Neural Cross-Lingual Coreference Resolution and its Application to Entity Linking

TL;DR

This paper introduces a neural cross-lingual coreference model that leverages multi-lingual embeddings and language-independent features, improving entity linking accuracy across languages without requiring annotated data in target languages.

Contribution

The paper presents a novel entity-centric neural cross-lingual coreference model that performs well across languages using only English training data, enhancing entity linking in Chinese and Spanish.

Findings

Model trained on English performs well on Chinese and Spanish.

Achieves competitive intrinsic coreference results across languages.

Improves entity linking accuracy without target language annotations.

Abstract

We propose an entity-centric neural cross-lingual coreference model that builds on multi-lingual embeddings and language-independent features. We perform both intrinsic and extrinsic evaluations of our model. In the intrinsic evaluation, we show that our model, when trained on English and tested on Chinese and Spanish, achieves competitive results to the models trained directly on Chinese and Spanish respectively. In the extrinsic evaluation, we show that our English model helps achieve superior entity linking accuracy on Chinese and Spanish test sets than the top 2015 TAC system without using any annotated data from Chinese or Spanish.