{"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/highly-parallel-autoregressive-entity-linking","title":"Highly Parallel Autoregressive Entity Linking with Discriminative Correction","arxiv_id":"2109.03792","date":"2021-09-08","proceeding":"EMNLP 2021 11","authors":["Nicola De Cao","Wilker Aziz","Ivan Titov"],"abstract":"Generative approaches have been recently shown to be effective for both Entity Disambiguation and Entity Linking (i.e., joint mention detection and disambiguation). However, the previously proposed autoregressive formulation for EL suffers from i) high computational cost due to a complex (deep) decoder, ii) non-parallelizable decoding that scales with the source sequence length, and iii) the need for training on a large amount of data. In this work, we propose a very efficient approach that parallelizes autoregressive linking across all potential mentions and relies on a shallow and efficient decoder. Moreover, we augment the generative objective with an extra discriminative component, i.e., a correction term which lets us directly optimize the generator's ranking. When taken together, these techniques tackle all the above issues: our model is >70 times faster and more accurate than the previous generative method, outperforming state-of-the-art approaches on the standard English dataset AIDA-CoNLL. Source code available at https://github.com/nicola-decao/efficient-autoregressive-EL","url_abs":"https://arxiv.org/abs/2109.03792v1","url_pdf":"https://arxiv.org/pdf/2109.03792v1.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":"highly-parallel-autoregressive-entity-linking","repo_url":"https://github.com/nicola-decao/efficient-autoregressive-EL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"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-linking-on-aida-conll","task":"Entity Linking","dataset":"AIDA-CoNLL","model":"De Cao et al. (2021b)","rank_in_archive_order":6,"of":17,"metrics":{"Micro-F1 strong":"85.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.03792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03792"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nicola-decao/efficient-autoregressive-EL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"96b6713ff1c322ca","entry":"label_smoothed_nll_loss","repo":"nicola-decao/efficient-autoregressive-EL","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/nicola-decao/efficient-autoregressive-EL/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"96b6713ff1c322ca"}},{"code_sha256_prefix":"f8d1fe362ffd1e5e","entry":"beam_search","repo":"nicola-decao/efficient-autoregressive-EL","repo_kind":"official","path":"src/beam_search.py","file_url":"https://github.com/nicola-decao/efficient-autoregressive-EL/blob/HEAD/src/beam_search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f8d1fe362ffd1e5e"}},{"code_sha256_prefix":"897b09255be412e5","entry":"get_markdown","repo":"nicola-decao/efficient-autoregressive-EL","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/nicola-decao/efficient-autoregressive-EL/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"897b09255be412e5"}},{"code_sha256_prefix":"88ca47687541fb04","entry":"tile","repo":"nicola-decao/efficient-autoregressive-EL","repo_kind":"official","path":"src/beam_search.py","file_url":"https://github.com/nicola-decao/efficient-autoregressive-EL/blob/HEAD/src/beam_search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88ca47687541fb04"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}