{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/clinical-concept-extraction","name":"Clinical Concept Extraction","slug":"clinical-concept-extraction","description_markdown":"Automatic extraction of clinical named entities such as clinical problems, treatments, tests and anatomical parts from clinical notes.\r\n\r\n( [Source](https://arxiv.org/pdf/2012.04005v1.pdf) )","categories":[{"name":"Medical","url":"/area/medical"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":24,"papers_with_code":9,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/clinical-concept-extraction-on-2010-i2b2va","slug":"clinical-concept-extraction-on-2010-i2b2va","dataset":"2010 i2b2/VA","dataset_url":"/dataset/2010-i2b2-va","rows_in_archive":5,"metrics":["Exact Span F1"],"first_row_in_archive_order":{"model":"BERTlarge (MIMIC)","paper_title":"Enhancing Clinical Concept Extraction with Contextual Embeddings","paper_url":"/paper/enhancing-clinical-concept-extraction-with","paper_date":"2019-02-22","arxiv_id":"1902.08691","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/2010-i2b2-va","name":"2010 i2b2/VA","full_name":"2010 i2b2/VA","num_papers_in_archive":18},{"url":"/dataset/ade-corpus","name":"Adverse Drug Events (ADE) Corpus","full_name":"","num_papers_in_archive":14},{"url":"/dataset/2018-n2c2-track-2-adverse-drug-events-and","name":"2018 n2c2 (Track 2) - Adverse Drug Events and Medication Extraction","full_name":"2018 n2c2 shared task on adverse drug events and medication extraction in electronic health records","num_papers_in_archive":8},{"url":"/dataset/toronto-neuroface-dataset","name":"Toronto NeuroFace Dataset","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/clinical-information-retreival","name":"Clinical Information Retreival"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":24,"of":24,"of_with_code":9,"tagged_in_all":24,"counts":{"archive_papers_tagged":24,"with_a_code_link":9,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":24,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/characterbert-reconciling-elmo-and-bert-for","slug":"characterbert-reconciling-elmo-and-bert-for","title":"CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters","date":"2020-10-20","arxiv_id":"2010.10392","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/characterbert-reconciling-elmo-and-bert-for#ran","syntology_url":"https://syntology.ai/paper/2010.10392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10392"}},"official":{"repos":["helboukkouri/character-bert"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/accurate-clinical-and-biomedical-named-entity","slug":"accurate-clinical-and-biomedical-named-entity","title":"Accurate clinical and biomedical Named entity recognition at scale","date":"2022-07-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/clin-x-pre-trained-language-models-and-a","slug":"clin-x-pre-trained-language-models-and-a","title":"CLIN-X: pre-trained language models and a study on cross-task transfer for concept extraction in the clinical domain","date":"2021-12-16","arxiv_id":"2112.08754","repositories_listed":1,"syntology":null},{"url":"/paper/improving-clinical-document-understanding-on","slug":"improving-clinical-document-understanding-on","title":"Improving Clinical Document Understanding on COVID-19 Research with Spark NLP","date":"2020-12-07","arxiv_id":"2012.04005","repositories_listed":1,"syntology":null},{"url":"/paper/embedding-strategies-for-specialized-domains","slug":"embedding-strategies-for-specialized-domains","title":"Embedding Strategies for Specialized Domains: Application to Clinical Entity Recognition","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/clinical-concept-extraction-with-contextual","slug":"clinical-concept-extraction-with-contextual","title":"Clinical Concept Extraction with Contextual Word Embedding","date":"2018-10-24","arxiv_id":"1810.10566","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clinical-concept-extraction-with-contextual#ran","syntology_url":"https://syntology.ai/paper/1810.10566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.10566"}},"official":{"repos":["noc-lab/clinical_concept_extraction"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/recurrent-neural-networks-with-specialized","slug":"recurrent-neural-networks-with-specialized","title":"Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition","date":"2017-06-29","arxiv_id":"1706.09569","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-lstm-crf-for-clinical-concept","slug":"bidirectional-lstm-crf-for-clinical-concept","title":"Bidirectional