XCoref: Cross-document Coreference Resolution in the Wild

TL;DR

XCoref is an unsupervised cross-document coreference resolution method that effectively handles abstract, loose, and complex coreference relations in political news, exposing biases in word choice and labeling.

Contribution

The paper introduces XCoref, a novel unsupervised approach capable of resolving complex and abstract coreference mentions in the wild, outperforming existing methods.

Findings

XCoref outperforms state-of-the-art CDCR methods.

It effectively resolves abstract and loose coreference relations.

Evaluation shows improved accuracy on complex political news mentions.

Abstract

Datasets and methods for cross-document coreference resolution (CDCR) focus on events or entities with strict coreference relations. They lack, however, annotating and resolving coreference mentions with more abstract or loose relations that may occur when news articles report about controversial and polarized events. Bridging and loose coreference relations trigger associations that may lead to exposing news readers to bias by word choice and labeling. For example, coreferential mentions of "direct talks between U.S. President Donald Trump and Kim" such as "an extraordinary meeting following months of heated rhetoric" or "great chance to solve a world problem" form a more positive perception of this event. A step towards bringing awareness of bias by word choice and labeling is the reliable resolution of coreferences with high lexical diversity. We propose an unsupervised method named XCoref, which is a CDCR method that capably resolves not only previously prevalent entities, such as persons, e.g., "Donald Trump," but also abstractly defined concepts, such as groups of persons, "caravan of immigrants," events and actions, e.g., "marching to the U.S. border." In an extensive evaluation, we compare the proposed XCoref to a state-of-the-art CDCR method and a previous method TCA that resolves such complex coreference relations and find that XCoref outperforms these methods. Outperforming an established CDCR model shows that the new CDCR models need to be evaluated on semantically complex mentions with more loose coreference relations to indicate their applicability of models to resolve mentions in the "wild" of political news articles.