Litcius/Paper detail

Multilingual Autoregressive Entity Linking

Nicola De Cao, Ledell Wu, Kashyap Popat, Mikel Artetxe, Naman Goyal, Mikhail Plekhanov, Luke Zettlemoyer, Nicola Cancedda, Sebastian Riedel, Fabio Petroni

2022Transactions of the Association for Computational Linguistics88 citationsDOIOpen Access PDF

Abstract

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.

Topics & Concepts

Computer scienceSecurity tokenEntity linkingNatural language processingSequence (biology)ENCODEString (physics)Code (set theory)Language modelTask (project management)Autoregressive modelArtificial intelligenceRepresentation (politics)Base (topology)Source codeKnowledge baseProgramming languageEconometricsPoliticsBiologyBiochemistryEconomicsPhysicsSet (abstract data type)ManagementPolitical scienceMathematicsComputer securityQuantum mechanicsGeneChemistryLawGeneticsMathematical analysisTopic ModelingNatural Language Processing TechniquesData Quality and Management
Multilingual Autoregressive Entity Linking | Litcius