A Hierarchical Distance-dependent Bayesian Model for Event Coreference Resolution

Bishan Yang,Peter Frazier,Claire Cardie

doi:10.1162/tacl_a_00155

Bishan Yang, Peter Frazier + Show 1 more

Open Access

https://doi.org/10.1162/tacl_a_00155

Copy DOI

Abstract

We present a novel hierarchical distance-dependent Bayesian model for event coreference resolution. While existing generative models for event coreference resolution are completely unsupervised, our model allows for the incorporation of pairwise distances between event mentions — information that is widely used in supervised coreference models to guide the generative clustering processing for better event clustering both within and across documents. We model the distances between event mentions using a feature-rich learnable distance function and encode them as Bayesian priors for nonparametric clustering. Experiments on the ECB+ corpus show that our model outperforms state-of-the-art methods for both within- and cross-document event coreference resolution.

Highlights

The task of event coreference resolution consists of identifying text snippets that describe events, and clustering them such that all event mentions in the same partition refer to the same unique event
We show that integrating pairwise learning of event coreference relations with unsupervised hierarchical modeling of event clustering achieves promising improvements over state-of-theart approaches for within- and cross-document event coreference resolution
dependent Chinese Restaurant Process (DDCRP): a DDCRP model we develop for event coreference resolution

Summary

Introduction

The task of event coreference resolution consists of identifying text snippets that describe events, and clustering them such that all event mentions in the same partition refer to the same unique event. In comparison to entity coreference resolution (Ng, 2010), which deals with identifying and grouping noun phrases that refer to the same discourse entity, event coreference resolution has not been extensively studied. This is, in part, because events typically exhibit a more complex structure than entities: a single event can be described via multiple event mentions, and a single event mention can be associated with multiple event arguments that characterize the participants in the event as well as spatio-temporal information (Bejan and Harabagiu, 2010).

Methods

Results

Discussion

Conclusion