Top Cited Papers
Open Access
- 25 March 2022
- journal article
- research article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 10, 274-290
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.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Question Answering by Reasoning Across Documents with Graph Convolutional Networks2019
- Joint Multilingual Supervision for Cross-lingual Entity Linking2018
- Robust Coreference Resolution and Entity Linking on Dialogues: Character Identification on TV Show Transcripts2017
- Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning2017
- Rethinking the Inception Architecture for Computer Vision2016
- Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation2016
- Cross-lingual Wikification Using Multilingual Embeddings2016
- Entity linking for biomedical literatureBMC Medical Informatics and Decision Making, 2015
- WikidataCommunications of the ACM, 2014
- Freebase2008