Abstract
Most existing aspect-term level sentiment analysis (ATSA) approaches combined neural networks with attention mechanisms built upon given aspect to generate refined sentence representation for better predictions. In these methods, aspect terms are always provided in both training and testing process which may degrade aspect-level analysis into sentence-level prediction. However, the annotated aspect term might be unavailable in real-world scenarios which may challenge the applicability of the existing methods. In this paper, we aim to improve ATSA by discovering the potential aspect terms of the predicted sentiment polarity when the aspect terms of a test sentence are unknown. We access this goal by proposing a capsule network based model named CAPSAR. In CAPSAR, sentiment categories are denoted by capsules and aspect term information is injected into sentiment capsules through a sentiment-aspect reconstruction procedure during the training. As a result, coherent patterns between aspects and sentimental expressions are encapsulated by these sentiment capsules. Experiments on three widely used benchmarks demonstrate these patterns have potential in exploring aspect terms from test sentence when only feeding the sentence to the model. Meanwhile, the proposed CAPSAR can clearly outperform SOTA methods in standard ATSA tasks.
C. Xu and H. Feng—Equally contributed.
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
Similar content being viewed by others
Notes
- 1.
- 2.
The aspect embedding is calculated by the average of the word embeddings that form the aspect term.
- 3.
t is possibly larger than \(n_i\) because of sentence padding.
- 4.
The dimension of \(v_{mask}\) is C.
- 5.
If there are more than one aspect in a same sentence, every aspect will be separately trained.
- 6.
References
Chen, P., Sun, Z., Bing, L., Yang, W.: Recurrent attention network on memory for aspect sentiment analysis. In: EMNLP (2017)
Chen, Z., Qian, T.: Relation-aware collaborative learning for unified aspect-based sentiment analysis. In: ACL, pp. 3685–3694 (2020)
Cheng, J., Zhao, S., Zhang, J., King, I., Zhang, X., Wang, H.: Aspect-level sentiment classification with heat (hierarchical attention) network. In: CIKM, pp. 97–106 (2017)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)
Ding, X., Liu, B., Yu, P.S.: A holistic lexicon-based approach to opinion mining. In: WSDM (2008)
Dong, L., Wei, F., Tan, C., Tang, D., Zhou, M., Xu, K.: Adaptive recursive neural network for target-dependent Twitter sentiment classification. In: ACL (2014)
Du, C., et al.: Capsule network with interactive attention for aspect-level sentiment classification. In: EMNLP-IJCNLP (2019)
Fan, F., Feng, Y., Zhao, D.: Multi-grained attention network for aspect-level sentiment classification. In: EMNLP (2018)
He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: Effective attention modeling for aspect-level sentiment classification. In: COLING, pp. 1121–1131 (2018)
He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: Exploiting document knowledge for aspect-level sentiment classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Melbourne, Australia, pp. 579–585. ACL (July 2018)
He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: An interactive multi-task learning network for end-to-end aspect-based sentiment analysis. In: ACL, pp. 504–515 (2019)
Hinton, G.E., Sabour, S., Frosst, N.: Matrix capsules with em routing. In: ICLR (2018)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)
Hu, M., Peng, Y., Huang, Z., Li, D., Lv, Y.: Open-domain targeted sentiment analysis via span-based extraction and classification. In: ACL, pp. 537–546 (2019)
Hu, M., Liu, B.: Mining and summarizing customer reviews. In: KDD (2004)
Huang, B., Ou, Y., Carley, K.M.: Aspect level sentiment classification with attention-over-attention neural networks. In: SBP-BRiMS (2018)
Jiang, Q., Chen, L., Xu, R., Ao, X., Yang, M.: A challenge dataset and effective models for aspect-based sentiment analysis. In: EMNLP (2019)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Kiritchenko, S., Zhu, X., Cherry, C., Mohammad, S.: NRC-Canada-2014: detecting aspects and sentiment in customer reviews. In: Proceedings of the 8th International Workshop on Semantic Evaluation, SemEval 2014 (2014)
Lei, Z., Yang, Y., Yang, M., Zhao, W., Guo, J., Liu, Y.: A human-like semantic cognition network for aspect-level sentiment classification. AAAI 33, 6650–6657 (2019)
Li, X., Bing, L., Lam, W., Shi, B.: Transformation networks for target-oriented sentiment classification. In: ACL (2018)
Li, X., Bing, L., Li, P., Lam, W.: A unified model for opinion target extraction and target sentiment prediction. AAAI 33, 6714–6721 (2019)
