Neural Cross-Lingual Entity Linking

TL;DR

This paper introduces a neural cross-lingual entity linking model that effectively disambiguates mentions across languages using multi-perspective similarity training and achieves state-of-the-art results in English, Spanish, and Chinese datasets.

Contribution

The paper presents a novel neural model for cross-lingual entity linking that leverages multi-perspective similarity training and zero-shot transfer with multilingual embeddings.

Findings

Achieves state-of-the-art results on English, Spanish, and Chinese datasets.

Effective zero-shot cross-lingual transfer using multilingual embeddings.

Outperforms previous models in cross-lingual entity linking tasks.

Abstract

A major challenge in Entity Linking (EL) is making effective use of contextual information to disambiguate mentions to Wikipedia that might refer to different entities in different contexts. The problem exacerbates with cross-lingual EL which involves linking mentions written in non-English documents to entries in the English Wikipedia: to compare textual clues across languages we need to compute similarity between textual fragments across languages. In this paper, we propose a neural EL model that trains fine-grained similarities and dissimilarities between the query and candidate document from multiple perspectives, combined with convolution and tensor networks. Further, we show that this English-trained system can be applied, in zero-shot learning, to other languages by making surprisingly effective use of multi-lingual embeddings. The proposed system has strong empirical evidence yielding state-of-the-art results in English as well as cross-lingual: Spanish and Chinese TAC 2015 datasets.