Abstract
Event temporal relation extraction aims to automatically identify the temporal order between a pair of events, which is an essential step towards event-oriented natural language understanding and generation. For this task, impressive improvements have been made in neural network-based approaches. However, they typically treat it as a supervised classification task and inevitably suffer from under-annotated data and label imbalance problems. In this paper, we propose a new retrieval-enhanced event temporal relation extraction model, called PRetrieval, which addresses these issues by making full use of the golden relation labels to learn potential temporal knowledge in a pre-trained language model and to perform prompt tuning. Specifically, PRetrieval first generates an initial prediction using the prompt-based input and constructs a datastore using this prediction result and the associated golden labels, which has the advantage of not relying on any external datasets or additional knowledge enhancement. PRetrieval then retrieves examples with outputs similar to the preliminary prediction results as the new prompt to improve the model’s relation extraction ability under few-shot settings. In addition, it also retrieves examples with similar input to further enhance the model performance. The experimental results on two benchmark datasets (i.e., MATRES and TB-Dense) show that our proposed approach significantly outperforms the state-of-the-art methods.
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
References
Ballesteros, M., et al.: Severing the edge between before and after: neural architectures for temporal ordering of events. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 5412–5417 (2020)
Bethard, S., Martin, J.H.: CU-TMP: temporal relation classification using syntactic and semantic features. In: Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval), pp. 129–132 (2007)
Cao, P., Zuo, X., Chen, Y., Liu, K., Zhao, J., Bi, W.: Uncertainty-aware self-training for semi-supervised event temporal relation extraction. In: Proceedings of the 30th ACM International Conference on Information & Knowledge Management (CIKM), pp. 2900–2904 (2021)
Cassidy, T., McDowell, B., Chambers, N., Bethard, S.: An annotation framework for dense event ordering. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 501–506 (2014)
Chambers, N., Cassidy, T., McDowell, B., Bethard, S.: Dense event ordering with a multi-pass architecture. Trans. Assoc. Comput. Linguist. (TACL) 2, 273–284 (2014)
Chen, X., et al.: Relation extraction as open-book examination: retrieval-enhanced prompt tuning. In: Proceedings of the 45th International ACM Conference on Research and Development in Information Retrieval (SIGIR), pp. 2443–2448 (2022)
Cheng, F., Asahara, M., Kobayashi, I., Kurohashi, S.: Dynamically updating event representations for temporal relation classification with multi-category learning. In: Findings of the Association for Computational Linguistics (EMNLP), pp. 1352–1357 (2020)
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 (NAACL), pp. 4171–4186 (2019)
Han, R., Ning, Q., Peng, N.: Joint event and temporal relation extraction with shared representations and structured prediction. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 434–444 (2019)
Han, R., Ren, X., Peng, N.: ECONET: effective continual pretraining of language models for event temporal reasoning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 5367–5380 (2021)
Han, R., Zhou, Y., Peng, N.: Domain knowledge empowered structured neural net for end-to-end event temporal relation extraction. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 5717–5729 (2020)
Hwang, E., Lee, J.Y., Yang, T., Patel, D., Zhang, D., McCallum, A.: Event-event relation extraction using probabilistic box embedding. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 235–244 (2022)
Kassner, N., Schütze, H.: BERT-kNN: adding a KNN search component to pretrained language models for better QA. In: Findings of the Association for Computational Linguistics (EMNLP), pp. 3424–3430 (2020)
Khandelwal, U., Levy, O., Jurafsky, D., Zettlemoyer, L., Lewis, M.: Generalization through memorization: nearest neighbor language models. In: Proceedings of International Conference on Learning Representations (ICLR) (2020)
Khashabi, D., Khot, T., Sabharwal, A., Roth, D.: Question answering as global reasoning over semantic abstractions. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 32 (2018)
Laokulrat, N., Miwa, M., Tsuruoka, Y., Chikayama, T.: UTTime: temporal relation classification using deep syntactic features. In: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval), pp. 88–92 (2013)
Leeuwenberg, A., Moens, M.F.: Temporal information extraction by predicting relative time-lines. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1237–1246 (2018)
Li, L., Song, D., Ma, R., Qiu, X., Huang, X.: KNN-BERT: fine-tuning pre-trained models with KNN classifier. arXiv preprint arXiv:2110.02523 (2021)
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Ng, J.P., Chen, Y., Kan, M.Y., Li, Z.: Exploiting timelines to enhance multi-document summarization. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 923–933 (2014)
Ning, Q., Subramanian, S., Roth, D.: An improved neural baseline for temporal relation extraction. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 6203–6209 (2019)
Ning, Q., Wu, H., Han, R., Peng, N., Gardner, M., Roth, D.: TORQUE: a reading comprehension dataset of temporal ordering questions. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1158–1172 (2020)
Ning, Q., Wu, H., Roth, D.: A multi-axis annotation scheme for event temporal relations. arXiv preprint arXiv:1804.07828 (2018)
Pasupat, P., Zhang, Y., Guu, K.: Controllable semantic parsing via retrieval augmentation. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 7683–7698 (2021)
Rubin, O., Herzig, J., Berant, J.: Learning to retrieve prompts for in-context learning. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), pp. 2655–2671 (2022)
Tan, X., Pergola, G., He, Y.: Extracting event temporal relations via hyperbolic geometry. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 8065–8077 (2021)
Verhagen, M., Pustejovsky, J.: Temporal processing with the TARSQI toolkit. In: Proceedings of the 22nd International Conference on Computational Linguistics (COLING), pp. 189–192 (2008)
Wang, H., Chen, M., Zhang, H., Roth, D.: Joint constrained learning for event-event relation extraction. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 696–706 (2020)
Wang, S., et al.: Training data is more valuable than you think: a simple and effective method by retrieving from training data. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 3170–3179 (2022)
Wen, H., Ji, H.: Utilizing relative event time to enhance event-event temporal relation extraction. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 10431–10437 (2021)
Zhang, S., Ning, Q., Huang, L.: Extracting temporal event relation with syntax-guided graph transformer. In: Findings of the Association for Computational Linguistics (NAACL), pp. 379–390 (2022)
Zhang, X., Zang, L., Cheng, P., Wang, Y., Hu, S.: A knowledge/data enhanced method for joint event and temporal relation extraction. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6362–6366 (2022)
Acknowledgements
This work was supported by the National Social Science Fund of China under Grant No. 20BTQ068.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Luo, R., Hu, P. (2024). Retrieval-Enhanced Event Temporal Relation Extraction by Prompt Tuning. In: Song, X., Feng, R., Chen, Y., Li, J., Min, G. (eds) Web and Big Data. APWeb-WAIM 2023. Lecture Notes in Computer Science, vol 14334. Springer, Singapore. https://doi.org/10.1007/978-981-97-2421-5_2
Download citation
DOI: https://doi.org/10.1007/978-981-97-2421-5_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2420-8
Online ISBN: 978-981-97-2421-5
eBook Packages: Computer ScienceComputer Science (R0)