Li, C., Quan, C., Li, P., Qi, Y., Deng, Y., Wu, L.: A capsule network for recommendation and explaining what you like and dislike. In: SIGIR (2019)
Liu, B.: Sentiment analysis and opinion mining. In: Synthesis Lectures on Human Language Technologies (2012)
Liu, J., Zhang, Y.: Attention modeling for targeted sentiment. In: ACL, pp. 572–577 (2017)
Luo, H., Li, T., Liu, B., Zhang, J.: DOER: dual cross-shared RNN for aspect term-polarity co-extraction. In: ACL, pp. 591–601 (2019)
Luo, L., et al.: Beyond polarity: interpretable financial sentiment analysis with hierarchical query-driven attention. In: IJCAI (2018)
Luo, L., et al.: Unsupervised neural aspect extraction with sememes. In: IJCAI (2019)
Ma, D., Li, S., Zhang, X., Wang, H.: Interactive attention networks for aspect-level sentiment classification. In: IJCAI (2017)
Mao, Q., et al.: Aspect-based sentiment classification with attentive neural turing machines. In: IJCAI (2019)
Peng, H., Xu, L., Bing, L., Huang, F., Lu, W., Si, L.: Knowing what, how and why: a near complete solution for aspect-based sentiment analysis. In: AAAI, pp. 8600–8607 (2020)
Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: EMNLP (2014)
Phan, M.H., Ogunbona, P.O.: Modelling context and syntactical features for aspect-based sentiment analysis. In: ACL, pp. 3211–3220 (2020)
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: NIPS (2017)
Socher, R., Pennington, J., Huang, E.H., Ng, A.Y., Manning, C.D.: Semi-supervised recursive autoencoders for predicting sentiment distributions. In: EMNLP (2011)
Tang, D., Qin, B., Feng, X., Liu, T.: Effective LSTMs for target-dependent sentiment classification. In: COLING (2016)
Tang, D., Qin, B., Liu, T.: Aspect level sentiment classification with deep memory network. In: EMNLP (2016)
Tang, J., et al.: Progressive self-supervised attention learning for aspect-level sentiment analysis. In: ACL, pp. 557–566 (2019)
Wang, B., Lu, W.: Learning latent opinions for aspect-level sentiment classification. In: AAAI (2018)
Wang, F., Lan, M., Wang, W.: Towards a one-stop solution to both aspect extraction and sentiment analysis tasks with neural multi-task learning. In: IJCNN, pp. 1–8 (2018)
Wang, J., Wang, Z., Zhang, D., Yan, J.: Combining knowledge with deep convolutional neural networks for short text classification. In: IJCAI (2017)
Wang, S., Mazumder, S., Liu, B., Zhou, M., Chang, Y.: Target-sensitive memory networks for aspect sentiment classification. In: ACL (2018)
Wang, Y., Huang, M., Zhao, L., et al.: Attention-based LSTM for aspect-level sentiment classification. In: EMNLP (2016)
Wang, Y., Sun, A., Han, J., Liu, Y., Zhu, X.: Sentiment analysis by capsules. In: The Web Conference (2018)
Wang, Y., Sun, A., Huang, M., Zhu, X.: Aspect-level sentiment analysis using AS-capsules. In: The Web Conference (2019)
Xue, W., Li, T.: Aspect based sentiment analysis with gated convolutional networks. In: ACL (2018)
Yang, Z., Yang, D., Dyer, C., He, X., Smola, A.J., Hovy, E.H.: Hierarchical attention networks for document classification. In: HLT-NAACL (2016)
Zhang, C., Li, Q., Song, D.: Aspect-based sentiment classification with aspect-specific graph convolutional networks. In: EMNLP, pp. 4560–4570 (2019)
Zhang, M., Zhang, Y., Vo, D.T.: Gated neural networks for targeted sentiment analysis. In: AAAI (2016)
Zhang, N., Deng, S., Sun, Z., Chen, X., Zhang, W., Chen, H.: Attention-based capsule networks with dynamic routing for relation extraction. In: EMNLP (2018)
Zhang, X., Li, P., Jia, W., Zhao, H.: Multi-labeled relation extraction with attentive capsule network. In: AAAI (2019)
Zhao, W., Ye, J., Yang, M., Lei, Z., Zhang, S., Zhao, Z.: Investigating capsule networks with dynamic routing for text classification. In: EMNLP (2018)
Acknowledgments
This work is supported by the National Natural Science Foundation of China under Grant No. 61976204, 92046003 and U1811461, the Project of Youth Innovation Promotion Association CAS and Beijing Nova Program Z201100006820062. This work was also supported by the Natural Science Foundation of Chongqing under Grant No. cstc2019jcyj-msxmX0149. Min Yang is partially supported by Shenzhen Basic Research Foundation (No. JCYJ20200109113441941).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, C. et al. (2021). Discovering Protagonist of Sentiment with Aspect Reconstructed Capsule Network. In: Jensen, C.S., et al. Database Systems for Advanced Applications. DASFAA 2021. Lecture Notes in Computer Science(), vol 12682. Springer, Cham. https://doi.org/10.1007/978-3-030-73197-7_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-73197-7_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73196-0
Online ISBN: 978-3-030-73197-7
eBook Packages: Computer ScienceComputer Science (R0)