Cross-document Event Coreference Search: Task, Dataset and Modeling
This addresses the need for efficient event coreference resolution in large-scale document collections, offering a more applicable setup than traditional methods, though it is incremental as it builds on existing models like DPR.
The paper tackles the problem of cross-document event coreference search by proposing a new task setup where, given an event mention as a query, the goal is to find all coreferring mentions in a large document collection, and they achieve improved performance with a novel model integrating a coreference scoring scheme into the Deep Passage Retrieval architecture.
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.