UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Multilingual Autoregressive Entity Linking

De Cao, N; Wu, L; Popat, K; Artetxe, M; Goyal, N; Plekhanov, M; Zettlemoyer, L; ... Petroni, F; + view all (2022) Multilingual Autoregressive Entity Linking. Transactions of the Association for Computational Linguistics , 10 pp. 274-290. 10.1162/tacl_a_00460. Green open access

[thumbnail of tacl_a_00460.pdf]
Preview
Text
tacl_a_00460.pdf - Published Version

Download (576kB) | Preview

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 we establish new state-of-the-art results. Source code available at https://github.com/facebookresearch/GENRE.

Type: Article
Title: Multilingual Autoregressive Entity Linking
Open access status: An open access version is available from UCL Discovery
DOI: 10.1162/tacl_a_00460
Publisher version: https://doi.org/10.1162/tacl_a_00460
Language: English
Additional information: Copyright © 2022 Association for Computational Linguistics. Distributed under a CC-BY 4.0 license. This is an open-access article distributed under the terms of the Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. For a full description of the license, please visit https://creativecommons.org/licenses/by/4.0/legalcode.
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
URI: https://discovery.ucl.ac.uk/id/eprint/10148264
Downloads since deposit
Loading...
48Downloads
Download activity - last month
Loading...
Download activity - last 12 months
Loading...
Downloads by country - last 12 months
1.Russian Federation
2
2.China
2
3.United Kingdom
1
4.Singapore
1
5.Germany
1
6.United States
1

Archive Staff Only

View Item View Item