Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Multi-label Classification of Long Text Based on Key-Sentences Extraction Read chapter Read first chapter

2021 | OriginalPaper | Chapter

Discovering Protagonist of Sentiment with Aspect Reconstructed Capsule Network

Authors : Chi Xu, Hao Feng, Guoxin Yu, Min Yang, Xiting Wang, Yan Song, Xiang Ao

Published in: Database Systems for Advanced Applications

Publisher: Springer International Publishing

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

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.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
previous chapter Discriminative Feature Adaptation via Conditional Mean Discrepancy for Cross-Domain Text Classification
next chapter Discriminant Mutual Information for Text Feature Selection
Footnotes
1
Here we refer to the capsule network proposed by [34]. Though the models in [44] and [45] also called capsule network in their papers, they are basically built upon RNN and attention mechanisms with distinct concepts and implementations.
 
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.
 
Literature
1.
Chen, P., Sun, Z., Bing, L., Yang, W.: Recurrent attention network on memory for aspect sentiment analysis. In: EMNLP (2017)
2.
Chen, Z., Qian, T.: Relation-aware collaborative learning for unified aspect-based sentiment analysis. In: ACL, pp. 3685–3694 (2020)
3.
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)
4.
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)
5.
Ding, X., Liu, B., Yu, P.S.: A holistic lexicon-based approach to opinion mining. In: WSDM (2008)
6.
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)
7.
Du, C., et al.: Capsule network with interactive attention for aspect-level sentiment classification. In: EMNLP-IJCNLP (2019)
8.
Fan, F., Feng, Y., Zhao, D.: Multi-grained attention network for aspect-level sentiment classification. In: EMNLP (2018)
9.
He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: Effective attention modeling for aspect-level sentiment classification. In: COLING, pp. 1121–1131 (2018)
10.
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)
11.
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)
12.
Hinton, G.E., Sabour, S., Frosst, N.: Matrix capsules with em routing. In: ICLR (2018)
13.
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)CrossRef
14.
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)
15.
Hu, M., Liu, B.: Mining and summarizing customer reviews. In: KDD (2004)
16.
Huang, B., Ou, Y., Carley, K.M.: Aspect level sentiment classification with attention-over-attention neural networks. In: SBP-BRiMS (2018)
17.
Jiang, Q., Chen, L., Xu, R., Ao, X., Yang, M.: A challenge dataset and effective models for aspect-based sentiment analysis. In: EMNLP (2019)
18.
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
19.
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)
20.
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)CrossRef
21.
Li, X., Bing, L., Lam, W., Shi, B.: Transformation networks for target-oriented sentiment classification. In: ACL (2018)
22.
Li, X., Bing, L., Li, P., Lam, W.: A unified model for opinion target extraction and target sentiment prediction. AAAI 33, 6714–6721 (2019)CrossRef
23.
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)
24.
Liu, B.: Sentiment analysis and opinion mining. In: Synthesis Lectures on Human Language Technologies (2012)
25.
Liu, J., Zhang, Y.: Attention modeling for targeted sentiment. In: ACL, pp. 572–577 (2017)
26.
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)
27.
Luo, L., et al.: Beyond polarity: interpretable financial sentiment analysis with hierarchical query-driven attention. In: IJCAI (2018)
28.
Luo, L., et al.: Unsupervised neural aspect extraction with sememes. In: IJCAI (2019)
29.
Ma, D., Li, S., Zhang, X., Wang, H.: Interactive attention networks for aspect-level sentiment classification. In: IJCAI (2017)
30.
Mao, Q., et al.: Aspect-based sentiment classification with attentive neural turing machines. In: IJCAI (2019)
31.
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)
32.
Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: EMNLP (2014)
33.
Phan, M.H., Ogunbona, P.O.: Modelling context and syntactical features for aspect-based sentiment analysis. In: ACL, pp. 3211–3220 (2020)
34.
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: NIPS (2017)
35.
Socher, R., Pennington, J., Huang, E.H., Ng, A.Y., Manning, C.D.: Semi-supervised recursive autoencoders for predicting sentiment distributions. In: EMNLP (2011)
36.
Tang, D., Qin, B., Feng, X., Liu, T.: Effective LSTMs for target-dependent sentiment classification. In: COLING (2016)
37.
Tang, D., Qin, B., Liu, T.: Aspect level sentiment classification with deep memory network. In: EMNLP (2016)
38.
Tang, J., et al.: Progressive self-supervised attention learning for aspect-level sentiment analysis. In: ACL, pp. 557–566 (2019)
39.
Wang, B., Lu, W.: Learning latent opinions for aspect-level sentiment classification. In: AAAI (2018)
40.
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)
41.
Wang, J., Wang, Z., Zhang, D., Yan, J.: Combining knowledge with deep convolutional neural networks for short text classification. In: IJCAI (2017)
42.
Wang, S., Mazumder, S., Liu, B., Zhou, M., Chang, Y.: Target-sensitive memory networks for aspect sentiment classification. In: ACL (2018)
43.
Wang, Y., Huang, M., Zhao, L., et al.: Attention-based LSTM for aspect-level sentiment classification. In: EMNLP (2016)
44.
Wang, Y., Sun, A., Han, J., Liu, Y., Zhu, X.: Sentiment analysis by capsules. In: The Web Conference (2018)
45.
Wang, Y., Sun, A., Huang, M., Zhu, X.: Aspect-level sentiment analysis using AS-capsules. In: The Web Conference (2019)
46.
Xue, W., Li, T.: Aspect based sentiment analysis with gated convolutional networks. In: ACL (2018)
47.
Yang, Z., Yang, D., Dyer, C., He, X., Smola, A.J., Hovy, E.H.: Hierarchical attention networks for document classification. In: HLT-NAACL (2016)
48.
Zhang, C., Li, Q., Song, D.: Aspect-based sentiment classification with aspect-specific graph convolutional networks. In: EMNLP, pp. 4560–4570 (2019)
49.
Zhang, M., Zhang, Y., Vo, D.T.: Gated neural networks for targeted sentiment analysis. In: AAAI (2016)
50.
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)
51.
Zhang, X., Li, P., Jia, W., Zhao, H.: Multi-labeled relation extraction with attentive capsule network. In: AAAI (2019)
52.
Zhao, W., Ye, J., Yang, M., Lei, Z., Zhang, S., Zhao, Z.: Investigating capsule networks with dynamic routing for text classification. In: EMNLP (2018)
Metadata
Title
Discovering Protagonist of Sentiment with Aspect Reconstructed Capsule Network
Authors
Chi Xu
Hao Feng
Guoxin Yu
Min Yang
Xiting Wang
Yan Song
Xiang Ao
Copyright Year
2021
Book
Database Systems for Advanced Applications

Print ISBN: 978-3-030-73196-0

Electronic ISBN: 978-3-030-73197-7

Copyright Year: 2021

DOI
https://doi.org/10.1007/978-3-030-73197-7_8

Premium Partner

    Image Credits