{"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/cg","name":"NER","slug":"cg","description_markdown":"The named entity recognition (NER) involves identification of key information in the text and classification into a set of predefined categories. This includes standard entities in the text like Part of Speech (PoS) and entities like places, names etc...","categories":[{"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":1729,"papers_with_code":665,"benchmarks":4,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":27,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/ner-on-conll-2003-1","slug":"ner-on-conll-2003-1","dataset":"CoNLL 2003","dataset_url":"/dataset/conll-2003","rows_in_archive":1,"metrics":["AUC","Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":{"model":"Def2Vec","paper_title":"Def2Vec: Extensible Word Embeddings from Dictionary Definitions","paper_url":"/paper/def2vec-extensible-word-embeddings-from","paper_date":"2023-12-16","arxiv_id":null,"code_links":[{"title":"IreneMorazzoni/def_2_vec_irene","url":"https://github.com/IreneMorazzoni/def_2_vec_irene"},{"title":"vincenzo-scotti/def_2_vec","url":"https://github.com/vincenzo-scotti/def_2_vec"}],"syntology":null}},{"leaderboard":"/sota/ner-on-inlegalner","slug":"ner-on-inlegalner","dataset":"InLegalNER","dataset_url":"/dataset/inlegalner","rows_in_archive":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"opennyaiorg/en_legal_ner_trf","paper_title":"Named Entity Recognition in Indian court judgments","paper_url":"/paper/named-entity-recognition-in-indian-court","paper_date":"2022-11-07","arxiv_id":"2211.03442","code_links":[{"title":"legal-nlp-ekstep/legal_ner","url":"https://github.com/legal-nlp-ekstep/legal_ner"}],"syntology":null}},{"leaderboard":"/sota/ner-on-supermat","slug":"ner-on-supermat","dataset":"SuperMat","dataset_url":"/dataset/supermat","rows_in_archive":1,"metrics":["F1","Precision","Recall"],"first_row_in_archive_order":{"model":"superconductors-Scibert","paper_title":"Automatic extraction of materials and properties from superconductors scientific literature","paper_url":"/paper/automatic-extraction-of-materials-and","paper_date":"2022-10-26","arxiv_id":"2210.15600","code_links":[{"title":"lfoppiano/grobid-superconductors","url":"https://github.com/lfoppiano/grobid-superconductors"},{"title":"lfoppiano/supercon","url":"https://github.com/lfoppiano/supercon"}],"syntology":null}},{"leaderboard":"/sota/ner-on-the-embo-sourcedata-nlp-dataset","slug":"ner-on-the-embo-sourcedata-nlp-dataset","dataset":"The EMBO SourceData-NLP dataset","dataset_url":"/dataset/the-embo-sourcedata-nlp-dataset","rows_in_archive":1,"metrics":["F1 Micro"],"first_row_in_archive_order":{"model":"BioLinkBERT-large","paper_title":"Integrating curation into scientific publishing to train AI models","paper_url":"/paper/the-sourcedata-nlp-dataset-integrating","paper_date":"2023-10-31","arxiv_id":"2310.20440","code_links":[{"title":"source-data/soda-data","url":"https://github.com/source-data/soda-data"}],"syntology":null}},{"leaderboard":null,"slug":"ner-on-dane","dataset":"DaNE","dataset_url":"/dataset/dane","rows_in_archive":0,"metrics":["NER F Score","NER Precision","NER Recall"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/conll-2003","name":"CoNLL 2003","full_name":"","num_papers_in_archive":755},{"url":"/dataset/msra-cn-ner","name":"MSRA CN NER","full_name":"MSRA CN NER Dataset","num_papers_in_archive":23},{"url":"/dataset/ade-corpus","name":"Adverse Drug Events (ADE) Corpus","full_name":"","num_papers_in_archive":14},{"url":"/dataset/bc4chemd","name":"BC4CHEMD","full_name":"BioCreative IV Chemical compound and drug name recognition","num_papers_in_archive":6},{"url":"/dataset/dane","name":"DaNE","full_name":"Danish Dependency Treebank","num_papers_in_archive":6},{"url":"/dataset/harveyner","name":"HarveyNER","full_name":"","num_papers_in_archive":5},{"url":"/dataset/finer-139","name":"FiNER-139","full_name":"","num_papers_in_archive":4},{"url":"/dataset/nuner","name":"NuNER","full_name":"","num_papers_in_archive":4},{"url":"/dataset/supermat","name":"SuperMat","full_name":"","num_papers_in_archive":4},{"url":"/dataset/tlunified-ner","name":"TLUnified-NER","full_name":"","num_papers_in_archive":3},{"url":"/dataset/biographical","name":"Biographical","full_name":"Biographical: A Semi-Supervised Relation Extraction Dataset","num_papers_in_archive":2},{"url":"/dataset/fijo","name":"FIJO","full_name":"French Insurance Job Offer dataset","num_papers_in_archive":2},{"url":"/dataset/inlegalner","name":"InLegalNER","full_name":"InLegalNER","num_papers_in_archive":2},{"url":"/dataset/lepiszcze","name":"LEPISZCZE","full_name":"","num_papers_in_archive":2},{"url":"/dataset/aiseckg","name":"AISECKG","full_name":"AISecKG: Knowledge Graph Dataset for Cybersecurity Education","num_papers_in_archive":1},{"url":"/dataset/first-harem","name":"First HAREM","full_name":"Primeiro HAREM","num_papers_in_archive":1},{"url":"/dataset/iecsil-fire-2018-shared-task","name":"IECSIL FIRE-2018 Shared Task","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mini-harem","name":"Mini