Abstract

Event coreference resolution aims to classify all event mentions that refer to the same real-world event into the same group, which is necessary to information aggregation and many downstream applications. To resolve event coreference, existing methods usually calculate the similarities between event mentions and between specific kinds of event arguments. However, they fail to accurately identify paraphrase relations between events and may suffer from error propagation while extracting event components (i.e., event mentions and their arguments). Therefore, we propose a new model based on Event-specific Paraphrases and Argument-aware Semantic Embeddings, thus called EPASE, for event coreference resolution. EPASE recognizes deep paraphrase relations in an event-specific context of sentences and can cover event paraphrases of more situations, bringing about a better generalization. Additionally, the embeddings of argument roles are encoded into event embedding without relying on a fixed number and type of arguments, which results in the better scalability of EPASE. Experiments on both within- and cross-document event coreference demonstrate its consistent and significant superiority compared to existing methods.

Highlights

  • IntroductionEvent coreference resolution clusters event mentions referring to the same real-world event, no matter within a single document (denoted as WD) or across multiple documents (denoted as CD)

  • Event coreference resolution clusters event mentions referring to the same real-world event, no matter within a single document or across multiple documents

  • Experiments demonstrate the significant superiority of EPASE, and the event-specific paraphrase features and the argument-aware semantic embeddings are both beneficial to resolving event coreference

Read more

Summary

Introduction

Event coreference resolution clusters event mentions referring to the same real-world event, no matter within a single document (denoted as WD) or across multiple documents (denoted as CD). (2) The original trainwreck Tara Reid’s publicist confirmedm that the actress Reid was admitted intom Promises Treatment Center in Los Angeles and it was her decisionm5 These five event mentions in the sentences can be clustered into two sets {m1,m4, m5} and {m2, m3}. Many methods (Yang et al, 2015; Choubey and Huang, 2017; Barhom et al, 2019) have adopted these similarities as important features to train classifiers This means is to identify the paraphrase relation between events (i.e., one event can be viewed as a paraphrase of another event) by modeling the similarity between event components (i.e., event mentions and their arguments). Experiments demonstrate the significant superiority of EPASE, and the event-specific paraphrase features and the argument-aware semantic embeddings are both beneficial to resolving event coreference

Feature or template based methods
Neural network based methods
Information enhanced methods
The EPASE Model
Document clustering
Mention-pair sampling
Event-specific paraphrase identification
Semantic similarity evaluation
Semantic role labeling
Semantic integration
Training and inference
Experimental setup
Baselines
Implement details
Experimental results
Analysis of event-specific paraphrase
Conclusions and future work
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call