Exploiting Document Structures and Cluster Consistencies for Event Coreference Resolution

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pages 4840–4850 August 1–6, 2021. ©2021 Association for Computational Linguistics 4840 Exploiting Document Structures and Cluster Consistencies for Event Coreference Resolution Hieu Minh Tran1, Duy Phung1 and Thien Huu Nguyen2 1 VinAI Research, Vietnam 2 Department of Computer and Information Science, University of Oregon, Eugene, OR 97403, USA {v.hieutm4,v.duypv1}@vinai.io, thien@cs.uoregon.edu Abstract We study the problem of event coreference resolution (ECR) that seeks to group coref- erent event mentions into the same clusters. Deep learning methods have recently been ap- plied for this task to deliver state-of-the-art performance. However, existing deep learn- ing models for ECR are limited in that they cannot exploit important interactions between relevant objects for ECR, e.g., context words and entity mentions, to support the encoding of document-level context. In addition, con- sistency constraints between golden and pre- dicted clusters of event mentions have not been considered to improve representation learning in prior deep learning models for ECR. This work addresses such limitations by introduc- ing a novel deep learning model for ECR. At the core of our model are document structures to explicitly capture relevant objects for ECR. Our document structures introduce diverse knowledge sources (discourse, syntax, seman- tics) to compute edges/interactions between structure nodes for document-level representa- tion learning. We also present novel regular- ization techniques based on consistencies of golden and predicted clusters for event men- tions in documents. Extensive experiments show that our model achieve state-of-the-art performance on two benchmark datasets. 1 Introduction Event coreference resolution (ECR) is the task of clustering event mentions (i.e., trigger words that evoke an event) in a document such that each clus- ter represents a unique real world event. For ex- ample, the three event mentions in Figure 1, i.e., “refuse to sign, “raised objections”, and “doesn’t sign”, should be grouped into the same cluster to indicate their coreference to the same event. A common component in prior ECR models in- volves a binary classifier that receives a pair of event mentions and predict their coreference (Chen et al., 2009; Lu et al., 2016; Lu and Ng, 2017). To this end, an important step in ECR models is to transform event mention pairs into representa- tion vectors to encode discriminative features for coreference prediction. Early work on ECR has achieved feature representation via feature engi- neering where multiple features are hand-designed for input event mention pairs (Lu and Ng, 2017). A major problem with feature engineering is the spar- sity of the features that limits the generalization to unseen data. Representation learning in deep learning models has recently been introduced to address this issue, leading to more robust methods with better performance for ECR (Nguyen et al., 2016; Choubey and Huang, 2018; Huang et al., 2019; Barhom et al., 2019). As such, there are at least two limitations in existing deep learning mod- els for ECR that will be addressed in this work to improve …

Content truncated to 500 words