Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling
This work addresses evaluation inconsistencies for researchers in cross-document coreference resolution, though it is incremental as it adapts existing methods.
The authors tackled inconsistent evaluation in cross-document coreference resolution by proposing a pragmatic methodology and building the first end-to-end model, which significantly outperformed state-of-the-art results.
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.