HAREM","full_name":"","num_papers_in_archive":1},{"url":"/dataset/rate-ner","name":"RaTE-NER","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tasteset","name":"TASTEset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/the-embo-sourcedata-nlp-dataset","name":"The EMBO SourceData-NLP dataset","full_name":"The SourceData-NLP dataset: integrating curation into scientific publishing for training large language models","num_papers_in_archive":1},{"url":"/dataset/noise-sf","name":"Noise-SF","full_name":"","num_papers_in_archive":0},{"url":"/dataset/popcorn","name":"POPCORN","full_name":"POPCORN: Fictional and Synthetic Intelligence Reports for Named Entity Recognition and Relation Extraction Tasks","num_papers_in_archive":0},{"url":"/dataset/second-harem","name":"Second HAREM","full_name":"Segundo HAREM","num_papers_in_archive":0},{"url":"/dataset/sigarra-news-corpus","name":"SIGARRA News Corpus","full_name":"","num_papers_in_archive":0},{"url":"/dataset/sourcedata-nlp","name":"SourceData-NLP","full_name":"The SourceData-NLP dataset: integrating curation into scientific publishing for training large language models","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/event-extraction","name":"Event Extraction"},{"url":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)"}],"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":18,"rows_per_page":100,"shown":100,"of":1729,"of_with_code":665,"tagged_in_all":1729,"counts":{"archive_papers_tagged":1729,"with_a_code_link":665,"where_syntology_ran_a_sample":70,"not_listed_spam_title":0,"listed":1729,"listed_where_code_ran":70,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":60,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":60,"listed_every_run_a_failure_of_syntologys_instrument":10,"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/nezha-neural-contextualized-representation","slug":"nezha-neural-contextualized-representation","title":"NEZHA: Neural Contextualized Representation for Chinese Language Understanding","date":"2019-08-31","arxiv_id":"1909.00204","repositories_listed":10,"syntology":null},{"url":"/paper/crossner-evaluating-cross-domain-named-entity","slug":"crossner-evaluating-cross-domain-named-entity","title":"CrossNER: Evaluating Cross-Domain Named Entity Recognition","date":"2020-12-08","arxiv_id":"2012.04373","repositories_listed":5,"syntology":null},{"url":"/paper/arabert-transformer-based-model-for-arabic","slug":"arabert-transformer-based-model-for-arabic","title":"AraBERT: Transformer-based Model for Arabic Language Understanding","date":"2020-02-28","arxiv_id":"2003.00104","repositories_listed":4,"syntology":null},{"url":"/paper/fast-and-accurate-entity-recognition-with","slug":"fast-and-accurate-entity-recognition-with","title":"Fast and Accurate Entity Recognition with Iterated Dilated Convolutions","date":"2017-02-07","arxiv_id":"1702.02098","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fast-and-accurate-entity-recognition-with#ran","syntology_url":"https://syntology.ai/paper/1702.02098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.02098"}},"official":{"repos":["iesl/dilated-cnn-ner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rita-automatic-framework-for-designing-of","slug":"rita-automatic-framework-for-designing-of","title":"RITA: Automatic Framework for Designing of Resilient IoT Applications","date":"2024-11-27","arxiv_id":"2411.18324","repositories_listed":3,"syntology":null},{"url":"/paper/ratescore-a-metric-for-radiology-report","slug":"ratescore-a-metric-for-radiology-report","title":"RaTEScore: A Metric for Radiology Report Generation","date":"2024-06-24","arxiv_id":"2406.16845","repositories_listed":3,"syntology":null},{"url":"/paper/diffusionner-boundary-diffusion-for-named","slug":"diffusionner-boundary-diffusion-for-named","title":"DiffusionNER: Boundary Diffusion for Named Entity Recognition","date":"2023-05-22","arxiv_id":"2305.13298","repositories_listed":3,"syntology":null},{"url":"/paper/finer-financial-named-entity-recognition","slug":"finer-financial-named-entity-recognition","title":"FiNER-ORD: Financial Named Entity Recognition Open Research Dataset","date":"2023-02-22","arxiv_id":"2302.11157","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/finer-financial-named-entity-recognition#ran","syntology_url":"https://syntology.ai/paper/2302.11157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11157"}},"official":{"repos":["gtfintechlab/finer","gtfintechlab/finer-ord"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/let-s-stop-incorrect-comparisons-in-end-to","slug":"let-s-stop-incorrect-comparisons-in-end-to","title":"Let's Stop Incorrect Comparisons in End-to-end Relation Extraction!","date":"2020-09-22","arxiv_id":"2009.10684","repositories_listed":3,"syntology":null},{"url":"/paper/beheshti-ner-persian-named-entity-recognition","slug":"beheshti-ner-persian-named-entity-recognition","title":"Beheshti-NER: Persian Named Entity Recognition Using BERT","date":"2020-03-19","arxiv_id":"2003.08875","repositories_listed":3,"syntology":null},{"url":"/paper/parallel-sequence-tagging-for-concept","slug":"parallel-sequence-tagging-for-concept","title":"Parallel