Abstract
Aspect Sentiment Triplet Extraction (ASTE) is an Aspect-Based Sentiment Analysis subtask (ABSA). It aims to extract aspect-opinion pairs from a sentence and identify the sentiment polarity associated with them. For instance, given the sentence “Large rooms and great breakfast”, ASTE outputs the triplet T = {(rooms, large, positive), (breakfast, great, positive)}. Although several approaches to ASBA have recently been proposed, those for Portuguese have been mostly limited to extracting only aspects without addressing ASTE tasks. This work aims to develop a framework based on Deep Learning to perform the Aspect Sentiment Triplet Extraction task in Portuguese. The framework uses BERT as a context-awareness sentence encoder, multiple parallel non-linear layers to get aspect and opinion representations, and a Graph Attention layer along with a Biaffine scorer to determine the sentiment dependency between each aspect-opinion pair. The comparison results show that our proposed framework significantly outperforms the baselines in Portuguese and is competitive with its counterparts in English.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Source code available at https://github.com/josemelendezb/bote.
- 2.
We obtain the syntactic dependency graph of a sentence using Spacy parser.
- 3.
Datasets are available by Zhang et al. at https://github.com/GeneZC/OTE-MTL.
- 4.
- 5.
References
Aires, J.P., Padilha, C., Quevedo, C., Meneguzzi, F.: A deep learning approach to classify aspect-level sentiment using small datasets. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2018)
Balage Filho, P.P.: Aspect extraction in sentiment analysis for Portuguese language. Ph.D. thesis, Universidade de Sao Paulo (2017)
Bekoulis, G., Deleu, J., Demeester, T., Develder, C.: Joint entity recognition and relation extraction as a multi-head selection problem. Expert Syst. Appl. 114, 34–45 (2018)
Cardoso, B., Pereira, D.: Evaluating an aspect extraction method for opinion mining in the Portuguese language. In: Anais do VIII Symposium on Knowledge Discovery, Mining and Learning, pp. 137–144. SBC (2020)
Cui, Z., Maojie, Z.: Aspect level sentiment classification based on double attention mechanism. In: Proceedings of the 2019 2nd International Conference on E-Business, Information Management and Computer Science. EBIMCS 2019. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3377817.3377834
Demšar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7(1), 1–30 (2006). http://jmlr.org/papers/v7/demsar06a.html
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: 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, Minneapolis, Minnesota, pp. 4171–4186. Association for Computational Linguistics, June 2019. https://doi.org/10.18653/v1/N19-1423
Dietterich, T.G.: Approximate statistical tests for comparing supervised classification learning algorithms. Neural Comput. 10(7), 1895–1923 (1998)
Dozat, T., Manning, C.D.: Deep biaffine attention for neural dependency parsing. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24–26 April 2017, Conference Track Proceedings. OpenReview.net (2017). https://openreview.net/forum?id=Hk95PK9le
Fan, Z., Wu, Z., Dai, X.Y., Huang, S., Chen, J.: Target-oriented opinion words extraction with target-fused neural sequence labeling. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, Minneapolis, Minnesota, pp. 2509–2518. Association for Computational Linguistics, June 2019. https://doi.org/10.18653/v1/N19-1259
Farias, D.S., Matsuno, I.P., Marcacini, R.M., Rezende, S.O.: Opinion-meter: a framework for aspect-based sentiment analysis. In: Proceedings of the 22nd Brazilian Symposium on Multimedia and the Web, pp. 351–354. ACM (2016). https://doi.org/10.1145/2976796.2988214
Freitas, C., Motta, E., Milidiú, R., César, J.: Vampiro que brilha... rá! desafios na anotaçao de opiniao em um corpus de resenhas de livros. Encontro de Linguística de Corpus 11, 22 (2012)
Freitas, L.A., Vieira, R.: Exploring resources for sentiment analysis in Portuguese language. In: Brazilian Conference on Intelligent Systems, pp. 152–156. IEEE (2015)
García, S., Herrera, F.: An extension on “statistical comparisons of classifiers over multiple data sets” for all pairwise comparisons. J. Mach. Learn. Res. 9(89), 2677–2694 (2008). http://jmlr.org/papers/v9/garcia08a.html
Goldberg, Y.: Assessing Bert’s syntactic abilities. arXiv (2019). http://arxiv.org/abs/1901.05287
