Cross-document Coreference Resolution over Predicted Mentions

TL;DR

This paper introduces the first end-to-end model for cross-document coreference resolution from raw text, achieving competitive results on gold mentions and establishing baseline results on predicted mentions without external resources.

Contribution

It extends within-document coreference models to the cross-document setting and provides the first baseline results on predicted mentions for this task.

Findings

Achieves competitive results on gold mentions.

Establishes baseline results on predicted mentions.

Model is simpler and more efficient than previous systems.

Abstract

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.