LSTM-CRF for Clinical Concept Extraction","date":"2016-11-25","arxiv_id":"1611.08373","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-lstm-crf-for-clinical-concept-1","slug":"bidirectional-lstm-crf-for-clinical-concept-1","title":"Bidirectional LSTM-CRF for Clinical Concept Extraction","date":"2016-10-19","arxiv_id":"1610.05858","repositories_listed":1,"syntology":null},{"url":null,"slug":"selective-attention-federated-learning","title":"Selective Attention Federated Learning: Improving Privacy and Efficiency for Clinical Text Classification","date":"2025-04-16","arxiv_id":"2504.11793","repositories_listed":0,"syntology":null},{"url":null,"slug":"burextract-llama-an-llm-for-clinical-concept","title":"BURExtract-Llama: An LLM for Clinical Concept Extraction in Breast Ultrasound Reports","date":"2024-08-21","arxiv_id":"2408.11334","repositories_listed":0,"syntology":null},{"url":null,"slug":"clinical-concept-and-relation-extraction","title":"Clinical Concept and Relation Extraction Using Prompt-based Machine Reading Comprehension","date":"2023-03-14","arxiv_id":"2303.08262","repositories_listed":0,"syntology":null},{"url":"/paper/gatortron-a-large-clinical-language-model-to","slug":"gatortron-a-large-clinical-language-model-to","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","date":"2022-02-02","arxiv_id":"2203.03540","repositories_listed":0,"syntology":null},{"url":null,"slug":"nlnde-at-cantemist-neural-sequence-labeling","title":"NLNDE at CANTEMIST: Neural Sequence Labeling and Parsing Approaches for Clinical Concept Extraction","date":"2020-10-23","arxiv_id":"2010.12322","repositories_listed":0,"syntology":null},{"url":"/paper/cost-effective-selection-of-pretraining-data","slug":"cost-effective-selection-of-pretraining-data","title":"Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media","date":"2020-10-02","arxiv_id":"2010.01150","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-clinical-concepts-from-user","title":"Extracting clinical concepts from user queries","date":"2019-12-12","arxiv_id":"1912.06262","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-the-end-to-end-methodologies-for","title":"Clinical Concept Extraction: a Methodology Review","date":"2019-10-24","arxiv_id":"1910.11377","repositories_listed":0,"syntology":null},{"url":null,"slug":"clinical-concept-extraction-for-document","title":"Clinical Concept Extraction for Document-Level Coding","date":"2019-06-08","arxiv_id":"1906.03380","repositories_listed":0,"syntology":null},{"url":"/paper/enhancing-clinical-concept-extraction-with","slug":"enhancing-clinical-concept-extraction-with","title":"Enhancing Clinical Concept Extraction with Contextual Embeddings","date":"2019-02-22","arxiv_id":"1902.08691","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-risk-factors-for-heart-disease-in","title":"Identifying Risk Factors For Heart Disease in Electronic Medical Records: A Deep Learning Approach","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cliner-20-accessible-and-accurate-clinical","title":"CliNER 2.0: Accessible and Accurate Clinical Concept Extraction","date":"2018-03-06","arxiv_id":"1803.02245","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-word-embeddings-and-sequence","title":"Analysis of Word Embeddings and Sequence Features for Clinical Information Extraction","date":"2015-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"thinkminers-disorder-recognition-using","title":"ThinkMiners: Disorder Recognition using Conditional Random Fields and Distributional Semantics","date":"2014-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/machine-learned-solutions-for-three-stages-of","slug":"machine-learned-solutions-for-three-stages-of","title":"Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010","date":"2011-05-12","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/task/clinical-concept-extraction/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/clinical-concept-extraction/papers/ran/1","json":"/task/clinical-concept-extraction/papers/ran/1.json","rows":2}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"f4a9db5fd45fcf82abada055601dd4d08506ba2371d15b68c4e24ea2a7d931a5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}