sequence tagging for concept recognition","date":"2020-03-16","arxiv_id":"2003.07424","repositories_listed":3,"syntology":null},{"url":"/paper/cluener2020-fine-grained-name-entity","slug":"cluener2020-fine-grained-name-entity","title":"CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese","date":"2020-01-13","arxiv_id":"2001.04351","repositories_listed":3,"syntology":null},{"url":"/paper/remedying-bilstm-cnn-deficiency-in-modeling","slug":"remedying-bilstm-cnn-deficiency-in-modeling","title":"Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER","date":"2019-08-29","arxiv_id":"1908.11046","repositories_listed":3,"syntology":null},{"url":"/paper/chinese-ner-using-lattice-lstm","slug":"chinese-ner-using-lattice-lstm","title":"Chinese NER Using Lattice LSTM","date":"2018-05-05","arxiv_id":"1805.02023","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chinese-ner-using-lattice-lstm#ran","syntology_url":"https://syntology.ai/paper/1805.02023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.02023"}},"official":{"repos":["jiesutd/LatticeLSTM"],"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/empower-sequence-labeling-with-task-aware","slug":"empower-sequence-labeling-with-task-aware","title":"Empower Sequence Labeling with Task-Aware Neural Language Model","date":"2017-09-13","arxiv_id":"1709.04109","repositories_listed":3,"syntology":null},{"url":"/paper/multimodal-llms-for-ocr-ocr-post-correction","slug":"multimodal-llms-for-ocr-ocr-post-correction","title":"Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents","date":"2025-04-01","arxiv_id":"2504.00414","repositories_listed":2,"syntology":null},{"url":"/paper/insightbuddy-ai-medication-extraction-and","slug":"insightbuddy-ai-medication-extraction-and","title":"INSIGHTBUDDY-AI: Medication Extraction and Entity Linking using Large Language Models and Ensemble Learning","date":"2024-09-28","arxiv_id":"2409.19467","repositories_listed":2,"syntology":null},{"url":"/paper/whisperner-unified-open-named-entity-and","slug":"whisperner-unified-open-named-entity-and","title":"WhisperNER: Unified Open Named Entity and Speech Recognition","date":"2024-09-12","arxiv_id":"2409.08107","repositories_listed":2,"syntology":null},{"url":"/paper/do-english-named-entity-recognizers-work-well","slug":"do-english-named-entity-recognizers-work-well","title":"Do \"English\" Named Entity Recognizers Work Well on Global Englishes?","date":"2024-04-20","arxiv_id":"2404.13465","repositories_listed":2,"syntology":null},{"url":"/paper/embedded-named-entity-recognition-using","slug":"embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/embedded-named-entity-recognition-using#ran","syntology_url":"https://syntology.ai/paper/2403.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11747"}},"official":{"repos":["nicpopovic/stoke","nicpopovic/ember"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-named-entity-recognition","slug":"evaluating-named-entity-recognition","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","date":"2024-03-18","arxiv_id":"2403.12212","repositories_listed":2,"syntology":null},{"url":"/paper/rethinking-negative-instances-for-generative","slug":"rethinking-negative-instances-for-generative","title":"Rethinking Negative Instances for Generative Named Entity Recognition","date":"2024-02-26","arxiv_id":"2402.16602","repositories_listed":2,"syntology":null},{"url":"/paper/def2vec-extensible-word-embeddings-from","slug":"def2vec-extensible-word-embeddings-from","title":"Def2Vec: Extensible Word Embeddings from Dictionary Definitions","date":"2023-12-16","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/universal-ner-a-gold-standard-multilingual-1","slug":"universal-ner-a-gold-standard-multilingual-1","title":"Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark","date":"2023-11-15","arxiv_id":"2311.09122","repositories_listed":2,"syntology":null},{"url":"/paper/gliner-generalist-model-for-named-entity","slug":"gliner-generalist-model-for-named-entity","title":"GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer","date":"2023-11-14","arxiv_id":"2311.08526","repositories_listed":2,"syntology":null},{"url":"/paper/reading-order-matters-information-extraction","slug":"reading-order-matters-information-extraction","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","date":"2023-10-17","arxiv_id":"2310.11016","repositories_listed":2,"syntology":null},{"url":"/paper/puoberta-training-and-evaluation-of-a-curated","slug":"puoberta-training-and-evaluation-of-a-curated","title":"PuoBERTa: Training and evaluation of a curated language model for Setswana","date":"2023-10-13","arxiv_id":"2310.09141","repositories_listed":2,"syntology":null},{"url":"/paper/label-supervised-llama-finetuning","slug":"label-supervised-llama-finetuning","title":"Label Supervised LLaMA