Han, H., Li, X., Zhi, S., Wang, H.: Multi-attention network for aspect sentiment analysis. In: Proceedings of the 2019 8th International Conference on Software and Computer Applications, ICSCA 2019, pp. 22–26. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3316615.3316673
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: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp. 504–515. Association for Computational Linguistics, July 2019
Huang, B., Carley, K.: Syntax-aware aspect level sentiment classification with graph attention networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, Hong Kong, China, pp. 5469–5477. Association for Computational Linguistics, November 2019. https://doi.org/10.18653/v1/D19-1549
Li, Y., Li, Z., Zhang, M., Wang, R., Li, S., Si, L.: Self-attentive biaffine dependency parsing. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI, pp. 5067–5073. ijcai.org (2019). https://doi.org/10.24963/ijcai.2019/704
Li, Z., et al.: Dependency or span, end-to-end uniform semantic role labeling. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 6730–6737 (2019). https://doi.org/10.1609/aaai.v33i01.33016730
Liu, B.: Sentiment analysis and opinion mining. Synthesis Lect. Hum. Lang. Technol. 5(1), 1–167 (2012)
Lu, Z., Du, P., Nie, J.-Y., et al.: VGCN-BERT: augmenting BERT with graph embedding for text classification. In: Jose, J.M. (ed.) ECIR 2020. LNCS, vol. 12035, pp. 369–382. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-45439-5_25
Machado, M.T., Pardo, T.A.S., Ruiz, E.E.S.: Analysis of unsupervised aspect term identification methods for Portuguese reviews. In: Anais do XIV Encontro Nacional de Inteligncia Artificial e Computacional (ENIAC), SBC, pp. 239–249 (2017)
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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 05, pp. 8600–8607 (2020). https://doi.org/10.1609/aaai.v34i05.6383
Pereira, D.A.: A survey of sentiment analysis in the Portuguese language. Artif. Intell. Rev. 54(2), 1087–1115 (2020). https://doi.org/10.1007/s10462-020-09870-1
Saias, J., Mourão, M., Oliveira, E.: Detailing sentiment analysis to consider entity aspects: an approach for Portuguese short texts. Trans. Mach. Learn. Artif. Intell. 6, 26–35 (2018)
Souza, F., Nogueira, R., Lotufo, R.: BERTimbau: pretrained BERT models for Brazilian Portuguese. In: Cerri, R., Prati, R.C. (eds.) BRACIS 2020. LNCS (LNAI), vol. 12319, pp. 403–417. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61377-8_28
Vargas, F.A., Pardo, T.A.S.: Hierarchical clustering of aspects for opinion mining: a corpus study. In: Finatto, M.J.B., Rebechi, R.R., Sarmento, S., Bocorny, A.E.P. (eds.) Linguística de Corpus: Perspectivas, pp. 69–91 (2018)
Wang, W., Pan, S.J., Dahlmeier, D., Xiao, X.: Coupled multi-layer attentions for co-extraction of aspect and opinion terms. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)
Wu, Z., Ying, C., Zhao, F., Fan, Z., Dai, X., Xia, R.: Grid tagging scheme for aspect-oriented fine-grained opinion extraction. In: Findings of the Association for Computational Linguistics, pp. 2576–2585. Association for Computational Linguistics, November 2020. https://doi.org/10.18653/v1/2020.findings-emnlp.234
Xu, L., Bing, L., Lu, W., Huang, F.: Aspect sentiment classification with aspect-specific opinion spans. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3561–3567. Association for Computational Linguistics, November 2020. https://doi.org/10.18653/v1/2020.emnlp-main.288
Zhang, C., Li, Q., Song, D., Wang, B.: A multi-task learning framework for opinion triplet extraction. In: Findings of the Association for Computational Linguistics, pp. 819–828. Association for Computational Linguistics, November 2020. https://doi.org/10.18653/v1/2020.findings-emnlp.72
Acknowledgments
This work was supported by CAPES and Ministerio de Ciencia from Colombia.
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
Barros, J.M., De Bona, G. (2021). A Deep Learning Approach for Aspect Sentiment Triplet Extraction in Portuguese. In: Britto, A., Valdivia Delgado, K. (eds) Intelligent Systems. BRACIS 2021. Lecture Notes in Computer Science(), vol 13074. Springer, Cham. https://doi.org/10.1007/978-3-030-91699-2_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-91699-2_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91698-5
Online ISBN: 978-3-030-91699-2
eBook Packages: Computer ScienceComputer Science (R0)