Abstract
Temporal relation classification, an important branch of relation extraction, aims to identify the time sequence among events. Currently, Shortest Dependency Path (SDP) is widely used in various kinds of neural network models to capture the crucial information from sentences. However, while eliminating irrelevant words in event sentences, SDP will miss some useful information, e.g., time expressions. To address the above issue, we propose a neural network method incorporating the temporal cues to AC-GCN (Augmented Contextualized Graph Convolutional Network) to classify temporal relations. Firstly, we introduce the semantic role labeling and heuristic rules to extract the time expressions corresponding to event triggers and other words in SDPs, respectively. Then, the SDP with time expression (i.e., T-SDP) is encoded by a Bi-LSTM with the parameter sharing mechanism and fed into GCN to classify temporal relations. The experimental results on TimeBank-Dense show that our proposed model outperforms all baselines significantly.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
We use Allennlp [18] to extract the time expression, i.e., the role “ARGM-TMP” in SRL.
References
Jia, Z., Abujabal, A., Saha Roy, R., Strotgen, J., Weikum, G.: TEQUILA: temporal question answering over knowledge bases. Proc. ACM 2018, 1807–1810 (2018)
Sakaguchi, T., Kurohashi, S.: Timeline generation based on a two-stage event-time anchoring model. In: Gelbukh, A. (ed.) CICLing 2017. LNCS, vol. 10762, pp. 535–545. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-77116-8_40
Xu, Y., Mou, L., Li, G., et al.: Classifying relations via long short term memory networks along shortest dependency path. In: Proceedings of EMNLP 2015, pp. 1785–1794 (2015)
Cheng, F., Miyao, Y.: Classifying temporal relations by bidirectional LSTM over dependency paths. In: Proceedings of ACL 2017, pp. 1–6 (2017)
Mani, I., Verhagen, M., Wellner, B., et al.: Machine learning of temporal relations. In: Proceedings of ACL 2006, pp. 753–760 (2006)
Chambers, N., Wang, S., Jurafsky, D.: Classifying temporal relations between events. In: Proceeding of ACL 2007, pp. 173–176 (2007)
Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38, 39–41 (1995)
Chambers, N., Jurafsky, D.: Jointly combining implicit constraints improves temporal ordering. In: Proceedings of EMNLP 2008, pp. 698–706 (2008)
Do, Q., Lu, W., Roth, D.: Joint inference for event timeline construction. In: Proceedings of EMNLP 2012, pp. 677–687 (2012)
Ng, J., et al.: Exploiting discourse analysis for article-wide temporal classification. In: Proceedings of EMNLP 2013, pp. 12–23 (2013)
Li, P., Zhu, Q., Zhou, G., Wang, H.: Global inference to Chinese temporal relation extraction. In: Proceedings of COLING 2016, pp. 1451–1460 (2016)
Choubey, P. K., Huang, R.: A sequential model for classifying temporal relations between intra-sentence events. In: Proceedings of EMNLP 2017, pp. 1796–1802 (2017)
Yao, W., Huang, R.: Temporal event knowledge acquisition via identifying narratives. In: Proceedings of ACL 2018, pp. 537–547 (2018)
Meng, Y.L., Rumshisky, A.: Context-aware neural model for temporal information extraction. In: Proceedings of ACL 2018, pp. 527–536 (2018)
Dai, Q., Kong, F., Dai, Q.: Event temporal relation classification based on graph convolutional networks. In: Tang, J., Kan, M.-Y., Zhao, D., Li, S., Zan, H. (eds.) NLPCC 2019. LNCS (LNAI), vol. 11839, pp. 393–403. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32236-6_35
Zhang, Y., Li, P., Zhou, G.: Classifying temporal relation between events by deep BiLSTM. In: Proceedings of IALP 2018, pp. 267–272 (2018)
Lin, C., Miller, T., Dligach, D., Bethard, S., Savova, G.: Representations of time expressions for temporal relation extraction with convolutional neural networks. In: Proceedings of BioNLP 2017, pp. 322–327 (2017)
Gardner, M., Grus, J., Neumann, M.: AllenNLP: a deep semantic natural language processing platform. In: Proceedings of the ACL Workshop for Natural Language Processing Open Source Software, pp. 1–6 (2017)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Zhang, Y., Qi, P., Manning, C.D.: Graph convolution over pruned dependency trees improves relation extraction. In: Proceedings of EMNLP 2018, pp. 2205–2215 (2018)
Mirza, P., Tonelli, S.: On the contribution of word embeddings to temporal relation classification. In: Proceedings of COLING 2016, pp. 2818–2828 (2016)
Acknowledgments
The authors would like to thank the three anonymous reviewers for their comments on this paper. This research was supported by the National Natural Science Foundation of China (No. 61836007, 61772354 and 61773276.), and the Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, X., Li, P., Zhu, Q., Kong, F. (2020). Incorporating Temporal Cues and AC-GCN to Improve Temporal Relation Classification. In: Zhu, X., Zhang, M., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2020. Lecture Notes in Computer Science(), vol 12430. Springer, Cham. https://doi.org/10.1007/978-3-030-60450-9_46
Download citation
DOI: https://doi.org/10.1007/978-3-030-60450-9_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60449-3
Online ISBN: 978-3-030-60450-9
eBook Packages: Computer ScienceComputer Science (R0)
