{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multilingual-autoregressive-entity-linking","title":"Multilingual Autoregressive Entity Linking","arxiv_id":"2103.12528","date":"2021-03-23","proceeding":null,"authors":["Nicola De Cao","Ledell Wu","Kashyap Popat","Mikel Artetxe","Naman Goyal","Mikhail Plekhanov","Luke Zettlemoyer","Nicola Cancedda","Sebastian Riedel","Fabio Petroni"],"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.","url_abs":"https://arxiv.org/abs/2103.12528v1","url_pdf":"https://arxiv.org/pdf/2103.12528v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multilingual-autoregressive-entity-linking","repo_url":"https://github.com/facebookresearch/GENRE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"entity-disambiguation","task_name":"Entity Disambiguation"},{"task_slug":"entity-linking","task_name":"Entity Linking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/entity-disambiguation-on-mewsli-9","task":"Entity Disambiguation","dataset":"Mewsli-9","model":"mGENRE","rank_in_archive_order":2,"of":2,"metrics":{"Micro Precision":"90.6"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.12528","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}