Finetuning","date":"2023-10-02","arxiv_id":"2310.01208","repositories_listed":2,"syntology":null},{"url":"/paper/universalner-targeted-distillation-from-large","slug":"universalner-targeted-distillation-from-large","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","date":"2023-08-07","arxiv_id":"2308.03279","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/universalner-targeted-distillation-from-large#ran","syntology_url":"https://syntology.ai/paper/2308.03279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03279"}},"official":null}},{"url":"/paper/streamlining-social-media-information","slug":"streamlining-social-media-information","title":"Streamlining Social Media Information Retrieval for COVID-19 Research with Deep Learning","date":"2023-06-28","arxiv_id":"2306.16001","repositories_listed":2,"syntology":null},{"url":"/paper/h2ogpt-democratizing-large-language-models","slug":"h2ogpt-democratizing-large-language-models","title":"h2oGPT: Democratizing Large Language Models","date":"2023-06-13","arxiv_id":"2306.08161","repositories_listed":2,"syntology":null},{"url":"/paper/focus-effective-embedding-initialization-for","slug":"focus-effective-embedding-initialization-for","title":"FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models","date":"2023-05-23","arxiv_id":"2305.14481","repositories_listed":2,"syntology":null},{"url":"/paper/learning-in-context-learning-for-named-entity","slug":"learning-in-context-learning-for-named-entity","title":"Learning In-context Learning for Named Entity Recognition","date":"2023-05-18","arxiv_id":"2305.11038","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/learning-in-context-learning-for-named-entity#ran","syntology_url":"https://syntology.ai/paper/2305.11038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11038"}},"official":{"repos":["chen700564/metaner-icl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/impact-of-position-bias-on-language-models-in","slug":"impact-of-position-bias-on-language-models-in","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","date":"2023-04-26","arxiv_id":"2304.13567","repositories_listed":2,"syntology":null},{"url":"/paper/findvehicle-and-vehiclefinder-a-ner-dataset","slug":"findvehicle-and-vehiclefinder-a-ner-dataset","title":"FindVehicle and VehicleFinder: A NER dataset for natural language-based vehicle retrieval and a keyword-based cross-modal vehicle retrieval system","date":"2023-04-21","arxiv_id":"2304.10893","repositories_listed":2,"syntology":null},{"url":"/paper/gpt-ner-named-entity-recognition-via-large","slug":"gpt-ner-named-entity-recognition-via-large","title":"GPT-NER: Named Entity Recognition via Large Language Models","date":"2023-04-20","arxiv_id":"2304.10428","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-ner-named-entity-recognition-via-large#ran","syntology_url":"https://syntology.ai/paper/2304.10428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10428"}},"official":{"repos":["shuhewang1998/gpt-ner"],"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/type-aware-decomposed-framework-for-few-shot","slug":"type-aware-decomposed-framework-for-few-shot","title":"Type-Aware Decomposed Framework for Few-Shot Named Entity Recognition","date":"2023-02-13","arxiv_id":"2302.06397","repositories_listed":2,"syntology":null},{"url":"/paper/one-model-for-all-domains-collaborative","slug":"one-model-for-all-domains-collaborative","title":"One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER","date":"2023-01-25","arxiv_id":"2301.10410","repositories_listed":2,"syntology":null},{"url":"/paper/foresight-deep-generative-modelling-of","slug":"foresight-deep-generative-modelling-of","title":"Foresight -- Generative Pretrained Transformer (GPT) for Modelling of Patient Timelines using EHRs","date":"2022-12-13","arxiv_id":"2212.08072","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/foresight-deep-generative-modelling-of#ran","syntology_url":"https://syntology.ai/paper/2212.08072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08072"}},"official":{"repos":["cogstack/foresight"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/frustratingly-easy-label-projection-for-cross","slug":"frustratingly-easy-label-projection-for-cross","title":"Frustratingly Easy Label Projection for Cross-lingual Transfer","date":"2022-11-28","arxiv_id":"2211.15613","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/frustratingly-easy-label-projection-for-cross#ran","syntology_url":"https://syntology.ai/paper/2211.15613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.15613"}},"official":{"repos":["edchengg/easyproject"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/genius-sketch-based-language-model-pre","slug":"genius-sketch-based-language-model-pre","title":"GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation","date":"2022-11-18","arxiv_id":"2211.10330","repositories_listed":2,"syntology":null},{"url":"/paper/automatic-extraction-of-materials-and","slug":"automatic-extraction-of-materials-and","title":"Automatic extraction of materials and properties from superconductors scientific literature","date":"2022-10-26","arxiv_id":"2210.15600","repositories_listed":2,"syntology":null},{"url":"/paper/simple-yet-powerful-an-overlooked-1","slug":"simple-yet-powerful-an-overlooked-1","title":"Simple Yet Powerful: An Overlooked Architecture for