Abstract
Emotion-Cause Pair Extraction (ECPE) aims to extract all emotion clauses and their corresponding cause clauses from a document. Existing approaches tackle this task through multi-task learning (MTL) framework in which the two subtasks provide indicative clues for ECPE. However, the previous MTL framework considers only one round of multi-task reasoning and ignores the reverse feedbacks from ECPE to the subtasks. Besides, its multi-task reasoning only relies on semantics-level interactions, which cannot capture the explicit dependencies, and both the encoder sharing and multi-task hidden states concatenations can hardly capture the causalities. To solve these issues, we first put forward a new MTL framework based on Co-evolving Reasoning. It (1) models the bidirectional feedbacks between ECPE and its subtasks; (2) allows the three tasks to evolve together and prompt each other recurrently; (3) integrates prediction-level interactions to capture explicit dependencies. Then we propose a novel multi-task relational graph (MRG) to sufficiently exploit the causal relations. Finally, we propose a Co-evolving Graph Reasoning Network (CGR-Net) that implements our MTL framework and conducts Co-evolving Reasoning on MRG. Experimental results show that our model achieves new state-of-the-art performance, and further analysis confirms the advantages of our method.
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
References
Bao, Y., Ma, Q., Wei, L., Zhou, W., Hu, S.: Multi-granularity semantic aware graph model for reducing position bias in emotion cause pair extraction. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 1203–1213. Association for Computational Linguistics, Dublin, Ireland (May 2022)
Chen, X., Li, Q., Wang, J.: A unified sequence labeling model for emotion cause pair extraction. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 208–218. International Committee on Computational Linguistics, Barcelona, Spain (Online) (Dec 2020)
Chen, Y., Hou, W., Li, S., Wu, C., Zhang, X.: End-to-end emotion-cause pair extraction with graph convolutional network. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 198–207. International Committee on Computational Linguistics, Barcelona, Spain (Online) (Dec 2020)
Chen, Y., Lee, S.Y.M., Li, S., Huang, C.R.: Emotion cause detection with linguistic constructions. In: Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), pp. 179–187. Coling 2010 Organizing Committee, Beijing, China (Aug 2010)
Cheng, Z., Jiang, Z., Yin, Y., Li, N., Gu, Q.: A unified target-oriented sequence-to-sequence model for emotion-cause pair extraction. IEEE/ACM Trans. Audio Speech Lang. Process. 29, 2779–2791 (2021)
Cheng, Z., Jiang, Z., Yin, Y., Yu, H., Gu, Q.: A symmetric local search network for emotion-cause pair extraction. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 139–149. International Committee on Computational Linguistics, Barcelona, Spain (Online) (Dec 2020)
De Beaugrande, R., Dressler, W.U.: Introduction to Text Linguistics. Longmans, London (1981)
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: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171–4186. Association for Computational Linguistics, Minneapolis, Minnesota (2019)
Ding, Z., He, H., Zhang, M., Xia, R.: From independent prediction to reordered prediction: integrating relative position and global label information to emotion cause identification. In: AAAI, pp. 6343–6350. AAAI Press (2019)
Ding, Z., Xia, R., Yu, J.: ECPE-2D: emotion-cause pair extraction based on joint two-dimensional representation, interaction and prediction. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3161–3170. Association for Computational Linguistics (Online) (Jul 2020)
Ding, Z., Xia, R., Yu, J.: End-to-end emotion-cause pair extraction based on sliding window multi-label learning. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3574–3583. Association for Computational Linguistics (Online) (Nov 2020)
Fan, C., Yuan, C., Du, J., Gui, L., Yang, M., Xu, R.: Transition-based directed graph construction for emotion-cause pair extraction. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3707–3717. Association for Computational Linguistics (Online) (Jul 2020)
Fan, C., Yuan, C., Gui, L., Zhang, Y., Xu, R.: Multi-task sequence tagging for emotion-cause pair extraction via tag distribution refinement. IEEE/ACM Trans. Audio Speech Lang. Process. 29, 2339–2350 (2021)
Ghazi, D., Inkpen, D., Szpakowicz, S.: Detecting emotion stimuli in emotion-bearing sentences. In: Gelbukh, A. (ed.) CICLing 2015. LNCS, vol. 9042, pp. 152–165. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-18117-2_12
Gui, L., Hu, J., He, Y., Xu, R., Lu, Q., Du, J.: A question answering approach for emotion cause extraction. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1593–1602. Association for Computational Linguistics, Copenhagen, Denmark (Sep 2017)
Gui, L., Wu, D., Xu, R., Lu, Q., Zhou, Y.: Event-driven emotion cause extraction with corpus construction. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1639–1649. Association for Computational Linguistics, Austin, Texas (Nov 2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Lee, S.Y.M., Chen, Y., Huang, C.R.: A text-driven rule-based system for emotion cause detection. In: Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text, pp. 45–53. Association for Computational Linguistics, Los Angeles, CA (Jun 2010)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6–9 May 2019. OpenReview.net (2019)
