Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling

TL;DR

This paper proposes a practical evaluation protocol for cross-document coreference resolution that only requires raw text and introduces the first end-to-end neural model for this task, significantly outperforming previous methods.

Contribution

It introduces a new evaluation methodology for CD coreference resolution and presents the first end-to-end neural model tailored for this setting.

Findings

The new evaluation protocol is more consistent and realistic.

The proposed model outperforms existing state-of-the-art methods.

Baseline results are established for future research using this methodology.

Abstract

Recent evaluation protocols for Cross-document (CD) coreference resolution have often been inconsistent or lenient, leading to incomparable results across works and overestimation of performance. To facilitate proper future research on this task, our primary contribution is proposing a pragmatic evaluation methodology which assumes access to only raw text -- rather than assuming gold mentions, disregards singleton prediction, and addresses typical targeted settings in CD coreference resolution. Aiming to set baseline results for future research that would follow our evaluation methodology, we build the first end-to-end model for this task. Our model adapts and extends recent neural models for within-document coreference resolution to address the CD coreference setting, which outperforms state-of-the-art results by a significant margin.