Nested Named Entity Recognition","date":"2022-10-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/albeto-and-distilbeto-lightweight-spanish","slug":"albeto-and-distilbeto-lightweight-spanish","title":"ALBETO and DistilBETO: Lightweight Spanish Language Models","date":"2022-04-19","arxiv_id":"2204.09145","repositories_listed":2,"syntology":null},{"url":"/paper/miner-improving-out-of-vocabulary-named-1","slug":"miner-improving-out-of-vocabulary-named-1","title":"MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective","date":"2022-04-09","arxiv_id":"2204.04391","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/miner-improving-out-of-vocabulary-named-1#ran","syntology_url":"https://syntology.ai/paper/2204.04391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.04391"}},"official":{"repos":["beyonderxx/miner"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/xlm-k-improving-cross-lingual-language-model","slug":"xlm-k-improving-cross-lingual-language-model","title":"XLM-K: Improving Cross-Lingual Language Model Pre-training with Multilingual Knowledge","date":"2021-09-26","arxiv_id":"2109.12573","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/xlm-k-improving-cross-lingual-language-model#ran","syntology_url":"https://syntology.ai/paper/2109.12573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12573"}},"official":{"repos":["microsoft/Unicoder"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/reproducing-ner-and-pos-when-nothing-is","slug":"reproducing-ner-and-pos-when-nothing-is","title":"reproducing \"ner and pos when nothing is capitalized\"","date":"2021-09-17","arxiv_id":"2109.08396","repositories_listed":2,"syntology":null},{"url":"/paper/bertifying-the-hidden-markov-model-for-multi","slug":"bertifying-the-hidden-markov-model-for-multi","title":"BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition","date":"2021-05-26","arxiv_id":"2105.12848","repositories_listed":2,"syntology":{"n":20,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/bertifying-the-hidden-markov-model-for-multi#ran","syntology_url":"https://syntology.ai/paper/2105.12848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12848"}},"official":{"repos":["Yinghao-Li/CHMM-ALT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/optimizing-small-berts-trained-for-german-ner","slug":"optimizing-small-berts-trained-for-german-ner","title":"Optimizing small BERTs trained for German NER","date":"2021-04-23","arxiv_id":"2104.11559","repositories_listed":2,"syntology":null},{"url":"/paper/earnings-21-a-practical-benchmark-for-asr-in","slug":"earnings-21-a-practical-benchmark-for-asr-in","title":"Earnings-21: A Practical Benchmark for ASR in the Wild","date":"2021-04-22","arxiv_id":"2104.11348","repositories_listed":2,"syntology":null},{"url":"/paper/masakhaner-named-entity-recognition-for","slug":"masakhaner-named-entity-recognition-for","title":"MasakhaNER: Named Entity Recognition for African Languages","date":"2021-03-22","arxiv_id":"2103.11811","repositories_listed":2,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/masakhaner-named-entity-recognition-for#ran","syntology_url":"https://syntology.ai/paper/2103.11811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11811"}},"official":{"repos":["masakhane-io/masakhane-ner"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/few-shot-named-entity-recognition-a","slug":"few-shot-named-entity-recognition-a","title":"Few-Shot Named Entity Recognition: A Comprehensive Study","date":"2020-12-29","arxiv_id":"2012.14978","repositories_listed":2,"syntology":null},{"url":"/paper/enhancing-deep-neural-networks-with","slug":"enhancing-deep-neural-networks-with","title":"Enhancing deep neural networks with morphological information","date":"2020-11-24","arxiv_id":"2011.12432","repositories_listed":2,"syntology":null},{"url":"/paper/interpretable-multi-dataset-evaluation-for","slug":"interpretable-multi-dataset-evaluation-for","title":"Interpretable Multi-dataset Evaluation for Named Entity Recognition","date":"2020-11-13","arxiv_id":"2011.06854","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interpretable-multi-dataset-evaluation-for#ran","syntology_url":"https://syntology.ai/paper/2011.06854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.06854"}},"official":{"repos":["neulab/InterpretEval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/identifying-incorrect-labels-in-the-conll","slug":"identifying-incorrect-labels-in-the-conll","title":"Identifying Incorrect Labels in the CoNLL-2003 Corpus","date":"2020-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/dwie-an-entity-centric-dataset-for-multi-task","slug":"dwie-an-entity-centric-dataset-for-multi-task","title":"DWIE: an entity-centric dataset for multi-task document-level information extraction","date":"2020-09-26","arxiv_id":"2009.12626","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dwie-an-entity-centric-dataset-for-multi-task#ran","syntology_url":"https://syntology.ai/paper/2009.12626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12626"}},"official":{"repos":["klimzaporojets/DWIE"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hunflair-an-easy-to-use-tool-for-state-of-the","slug":"hunflair-an-easy-to-use-tool-for-state-of-the","title":"HunFlair: An Easy-to-Use Tool for State-of-the-Art Biomedical Named Entity Recognition","date":"2020-08-17","arxiv_id":"2008.07347","repositories_listed":2,"syntology":null},{"url":"/paper/domain-specific-language-model-pretraining","slug":"domain-specific-language-model-pretraining","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","date":"2020-07-31","arxiv_id":"2007.15779","repositories_listed":2,"syntology":null},{"url":"/paper/pyramid-a-layered-model-for-nested-named","slug":"pyramid-a-layered-model-for-nested-named","title":"Pyramid: A Layered Model for Nested Named Entity Recognition","date":"2020-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/information-extraction-of-clinical-trial","slug":"information-extraction-of-clinical-trial","title":"Information Extraction of Clinical Trial Eligibility Criteria","date":"2020-06-12","arxiv_id":"2006.07296","repositories_listed":2,"syntology":null},{"url":"/paper/foreshadowing-the-benefits-of-incidental","slug":"foreshadowing-the-benefits-of-incidental","title":"Foreseeing the Benefits of Incidental Supervision","date":"2020-06-09","arxiv_id":"2006.05500","repositories_listed":2,"syntology":null},{"url":"/paper/code-and-named-entity-recognition-in","slug":"code-and-named-entity-recognition-in","title":"Code and Named Entity Recognition in StackOverflow","date":"2020-05-04","arxiv_id":"2005.01634","repositories_listed":2,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/code-and-named-entity-recognition-in#ran","syntology_url":"https://syntology.ai/paper/2005.01634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.01634"}},"official":{"repos":["jeniyat/StackOverflowNER"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/word2vec-optimal-hyper-parameters-and-their","slug":"word2vec-optimal-hyper-parameters-and-their","title":"Word2Vec: Optimal Hyper-Parameters and Their Impact on NLP Downstream Tasks","date":"2020-03-23","arxiv_id":"2003.11645","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/word2vec-optimal-hyper-parameters-and-their#ran","syntology_url":"https://syntology.ai/paper/2003.11645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.11645"}},"official":{"repos":["tosingithub/sdesk"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/med7-a-transferable-clinical-natural-language","slug":"med7-a-transferable-clinical-natural-language","title":"Med7: a transferable clinical natural language processing model for electronic health records","date":"2020-03-03","arxiv_id":"2003.01271","repositories_listed":2,"syntology":null},{"url":"/paper/cross-lingual-alignment-vs-joint-training-a","slug":"cross-lingual-alignment-vs-joint-training-a","title":"Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework","date":"2019-10-10","arxiv_id":"1910.04708","repositories_listed":2,"syntology":null},{"url":"/paper/hierarchically-refined-label-attention","slug":"hierarchically-refined-label-attention","title":"Hierarchically-Refined Label Attention Network for Sequence Labeling","date":"2019-08-23","arxiv_id":"1908.08676","repositories_listed":2,"syntology":null},{"url":"/paper/simplify-the-usage-of-lexicon-in-chinese-ner","slug":"simplify-the-usage-of-lexicon-in-chinese-ner","title":"Simplify the Usage of Lexicon in Chinese NER","date":"2019-08-16","arxiv_id":"1908.05969","repositories_listed":2,"syntology":null},{"url":"/paper/scaling-up-open-tagging-from-tens-to","slug":"scaling-up-open-tagging-from-tens-to","title":"Scaling up Open Tagging from Tens to Thousands: Comprehension Empowered Attribute Value Extraction from Product Title","date":"2019-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/towards-robust-named-entity-recognition-for","slug":"towards-robust-named-entity-recognition-for","title":"Towards Robust Named Entity Recognition for Historic German","date":"2019-06-18","arxiv_id":"1906.07592","repositories_listed":2,"syntology":null},{"url":"/paper/beto-bentz-becas-the-surprising-cross-lingual","slug":"beto-bentz-becas-the-surprising-cross-lingual","title":"Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT","date":"2019-04-19","arxiv_id":"1904.09077","repositories_listed":2,"syntology":null},{"url":"/paper/etnlp-a-toolkit-for-extraction-evaluation-and","slug":"etnlp-a-toolkit-for-extraction-evaluation-and","title":"ETNLP: a visual-aided systematic approach to select pre-trained embeddings for a downstream task","date":"2019-03-11","arxiv_id":"1903.04433","repositories_listed":2,"syntology":null},{"url":"/paper/glyce-glyph-vectors-for-chinese-character","slug":"glyce-glyph-vectors-for-chinese-character","title":"Glyce: Glyph-vectors for Chinese Character Representations","date":"2019-01-29","arxiv_id":"1901.10125","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glyce-glyph-vectors-for-chinese-character#ran","syntology_url":"https://syntology.ai/paper/1901.10125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10125"}},"official":{"repos":["ShannonAI/glyce"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/collabonet-collaboration-of-deep-neural","slug":"collabonet-collaboration-of-deep-neural","title":"CollaboNet: