{"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/boosting-entity-linking-performance-by","title":"Boosting Entity Linking Performance by Leveraging Unlabeled Documents","arxiv_id":"1906.01250","date":"2019-06-04","proceeding":"ACL 2019 7","authors":["Phong Le","Ivan Titov"],"abstract":"Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and Wikipedia. Our approach consists of two stages. First, we construct a high recall list of candidate entities for each mention in an unlabeled document. Second, we use the candidate lists as weak supervision to constrain our document-level entity linking model. The model treats entities as latent variables and, when estimated on a collection of unlabelled texts, learns to choose entities relying both on local context of each mention and on coherence with other entities in the document. The resulting approach rivals fully-supervised state-of-the-art systems on standard test sets. It also approaches their performance in the very challenging setting: when tested on a test set sampled from the data used to estimate the supervised systems. By comparing to Wikipedia-only training of our model, we demonstrate that modeling unlabeled documents is beneficial.","url_abs":"https://arxiv.org/abs/1906.01250v1","url_pdf":"https://arxiv.org/pdf/1906.01250v1.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":"boosting-entity-linking-performance-by","repo_url":"https://github.com/lephong/wnel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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-aida-conll","task":"Entity Disambiguation","dataset":"AIDA-CoNLL","model":"Le& Titov (2019) (Le and Titov, 2019)","rank_in_archive_order":17,"of":20,"metrics":{"In-KB Accuracy":"89.66"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.01250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01250"}},"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/lephong/wnel","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"8b57b46d448ab02c","entry":"find_leaves","repo":"lephong/wnel","repo_kind":"official","path":"nel/extract_ent2cat.py","file_url":"https://github.com/lephong/wnel/blob/HEAD/nel/extract_ent2cat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8b57b46d448ab02c"}},{"code_sha256_prefix":"aa74ecd862f46c82","entry":"load_person_names","repo":"lephong/wnel","repo_kind":"official","path":"nel/dataset.py","file_url":"https://github.com/lephong/wnel/blob/HEAD/nel/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa74ecd862f46c82"}},{"code_sha256_prefix":"1a2c1760ddb8df3a","entry":"read_conll_file","repo":"lephong/wnel","repo_kind":"official","path":"nel/dataset.py","file_url":"https://github.com/lephong/wnel/blob/HEAD/nel/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1a2c1760ddb8df3a"}},{"code_sha256_prefix":"bc696571050e0978","entry":"read_csv_file","repo":"lephong/wnel","repo_kind":"official","path":"nel/dataset.py","file_url":"https://github.com/lephong/wnel/blob/HEAD/nel/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc696571050e0978"}},{"code_sha256_prefix":"c4a9afba6a26c7c1","entry":"read_ent_net","repo":"lephong/wnel","repo_kind":"official","path":"nel/read_entity_network.py","file_url":"https://github.com/lephong/wnel/blob/HEAD/nel/read_entity_network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c4a9afba6a26c7c1"}},{"code_sha256_prefix":"611ace9429a11414","entry":"read_exlude","repo":"lephong/wnel","repo_kind":"official","path":"nel/read_entity_network.py","file_url":"https://github.com/lephong/wnel/blob/HEAD/nel/read_entity_network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"611ace9429a11414"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}