Cross-document Event Coreference Search: Task, Dataset and Modeling

TL;DR

This paper introduces the task of cross-document event coreference search, creates a dataset from Wikipedia, and proposes a novel model that improves coreference retrieval performance by integrating coreference scoring into a passage retrieval framework.

Contribution

It defines the new task of cross-document event coreference search, provides a dataset derived from Wikipedia, and develops a novel model that enhances coreference scoring within a retrieval architecture.

Findings

The proposed model outperforms baseline retrieval methods.

The dataset enables research on large-scale event coreference search.

Integrating coreference scoring improves retrieval accuracy.

Abstract

The task of Cross-document Coreference Resolution has been traditionally formulated as requiring to identify all coreference links across a given set of documents. We propose an appealing, and often more applicable, complementary set up for the task - Cross-document Coreference Search, focusing in this paper on event coreference. Concretely, given a mention in context of an event of interest, considered as a query, the task is to find all coreferring mentions for the query event in a large document collection. To support research on this task, we create a corresponding dataset, which is derived from Wikipedia while leveraging annotations in the available Wikipedia Event Coreference dataset (WEC-Eng). Observing that the coreference search setup is largely analogous to the setting of Open Domain Question Answering, we adapt the prominent Deep Passage Retrieval (DPR) model to our setting, as an appealing baseline. Finally, we present a novel model that integrates a powerful coreference scoring scheme into the DPR architecture, yielding improved performance.