SemEval 2014), Dublin, Ireland, pp 437–442
Li X, Bing L, Lam W, Shi B (2018) Transformation networks for target-oriented sentiment classification. arXiv:1805.01086
Li L, Liu Y, Zhou AnQiao (2018) Hierarchical attention-based position-aware network for aspect-level sentiment analysis. In: Proceedings of the 22nd conference on computational natural language learning, pp 181–189
Lin P, Yang M, Lai J (2019) Deep mask memory network with semantic dependency and context moment for aspect level sentiment classification. In: Proceedings of IJCAI-2019, pp 5088–5094
Ma D, Li S, Zhang X, Wang H (2017) Interactive attention networks for aspect-level sentiment classification. In: Proceedings of the 26th international joint conference on artificial intelligence. AAAI Press, pp 4068–4074
Marcheggiani D, Titov I (2017) Encoding sentences with graph convolutional networks for semantic role labeling. In: Proceedings of the 2017 conference on empirical methods in natural language processing, pp 1506–1515
Maria Pontiki DG, John Pavlopoulos HP, Ion Androutsopoulos SM (2014) Semeval-2014 task 4: SemEval-2014 Task 4: Aspect based sentiment analysis. In: Proceedings of the 8th international workshop on semantic evaluation (SemEval 2014), Dublin, Ireland, pp 27–35
Nguyen TH, Shirai K (2015) Phrasernn: Phrase recursive neural network for aspect-based sentiment analysis. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp 2509–2514
Nicola DC, Aziz W, Titov I (2018) Question answering by reasoning across documents with graph convolutional networks arXiv 2019. arXiv:1808.09920
Pennington J, Socher R, Manning C (2014) Glove: Global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532–1543
Pontiki M, Galanis D, Papageorgiou H, Androutsopoulos I, Manandhar S, Al-Smadi M, Al-Ayyoub M, Zhao Y, Qin B, de Clercq O et al (2016) Semeval-2016 task 5: Aspect based sentiment analysis. In: Proceedings of the 10th international workshop on semantic evaluation (SemEval-2016), San Diego, CA, USA, pp 19–30
Pontiki M, Galanis D, Papageorgiou H, Manandhar S, Androutsopoulos I (2015) Semeval-2015 task 12: Aspect based sentiment analysis. In: Proceedings of the 9th international workshop on semantic evaluation (SemEval 2015), Denver, Colorado, pp 486–495
Qi S, Wang W, Jia B et al (2018) Learning human-object interactions by graph parsing neural networks[C]. In: European conference on computer vision, pp 407–423
Schlichtkrull M, Kipf TN, Bloem P, Van Den Berg R, Titov I, MaxWelling (2018) Modeling relational data with graph convolutional networks. In: European semantic web conference. Springer, pp 593–607
Shen J, Tang X, Dong X et al (2019) Visual object tracking by hierarchical attention siamese network[J]. IEEE Trans Syst Man Cybern 1–13
Song Y, Wang J, Jiang T, Liu Z, Rao Y (2019) Attentional encoder network for targeted sentiment classification. arXiv:1902.09314
Tang D, Qin B, Feng X, Liu T (2016a) Effective lstms for target-dependent sentiment classification. In: Proceedings of COLING 2016, the 26th international conference on computational linguistics: Technical papers, pp 3298–3307
Tang D, Qin B, Liu T (2016b) Aspect level sentiment classification with deep memory network. arXiv:1502.03167
Wagner J et al (2014) DCU: Aspect-based polarity classification for semeval task 4. In: Proc. 8th Int. Workshop Semantic Eval. (SemEval), Dublin, Ireland, pp 223–229
Wang Y, Huang M, Li Z et al (2016) Attention-based lstm for aspect-level sentiment classification. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp 606–615
Wang W, Lu X, Shen J et al (2019) Zero-shot video object segmentation via attentive graph neural networks[C]. In: International conference on computer vision, pp 9236–9245
Wang W, Shen J (2018) Deep visual attention prediction[J]. IEEE Trans Image Process 27(5):2368–2378
Wang W, Shen J, Ling H et al (2019) A deep network solution for attention and aesthetics aware photo cropping[J]. IEEE Trans Pattern Anal Mach Intell 41(7):1531–1544
Wang J, Sun C, Li S, Liu X, Si L, Zhang M, Zhou G (2019a) Aspect sentiment classification towards question-answering with reinforced bidirectional attention network. In: Proceedings of ACL-2019, pp 3548–3557
Wu D, Dong X, Shen J et al (2020) Reducing estimation bias via triplet-average deep deterministic policy gradient[J]. IEEE Trans Neural Netw 1–13
Xiao L, Hu X, Chen Y, Xue Y, Gu D, Chen B, Zhang T (2020) Targeted sentiment classification based on attentional encoding and graph convolutional networks. Appl. Sci. 10:957
Xu H, Liu B, Shu L, Yu PS (2019) Bert post-training for review reading comprehension and aspect-based sentiment analysis. arXiv:1904.02232
Xue W, Li T (2018) Aspect based sentiment analysis with gated convolutional networks. arXiv:1502.03167
You H, Tian S, Yu L et al (2020) Pixel-level remote sensing image recognition based on bidirectional word vectors[J]. IEEE Trans Geosci Remote Sens 58(2):1281–1293
Zeng B, Yang H, Xu R, Zhou W, Han X (2019) LCF: A local context focus mechanism for aspect-based sentiment classification. Appl Sci 9:3389
Zhang C, Li Q, Song D (2018) Aspect-based sentiment classification with aspect-specific graph convolutional networks. arXiv:1909.03477
Zhang Y, Qi P, Manning C (2018) Graph convolution over pruned dependency trees improves relation extraction. arXiv:1809.10185
Zhaoa P, Houb L, Wua O (2019) Modeling sentiment dependencies with graph convolutional networks for aspect-level sentiment classification. arXiv:1906.04501
Acknowledgements
This work was supported by China Scholarship Council, the National Statistical Science Research Project of China under Grant No. 2016LY98, the Science and Technology Department of Guangdong Province in China under Grant Nos. 2016A010101020, 2016A010101021 and 2016A010101022, the Characteristic Innovation Projects of Guangdong Colleges and Universities (Nos. 2018KTSCX049 and 2018GKTSCX069), the Science and Technology Plan Project of Guangzhou under Grant Nos. 201802010033 and 201903010013.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xiao, L., Hu, X., Chen, Y. et al. Multi-head self-attention based gated graph convolutional networks for aspect-based sentiment classification. Multimed Tools Appl 81, 19051–19070 (2022). https://doi.org/10.1007/s11042-020-10107-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-10107-0