Multilingual Autoregressive Entity Linking

TL;DR

This paper introduces mGENRE, a multilingual autoregressive sequence-to-sequence model for entity linking that improves accuracy and efficiency by leveraging cross-lingual entity name matching and zero-shot capabilities.

Contribution

The paper presents a novel autoregressive approach for multilingual entity linking that effectively models cross-lingual interactions and enables fast, scalable search without large vector indices.

Findings

Achieves over 50% improvement in zero-shot language accuracy.

Establishes new state-of-the-art results on MEL benchmarks.

Demonstrates efficient cross-lingual entity linking without large-scale vector search.

Abstract

We present mGENRE, a sequence-to-sequence system for the Multilingual Entity Linking (MEL) problem -- the task of resolving language-specific mentions to a multilingual Knowledge Base (KB). For a mention in a given language, mGENRE predicts the name of the target entity left-to-right, token-by-token in an autoregressive fashion. The autoregressive formulation allows us to effectively cross-encode mention string and entity names to capture more interactions than the standard dot product between mention and entity vectors. It also enables fast search within a large KB even for mentions that do not appear in mention tables and with no need for large-scale vector indices. While prior MEL works use a single representation for each entity, we match against entity names of as many languages as possible, which allows exploiting language connections between source input and target name. Moreover, in a zero-shot setting on languages with no training data at all, mGENRE treats the target language as a latent variable that is marginalized at prediction time. This leads to over 50% improvements in average accuracy. We show the efficacy of our approach through extensive evaluation including experiments on three popular MEL benchmarks where mGENRE establishes new state-of-the-art results. Code and pre-trained models at https://github.com/facebookresearch/GENRE.