Towards Consistent Document-level Entity Linking: Joint Models for Entity Linking and Coreference Resolution

TL;DR

This paper introduces a joint model for document-level entity linking and coreference resolution, improving consistency and accuracy by leveraging mention connections within documents and structured prediction techniques.

Contribution

It proposes a novel joint modeling approach that combines entity linking and coreference resolution using structured prediction over directed trees, enhancing performance on both tasks.

Findings

Up to +5% F1-score improvement on coref and EL tasks.

50% increase in accuracy for hard cases with missing candidate entities.

Joint modeling outperforms standalone models in experiments.

Abstract

We consider the task of document-level entity linking (EL), where it is important to make consistent decisions for entity mentions over the full document jointly. We aim to leverage explicit "connections" among mentions within the document itself: we propose to join the EL task with that of coreference resolution (coref). This is complementary to related works that exploit either (i) implicit document information (e.g., latent relations among entity mentions, or general language models) or (ii) connections between the candidate links (e.g, as inferred from the external knowledge base). Specifically, we cluster mentions that are linked via coreference, and enforce a single EL for all of the clustered mentions together. The latter constraint has the added benefit of increased coverage by joining EL candidate lists for the thus clustered mentions. We formulate the coref+EL problem as a structured prediction task over directed trees and use a globally normalized model to solve it. Experimental results on two datasets show a boost of up to +5% F1-score on both coref and EL tasks, compared to their standalone counterparts. For a subset of hard cases, with individual mentions lacking the correct EL in their candidate entity list, we obtain a +50% increase in accuracy.