collaboration of deep neural networks for biomedical named entity recognition","date":"2018-09-21","arxiv_id":"1809.07950","repositories_listed":2,"syntology":null},{"url":"/paper/design-challenges-and-misconceptions-in","slug":"design-challenges-and-misconceptions-in","title":"Design Challenges and Misconceptions in Neural Sequence Labeling","date":"2018-06-12","arxiv_id":"1806.04470","repositories_listed":2,"syntology":null},{"url":"/paper/a-deep-neural-network-model-for-the-task-of","slug":"a-deep-neural-network-model-for-the-task-of","title":"A Deep Neural Network Model for the Task of Named Entity Recognition","date":"2018-02-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/vncorenlp-a-vietnamese-natural-language","slug":"vncorenlp-a-vietnamese-natural-language","title":"VnCoreNLP: A Vietnamese Natural Language Processing Toolkit","date":"2018-01-04","arxiv_id":"1801.01331","repositories_listed":2,"syntology":null},{"url":"/paper/effective-use-of-bidirectional-language","slug":"effective-use-of-bidirectional-language","title":"Effective Use of Bidirectional Language Modeling for Transfer Learning in Biomedical Named Entity Recognition","date":"2017-11-21","arxiv_id":"1711.07908","repositories_listed":2,"syntology":null},{"url":"/paper/a-discourse-level-named-entity-recognition","slug":"a-discourse-level-named-entity-recognition","title":"A Discourse-Level Named Entity Recognition and Relation Extraction Dataset for Chinese Literature Text","date":"2017-11-19","arxiv_id":"1711.07010","repositories_listed":2,"syntology":null},{"url":"/paper/deep-active-learning-for-named-entity","slug":"deep-active-learning-for-named-entity","title":"Deep Active Learning for Named Entity Recognition","date":"2017-07-19","arxiv_id":"1707.05928","repositories_listed":2,"syntology":null},{"url":"/paper/pampo-using-pattern-matching-and-pos-tagging","slug":"pampo-using-pattern-matching-and-pos-tagging","title":"PAMPO: using pattern matching and pos-tagging for effective Named Entities recognition in Portuguese","date":"2016-12-30","arxiv_id":"1612.09535","repositories_listed":2,"syntology":null},{"url":"/paper/towards-deep-learning-in-hindi-ner-an","slug":"towards-deep-learning-in-hindi-ner-an","title":"Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Scarcity","date":"2016-10-31","arxiv_id":"1610.09756","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-job-learning-with-bayesian-decision","slug":"on-the-job-learning-with-bayesian-decision","title":"On-the-Job Learning with Bayesian Decision Theory","date":"2015-06-10","arxiv_id":"1506.03140","repositories_listed":2,"syntology":null},{"url":"/paper/selecting-and-merging-towards-adaptable-and","slug":"selecting-and-merging-towards-adaptable-and","title":"Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language Models","date":"2025-06-28","arxiv_id":"2506.22813","repositories_listed":1,"syntology":null},{"url":"/paper/label-guided-in-context-learning-for-named","slug":"label-guided-in-context-learning-for-named","title":"Label-Guided In-Context Learning for Named Entity Recognition","date":"2025-05-29","arxiv_id":"2505.23722","repositories_listed":1,"syntology":null},{"url":"/paper/named-entity-recognition-in-historical","slug":"named-entity-recognition-in-historical","title":"Named Entity Recognition in Historical Italian: The Case of Giacomo Leopardi's Zibaldone","date":"2025-05-26","arxiv_id":"2505.20113","repositories_listed":1,"syntology":null},{"url":"/paper/towards-ds-ner-unveiling-and-addressing","slug":"towards-ds-ner-unveiling-and-addressing","title":"Towards DS-NER: Unveiling and Addressing Latent Noise in Distant Annotations","date":"2025-05-18","arxiv_id":"2505.12454","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparative-analysis-of-static-word","slug":"a-comparative-analysis-of-static-word","title":"A Comparative Analysis of Static Word Embeddings for Hungarian","date":"2025-05-12","arxiv_id":"2505.07809","repositories_listed":1,"syntology":null},{"url":"/paper/vts-llm-domain-adaptive-llm-agent-for","slug":"vts-llm-domain-adaptive-llm-agent-for","title":"VTS-LLM: Domain-Adaptive LLM Agent for Enhancing Awareness in Vessel Traffic Services through Natural Language","date":"2025-05-02","arxiv_id":"2505.00989","repositories_listed":1,"syntology":null},{"url":"/paper/natural-language-processing-tools-for","slug":"natural-language-processing-tools-for","title":"Natural Language Processing tools for Pharmaceutical Manufacturing Information Extraction from Patents","date":"2025-04-29","arxiv_id":"2504.20598","repositories_listed":1,"syntology":null},{"url":"/paper/methods-for-recognizing-nested-terms","slug":"methods-for-recognizing-nested-terms","title":"Methods for Recognizing Nested Terms","date":"2025-04-22","arxiv_id":"2504.16007","repositories_listed":1,"syntology":null},{"url":"/paper/myner-contextualized-burmese-named-entity","slug":"myner-contextualized-burmese-named-entity","title":"myNER: Contextualized Burmese Named Entity Recognition with