A Sequential Model for Classifying Temporal Relations between Intra-Sentence Events

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1796–1802 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics A Sequential Model for Classifying Temporal Relations between Intra-Sentence Events Prafulla Kumar Choubey and Ruihong Huang Department of Computer Science and Engineering Texas A&M University (prafulla.choubey, huangrh)@tamu.edu Abstract We present a sequential model for tem- poral relation classification between intra- sentence events. The key observation is that the overall syntactic structure and compositional meanings of the multi-word context between events are important for distinguishing among fine-grained tempo- ral relations. Specifically, our approach first extracts a sequence of context words that indicates the temporal relation be- tween two events, which well align with the dependency path between two event mentions. The context word sequence, together with a parts-of-speech tag se- quence and a dependency relation se- quence that are generated corresponding to the word sequence, are then provided as input to bidirectional recurrent neural network (LSTM) models. The neural nets learn compositional syntactic and seman- tic representations of contexts surrounding the two events and predict the temporal relation between them. Evaluation of the proposed approach on TimeBank corpus shows that sequential modeling is capa- ble of accurately recognizing temporal re- lations between events, which outperforms a neural net model using various discrete features as input that imitates previous fea- ture based models. 1 Introduction Identifying temporal relations between events is crucial to constructing events timeline. It has di- rect application in tasks such as question answer- ing, event timeline generation and document sum- marization. Bush said he saw little reason to be optimistic about a settlement of the dispute, which stems from Iraq’s invasion of oil-wealthy Kuwait and its subsequent military buildup on the border of Saudi Arabia. Relations: (dispute after rel1 invasion, invasion ibefore rel2 buildup, dispute after rel3 buildup) Figure 1: Example sentence to illustrate the tem- poral context for event pairs. Previous works studied this task as the classifi- cation problem based on discrete features defined over lexico-syntactic, semantic and discourse fea- tures. However, these features are often derived from local contexts of two events and are only ca- pable of capturing direct evidences indicating the temporal relation. Specifically, when two events are distantly located or are separated by other events in between, feature based approaches often fail to utilize compositional evidences, which are hard to encode using discrete features. Consider the example sentence in Fig- ure 1. Here, the first two temporal re- 1796 lations, dispute after rel1 invasion and invation ibefore rel2 buildup, involve events that are close by and discrete features, such as dependency relations and bag-of-words extracted from local contexts of two events, might be sufficient to correctly detect their relations. However, for the temporal relation dispute after rel3 buildup, the context between the two events is long, complex and involves another event (invasion) as well, which makes it challenging for any individual feature or feature combinations to capture the temporal relation. We propose that the overall syntactic structure of …

Content truncated to 500 words