Cross-document Coreference Resolution over Predicted Mentions
This addresses the under-explored problem of linking mentions across documents for NLP researchers, though it is incremental as it extends an existing within-document model.
The paper tackles cross-document coreference resolution by introducing the first end-to-end model that works on raw text, achieving competitive results on gold mentions and setting baseline results on predicted mentions using the ECB+ dataset.
Coreference resolution has been mostly investigated within a single document scope, showing impressive progress in recent years based on end-to-end models. However, the more challenging task of cross-document (CD) coreference resolution remained relatively under-explored, with the few recent models applied only to gold mentions. Here, we introduce the first end-to-end model for CD coreference resolution from raw text, which extends the prominent model for within-document coreference to the CD setting. Our model achieves competitive results for event and entity coreference resolution on gold mentions. More importantly, we set first baseline results, on the standard ECB+ dataset, for CD coreference resolution over predicted mentions. Further, our model is simpler and more efficient than recent CD coreference resolution systems, while not using any external resources.