Abstract

We introduce a novel iterative approach for event coreference resolution that gradually builds event clusters by exploiting inter-dependencies among event mentions within the same chain as well as across event chains. Among event mentions in the same chain, we distinguish within- and cross-document event coreference links by using two distinct pairwise classifiers, trained separately to capture differences in feature distributions of within- and cross-document event clusters. Our event coreference approach alternates between WD and CD clustering and combines arguments from both event clusters after every merge, continuing till no more merge can be made. And then it performs further merging between event chains that are both closely related to a set of other chains of events. Experiments on the ECB+ corpus show that our model outperforms state-of-the-art methods in joint task of WD and CD event coreference resolution.

Highlights

  • Event coreference resolution is the task of identifying event mentions and clustering them such that each cluster represents a unique real world event

  • Another very common practice for event coreference is to first group event mentions within a document and group WD clusters across documents (Yang et al, 2015)

  • We presented a novel approach for event coreference resolution that extensively exploits event inter-dependencies between event mentions in the same chain and event mentions across chains

Read more

Summary

Introduction

Event coreference resolution is the task of identifying event mentions and clustering them such that each cluster represents a unique real world event. One common practice (Lee et al, 2012) to approach CD coreference task is to resolve event coreference in a megadocument created by concatenating topic-relevant documents, which essentially does not distinguish WD and CD event links. In a perfect scenario where all WD event mentions are properly clustered and their participants and arguments are combined within a cluster, CD clustering can be performed with ease as sufficient evidences are collected through initial WD clustering. Another very common practice for event coreference is to first group event mentions within a document and group WD clusters across documents (Yang et al, 2015)

Results
Discussion
Conclusion
Full Text
Paper version not known

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