{"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/learning-named-entity-tagger-using-domain","title":"Learning Named Entity Tagger using Domain-Specific Dictionary","arxiv_id":"1809.03599","date":"2018-09-10","proceeding":"EMNLP 2018 10","authors":["Jingbo Shang","Liyuan Liu","Xiang Ren","Xiaotao Gu","Teng Ren","Jiawei Han"],"abstract":"Recent advances in deep neural models allow us to build reliable named entity\nrecognition (NER) systems without handcrafting features. However, such methods\nrequire large amounts of manually-labeled training data. There have been\nefforts on replacing human annotations with distant supervision (in conjunction\nwith external dictionaries), but the generated noisy labels pose significant\nchallenges on learning effective neural models. Here we propose two neural\nmodels to suit noisy distant supervision from the dictionary. First, under the\ntraditional sequence labeling framework, we propose a revised fuzzy CRF layer\nto handle tokens with multiple possible labels. After identifying the nature of\nnoisy labels in distant supervision, we go beyond the traditional framework and\npropose a novel, more effective neural model AutoNER with a new Tie or Break\nscheme. In addition, we discuss how to refine distant supervision for better\nNER performance. Extensive experiments on three benchmark datasets demonstrate\nthat AutoNER achieves the best performance when only using dictionaries with no\nadditional human effort, and delivers competitive results with state-of-the-art\nsupervised benchmarks.","url_abs":"http://arxiv.org/abs/1809.03599v1","url_pdf":"http://arxiv.org/pdf/1809.03599v1.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":"learning-named-entity-tagger-using-domain","repo_url":"https://github.com/shangjingbo1226/AutoNER","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"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":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[{"method_slug":"crf","method_name":"CRF"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.03599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.03599"}},"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/shangjingbo1226/AutoNER","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"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":"7991e87d4cd61f17","entry":"build_label_mapping","repo":"shangjingbo1226/AutoNER","repo_kind":"official","path":"preprocess_partial_ner/encode_folder.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/preprocess_partial_ner/encode_folder.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":"7991e87d4cd61f17"}},{"code_sha256_prefix":"6ddc247104bc38fd","entry":"evaluate_chunking","repo":"shangjingbo1226/AutoNER","repo_kind":"official","path":"model_partial_ner/utils.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/model_partial_ner/utils.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":"6ddc247104bc38fd"}},{"code_sha256_prefix":"e5ae18d8434e8fe0","entry":"evaluate_typing","repo":"shangjingbo1226/AutoNER","repo_kind":"official","path":"model_partial_ner/utils.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/model_partial_ner/utils.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":"e5ae18d8434e8fe0"}},{"code_sha256_prefix":"312894e2aabb76ca","entry":"filter_words","repo":"shangjingbo1226/AutoNER","repo_kind":"official","path":"preprocess_partial_ner/encode_folder.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/preprocess_partial_ner/encode_folder.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":"312894e2aabb76ca"}},{"code_sha256_prefix":"0bdd8090a26c0251","entry":"filter_words","repo":"shangjingbo1226/AutoNER","repo_kind":"official","path":"preprocess_partial_ner/encode_mixed_dataset.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/preprocess_partial_ner/encode_mixed_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":"0bdd8090a26c0251"}},{"code_sha256_prefix":"a1ea6bd1afbd3741","entry":"hinge_loss","repo":"shangjingbo1226/AutoNER","repo_kind":"official","path":"model_partial_ner/object.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/model_partial_ner/object.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":"a1ea6bd1afbd3741"}},{"code_sha256_prefix":"235d841405c43b80","entry":"read_corpus","repo":"shangjingbo1226/AutoNER","repo_kind":"official","path":"preprocess_partial_ner/encode_mixed_dataset.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/preprocess_partial_ner/encode_mixed_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":"235d841405c43b80"}},{"code_sha256_prefix":"2ef9bf3ab2938a3d","entry":"read_noisy_corpus","repo":"shangjingbo1226/AutoNER","repo_kind":"official","path":"preprocess_partial_ner/encode_folder.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/preprocess_partial_ner/encode_folder.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":"2ef9bf3ab2938a3d"}},{"code_sha256_prefix":"59f61dc834a020db","entry":"read_noisy_corpus","repo":"shangjingbo1226/AutoNER","repo_kind":"official","path":"preprocess_partial_ner/encode_mixed_dataset.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/preprocess_partial_ner/encode_mixed_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":"59f61dc834a020db"}},{"code_sha256_prefix":"518e906f324956a0","entry":"to_scalar","repo":"shangjingbo1226/AutoNER","repo_kind":"official","path":"model_partial_ner/utils.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/model_partial_ner/utils.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":"518e906f324956a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}