{"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/distantly-supervised-named-entity-recognition","title":"Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning","arxiv_id":"1906.01378","date":"2019-06-04","proceeding":"ACL 2019 7","authors":["Minlong Peng","Xiaoyu Xing","Qi Zhang","Jinlan Fu","Xuanjing Huang"],"abstract":"In this work, we explore the way to perform named entity recognition (NER) using only unlabeled data and named entity dictionaries. To this end, we formulate the task as a positive-unlabeled (PU) learning problem and accordingly propose a novel PU learning algorithm to perform the task. We prove that the proposed algorithm can unbiasedly and consistently estimate the task loss as if there is fully labeled data. A key feature of the proposed method is that it does not require the dictionaries to label every entity within a sentence, and it even does not require the dictionaries to label all of the words constituting an entity. This greatly reduces the requirement on the quality of the dictionaries and makes our method generalize well with quite simple dictionaries. Empirical studies on four public NER datasets demonstrate the effectiveness of our proposed method. We have published the source code at \\url{https://github.com/v-mipeng/LexiconNER}.","url_abs":"https://arxiv.org/abs/1906.01378v2","url_pdf":"https://arxiv.org/pdf/1906.01378v2.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":"distantly-supervised-named-entity-recognition","repo_url":"https://github.com/v-mipeng/LexiconNER","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.01378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01378"}},"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/v-mipeng/LexiconNER","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"8ca83638ea04cd97","entry":"compute_precision_recall_f1","repo":"v-mipeng/LexiconNER","repo_kind":"official","path":"dict_match.py","file_url":"https://github.com/v-mipeng/LexiconNER/blob/HEAD/dict_match.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":"8ca83638ea04cd97"}},{"code_sha256_prefix":"6ce9c8347c180d5d","entry":"compute_precision_recall_f1_2","repo":"v-mipeng/LexiconNER","repo_kind":"official","path":"dict_match.py","file_url":"https://github.com/v-mipeng/LexiconNER/blob/HEAD/dict_match.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":"6ce9c8347c180d5d"}},{"code_sha256_prefix":"baee7959667f3ee4","entry":"getLabelsAndPreds","repo":"v-mipeng/LexiconNER","repo_kind":"official","path":"dict_match.py","file_url":"https://github.com/v-mipeng/LexiconNER/blob/HEAD/dict_match.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":"baee7959667f3ee4"}},{"code_sha256_prefix":"9dfdc3ee7db11b99","entry":"get_final_result","repo":"v-mipeng/LexiconNER","repo_kind":"official","path":"final_evl.py","file_url":"https://github.com/v-mipeng/LexiconNER/blob/HEAD/final_evl.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":"9dfdc3ee7db11b99"}},{"code_sha256_prefix":"779dc0b23e846462","entry":"get_output","repo":"v-mipeng/LexiconNER","repo_kind":"official","path":"final_evl.py","file_url":"https://github.com/v-mipeng/LexiconNER/blob/HEAD/final_evl.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":"779dc0b23e846462"}},{"code_sha256_prefix":"390527929922fd01","entry":"log_sum_exp","repo":"v-mipeng/LexiconNER","repo_kind":"official","path":"sub_model.py","file_url":"https://github.com/v-mipeng/LexiconNER/blob/HEAD/sub_model.py","link_basis":"harvester_set","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":"390527929922fd01"}},{"code_sha256_prefix":"057e0a226e67ecbd","entry":"prf1","repo":"v-mipeng/LexiconNER","repo_kind":"official","path":"final_evl.py","file_url":"https://github.com/v-mipeng/LexiconNER/blob/HEAD/final_evl.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":"057e0a226e67ecbd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}