Neviarouskaya, A., Aono, M.: Extracting causes of emotions from text. In: Proceedings of the Sixth International Joint Conference on Natural Language Processing, pp. 932–936. Asian Federation of Natural Language Processing, Nagoya, Japan (Oct 2013)
Russo, I., Caselli, T., Rubino, F., Boldrini, E., Martínez-Barco, P.: EMOCause: an easy-adaptable approach to extract emotion cause contexts. In: Proceedings of the 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (WASSA 2011), pp. 153–160. Association for Computational Linguistics, Portland, Oregon (Jun 2011)
Schlichtkrull, M.S., Kipf, T.N., Bloem, P., van den Berg, R., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. In: ESWC, pp. 593–607 (2018)
Wei, P., Zhao, J., Mao, W.: Effective inter-clause modeling for end-to-end emotion-cause pair extraction. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3171–3181. Association for Computational Linguistics (Online) (Jul 2020)
Wolf, T., et al.: Transformers: State-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38–45. Association for Computational Linguistics (Online) (2020)
Wu, S., Chen, F., Wu, F., Huang, Y., Li, X.: A multi-task learning neural network for emotion-cause pair extraction. In: ECAI. Frontiers in Artificial Intelligence and Applications, vol. 325, pp. 2212–2219. IOS Press (2020)
Xia, R., Ding, Z.: Emotion-cause pair extraction: A new task to emotion analysis in texts. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1003–1012. Association for Computational Linguistics, Florence, Italy (Jul 2019)
Xing, B., et al.: Earlier attention? aspect-aware lstm for aspect-based sentiment analysis. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, pp. 5313–5319. International Joint Conferences on Artificial Intelligence Organization (July 2019)
Xing, B., Tsang, I.: Co-guiding net: achieving mutual guidances between multiple intent detection and slot filling via heterogeneous semantics-label graphs. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 159–169. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Dec 2022)
Xing, B., Tsang, I.: DARER: dual-task temporal relational recurrent reasoning network for joint dialog sentiment classification and act recognition. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 3611–3621. Association for Computational Linguistics, Dublin, Ireland (May 2022)
Xing, B., Tsang, I.: Dignet: digging clues from local-global interactive graph for aspect-level sentiment classification. arXiv preprint arXiv:2201.00989 (2022)
Xing, B., Tsang, I.: Group is better than individual: exploiting label topologies and label relations for joint multiple intent detection and slot filling. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 3964–3975. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Dec 2022)
Xing, B., Tsang, I.: Neural subgraph explorer: reducing noisy information via target-oriented syntax graph pruning. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, pp. 4425–4431. International Joint Conferences on Artificial Intelligence Organization (July 2022), main Track
Xing, B., Tsang, I.: Relational temporal graph reasoning for dual-task dialogue language understanding. arXiv preprint arXiv:2306.09114 (2023)
Xing, B., Tsang, I.W.: Out of context: a new clue for context modeling of aspect-based sentiment analysis. J. Artifi. Intell. Res. 74, 627–659 (2022)
Xing, B., Tsang, I.W.: Understand me, if you refer to aspect knowledge: Knowledge-aware gated recurrent memory network. IEEE Trans. Emerging Topics Comput. Intell. 6(5), 1092–1102 (2022)
Yan, H., Gui, L., Pergola, G., He, Y.: Position bias mitigation: a knowledge-aware graph model for emotion cause extraction. In: 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), pp. 3364–3375. Association for Computational Linguistics (Online) (Aug 2021)
Yang, C., Zhang, Z., Ding, J., Zheng, W., Jing, Z., Li, Y.: A multi-granularity network for emotion-cause pair extraction via matrix capsule. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 4625–4629 (2022)
Yuan, C., Fan, C., Bao, J., Xu, R.: Emotion-cause pair extraction as sequence labeling based on a novel tagging scheme. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3568–3573. Association for Computational Linguistics, Online (Nov 2020)
Acknowledgments
This work was supported by Australian Research Council Grant DP200101328. Authors were also supported by A\(^*\)STAR Centre for Frontier AI Research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xing, B., Tsang, I.W. (2023). Co-Evolving Graph Reasoning Network for Emotion-Cause Pair Extraction. In: Koutra, D., Plant, C., Gomez Rodriguez, M., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Research Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14169. Springer, Cham. https://doi.org/10.1007/978-3-031-43412-9_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-43412-9_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43411-2
Online ISBN: 978-3-031-43412-9
eBook Packages: Computer ScienceComputer Science (R0)