Bidirectional LSTM and fastText Embeddings via Joint Training with POS Tagging","date":"2025-04-05","arxiv_id":"2504.04038","repositories_listed":1,"syntology":null},{"url":"/paper/gliner-biomed-a-suite-of-efficient-models-for","slug":"gliner-biomed-a-suite-of-efficient-models-for","title":"GLiNER-BioMed: A Suite of Efficient Models for Open Biomedical Named Entity Recognition","date":"2025-04-01","arxiv_id":"2504.00676","repositories_listed":1,"syntology":null},{"url":"/paper/transformer-based-named-entity-recognition-2","slug":"transformer-based-named-entity-recognition-2","title":"Transformer-Based Named Entity Recognition for Automated Server Provisioning","date":"2025-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/student-powered-digital-scholarship-colab","slug":"student-powered-digital-scholarship-colab","title":"Student-Powered Digital Scholarship CoLab Project in the HKUST Library: Develop a Chinese Named-Entity Recognition (NER) Tool within One Semester from the Ground Up","date":"2025-03-29","arxiv_id":"2503.22967","repositories_listed":1,"syntology":null},{"url":"/paper/nercat-fine-tuning-for-enhanced-named-entity","slug":"nercat-fine-tuning-for-enhanced-named-entity","title":"NERCat: Fine-Tuning for Enhanced Named Entity Recognition in Catalan","date":"2025-03-18","arxiv_id":"2503.14173","repositories_listed":1,"syntology":null},{"url":"/paper/gema-score-granular-explainable-multi-agent","slug":"gema-score-granular-explainable-multi-agent","title":"GEMA-Score: Granular Explainable Multi-Agent Score for Radiology Report Evaluation","date":"2025-03-07","arxiv_id":"2503.05347","repositories_listed":1,"syntology":null},{"url":"/paper/a-cooperative-multi-agent-framework-for-zero","slug":"a-cooperative-multi-agent-framework-for-zero","title":"A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognition","date":"2025-02-25","arxiv_id":"2502.18702","repositories_listed":1,"syntology":null},{"url":"/paper/small-language-model-makes-an-effective-long","slug":"small-language-model-makes-an-effective-long","title":"Small Language Model Makes an Effective Long Text Extractor","date":"2025-02-11","arxiv_id":"2502.07286","repositories_listed":1,"syntology":null},{"url":"/paper/fewtopner-integrating-few-shot-learning-with","slug":"fewtopner-integrating-few-shot-learning-with","title":"FewTopNER: Integrating Few-Shot Learning with Topic Modeling and Named Entity Recognition in a Multilingual Framework","date":"2025-02-04","arxiv_id":"2502.02391","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-projection-based-data-transfer-for","slug":"revisiting-projection-based-data-transfer-for","title":"Revisiting Projection-based Data Transfer for Cross-Lingual Named Entity Recognition in Low-Resource Languages","date":"2025-01-30","arxiv_id":"2501.18750","repositories_listed":1,"syntology":null}],"syntology_records":18,"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":70,"papers_where_code_ran_first_page":"/task/cg/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":"archive","page":2,"of":18,"url":"/task/cg/papers/2","json":"/task/cg/papers/2.json","rows":100},{"order":"archive","page":3,"of":18,"url":"/task/cg/papers/3","json":"/task/cg/papers/3.json","rows":100},{"order":"archive","page":4,"of":18,"url":"/task/cg/papers/4","json":"/task/cg/papers/4.json","rows":100},{"order":"archive","page":5,"of":18,"url":"/task/cg/papers/5","json":"/task/cg/papers/5.json","rows":100},{"order":"archive","page":6,"of":18,"url":"/task/cg/papers/6","json":"/task/cg/papers/6.json","rows":100},{"order":"archive","page":7,"of":18,"url":"/task/cg/papers/7","json":"/task/cg/papers/7.json","rows":100},{"order":"archive","page":8,"of":18,"url":"/task/cg/papers/8","json":"/task/cg/papers/8.json","rows":100},{"order":"archive","page":9,"of":18,"url":"/task/cg/papers/9","json":"/task/cg/papers/9.json","rows":100},{"order":"archive","page":10,"of":18,"url":"/task/cg/papers/10","json":"/task/cg/papers/10.json","rows":100},{"order":"archive","page":11,"of":18,"url":"/task/cg/papers/11","json":"/task/cg/papers/11.json","rows":100},{"order":"archive","page":12,"of":18,"url":"/task/cg/papers/12","json":"/task/cg/papers/12.json","rows":100},{"order":"archive","page":13,"of":18,"url":"/task/cg/papers/13","json":"/task/cg/papers/13.json","rows":100},{"order":"archive","page":14,"of":18,"url":"/task/cg/papers/14","json":"/task/cg/papers/14.json","rows":100},{"order":"archive","page":15,"of":18,"url":"/task/cg/papers/15","json":"/task/cg/papers/15.json","rows":100},{"order":"archive","page":16,"of":18,"url":"/task/cg/papers/16","json":"/task/cg/papers/16.json","rows":100},{"order":"archive","page":17,"of":18,"url":"/task/cg/papers/17","json":"/task/cg/papers/17.json","rows":100},{"order":"archive","page":18,"of":18,"url":"/task/cg/papers/18","json":"/task/cg/papers/18.json","rows":29},{"order":"ran","page":1,"of":1,"url":"/task/cg/papers/ran/1","json":"/task/cg/papers/ran/1.json","rows":70}],"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":"0d5d2c7f428fc46c8bde76510e1b94b57796ce940e638817814feb847dff7979","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}