Abstract：In the identification of temporal relation between the existing events, only the local context of two events is taken into account and the relationship between the events from the perspective of discourse is neglected. To address this issue, a method to identify the temporal relation of events is proposed by combining the discourse rhetoric relation and intra-sentential dependency relation. The inter-event correlation is represented from two aspects, the shortest dependency path between events and the rhetorical relationship between the elementary discourse units of the events location. Based on this representation system, a neural network model is built to capture more effective information and improve the performance of event temporal relation identification. A series of experiments on Timebank-Dense corpus show the superiority of the proposed method.
[1] 郑 新,李培峰,朱巧明.中文事件时序关系的标注和分类方法.计算机科学, 2015, 42(7): 276-279. (ZHENG X, LI P F, ZHU Q M, et al. Annotation and Classification of Temporal Relation between Chinese Events. Computer Science, 2015, 42(7): 276-279.) [2] ALLEN J F. Maintaining Knowledge about Temporal Intervals. Co-mmunications of the ACM, 1983, 26(11): 832-843. [3] ALLEN J F. Towards a General Theory of Action and Time. Artificial Intelligence, 1984, 23(2): 123-154. [4] LASCARIDES A, ASHER N.Temporal Interpretation, Discourse Relations and Commonsense Entailment. Linguistics and Philosophy, 1993, 16(5): 437-493. [5] KEHLER A. Resolving Temporal Relations Using Tense Meaning and Discourse Interpretation // FALLER M, KAUFMANN S, PAULY M, eds. Formalizing the Dynamics of Information. Stanford, USA: SCLI Publications, 2000: 189-205. [6] CHKLOVSKI T, PANTEL P. Global Path-Based Refinement of Noisy Graphs Applied to Verb Semantics // Proc of the International Conference on Natural Language Processing. Berlin, Germany: Springer, 2005: 792-803. [7] MANI I, VERHAGEN M, WELLNER B, et al. Machine Learning of Temporal Relations // Proc of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2006: 753-760. [8] CHAMBERS N, WANG S, JURAFSKY D. Classifying Temporal Relations between Events // Proc of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions. Stroudsburg, USA: ACL, 2007: 173-176. [9] FELLBAUN C, MILLER G. WordNet: An Electronic Lexical Database. Cambridge, USA: The MIT Press, 1998. [10] CHKLOVSKI T, PANTEL P. VERBOCEAN: Mining the Web for Fine-Grained Semantic Verb Relations // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2004: 33-40. [11] CHENG Y C, ASAHARA M, MATSUMOTO Y. NAIST. Japan: Temporal Relation Identification Using Dependency Parsed Tree // Proc of the 4th International Workshop on Semantic Evaluations. Stroudsburg, USA: ACL, 2007: 245-248. [12] BETHARD S, MARTIN J H. CU-TMP: Temporal Relation Classification Using Syntactic and Semantic Features // Proc of the 4th International Workshop on Semantic Evaluations. Stroudsburg, USA: ACL, 2007: 129-132. [13] PUSTEJOVSKY J, VERHAGEN M, XUE N W, et al. TempEval2: Evaluating Events, Time Expressions and Temporal Relations[J/OL]. [2019-08-22]. http://www.timeml.org/tempeval2/tempeval2-proposal.pdf. [14] KOLOMIYETS O, BETHARD S, MOENS M F. Extracting Narrative Timelines as Temporal Dependency Structures // Proc of the 50th Annual Meeting of the Association for Computational Linguistics(Long Papers). Stroudsburg, USA: ACL, 2012, I: 88-97. [15] CHENG F, MIYAO Y. Classifying Temporal Relations by Bidirectional LSTM over Dependency Paths // Proc of the 55th Annual Meeting of the Association for Computational Linguistics(Short Papers) . Stroudsburg, USA: ACL, 2017. DOI: 10.18653/v1/P17-2001. [16] CHOUBEY P K, HUANG R H. A Sequential Model for Classifying Temporal Relations between Intra-sentence Events // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2017: 1796-1802. [17] YAN X, MOU L l, LI G, et al. Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths // Proc of the Conference on Empirical Methods in Natural Language Processing. Berlin, Germany: Springer, 2015: 1785-1794. [18] NING Q, WU H, PENG H R, et al. Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource // Proc of the Conference of the North American Chapter of the Association for Computational Linguistics(Human Language Technologies). Strouds-burg, USA: ACL, 2019: 841-851. [19] NING Q, FENG Z L, WU H, et al. Joint Reasoning for Temporal and Causal Relations // Proc of the 56th Annual Meeting of the Association for Computational Linguistics(Long Papers). Stroudsburg, USA: ACL, 2018, I: 2278-2288. [20] MANN W C, THOMPSON S A. Rhetorical Structure Theory: Toward a Functional Theory of Text Organization. Text(Interdisciplinary Journal for the Study of Discourse), 1988, 8(3): 243-281. [21] ZHANG L Y, SUN C, TAN X, et al. RST Discourse Parsing with Tree-Structured Neural Networks // Proc of the China Workshop on Machine Translation. Berlin, Germany: Springer, 2018: 15-26. [22] CHAMBERS N, CASSIDY T, MCDOWELL B, et al. Dense Event Ordering with a Multi-pass Architecture. Transactions of the Association for Computational Linguistics, 2014, 2: 273-284. [23] MIRZA P, TONELLI S. On the Contribution of Word Embeddings to Temporal Relation Classification // Proc of the 26th International Conference on Computational Linguistics. Berlin, Germany: Sprin-ger, 2016: 2818-2828.
2019, Vol. 32 
