Browse State-of-the-Art › Named Entity Recognition (NER)

Named Entity Recognition (NER)

955 papers with code · 76 benchmarks · 130 datasets archive 2025-07-28

Natural Language Processing

Named Entity Recognition (NER) is a task of Natural Language Processing (NLP) that involves identifying and classifying named entities in a text into predefined categories such as person names, organizations, locations, and others. The goal of NER is to extract structured information from unstructured text data and represent it in a machine-readable format. Approaches typically use BIO notation, which differentiates the beginning (B) and the inside (I) of entities. O is used for non-entity tokens.

Example:

Mark Watney visited Mars
B-PER I-PER O B-LOC

( Image credit: Zalando )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

76 leaderboard tables shown for this task, 76 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 76 until expanded.

Syntology 4 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): CoNLL 2003 (English) (2 judged, 0 placed), BC5CDR (1 judged, 0 placed), GENIA (1 judged, 0 placed), BC2GM (1 judged, 0 placed), SciERC (1 judged, 0 placed), BC4CHEMD (1 judged, 0 placed), AnatEM (1 judged, 0 placed), BioRED (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
CoNLL 2003 (English) (73 rows) ACE + document-context Automated Concatenation of Embeddings for Structured Prediction code — Compare
Ontonotes v5 (English) (28 rows) BERT-MRC+DSC Dice Loss for Data-imbalanced NLP Tasks code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
NCBI-disease (26 rows) BioBERT BioBERT: a pre-trained biomedical language representation model... code Syntology official: no sample here; runs from other or unrecorded repositories · 15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified Compare
WNUT 2017 (23 rows) CL-KL Improving Named Entity Recognition by External Context Retrieving... code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
ACE 2005 (20 rows) Ours: cross-sentence ALB A Frustratingly Easy Approach for Entity and Relation Extraction code Syntology official (archive's flag): 3 ran · 3 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; 2 where Syntology's instrument failed) · 1 unverified Compare
JNLPBA (17 rows) KeBioLM Improving Biomedical Pretrained Language Models with Knowledge code — Compare
BC5CDR (16 rows) BINDER Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning code Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 0 unverified Compare
GENIA (14 rows) DeepStruct multi-task w/ finetune DeepStruct: Pretraining of Language Models for Structure Prediction code Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
BC2GM (13 rows) Spark NLP Biomedical Named Entity Recognition at Scale code — Compare
BC5CDR-chemical (13 rows) Spark NLP Biomedical Named Entity Recognition at Scale code — Compare
SLUE (13 rows) W2V2-L-LL60K (pipeline approach, uses LM) SLUE: New Benchmark Tasks for Spoken Language Understanding... code Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
CoNLL++ (11 rows) LUKE + SubRegWeigh (K-means) SubRegWeigh: Effective and Efficient Annotation Weighing with... code — Compare
BC5CDR-disease (10 rows) BioMegatron BioMegatron: Larger Biomedical Domain Language Model code — Compare
ACE 2004 (9 rows) Ours: cross-sentence ALB A Frustratingly Easy Approach for Entity and Relation Extraction code Syntology official (archive's flag): 3 ran · 3 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; 2 where Syntology's instrument failed) · 1 unverified Compare
SciERC (7 rows) SciDeBERTa v2 SciDeBERTa: Learning DeBERTa for Science Technology Documents and... code — Compare
BC4CHEMD (7 rows) BertForTokenClassification (Spark NLP) Accurate clinical and biomedical Named entity recognition at scale code — Compare
WNUT 2016 (7 rows) HGN Hero-Gang Neural Model For Named Entity Recognition code — Compare
CoNLL 2002 (Spanish) (6 rows) ACE + document-context Automated Concatenation of Embeddings for Structured Prediction code — Compare
CoNLL 2002 (Dutch) (6 rows) ACE + document-context Automated Concatenation of Embeddings for Structured Prediction code — Compare
CoNLL 2003 (German) (6 rows) ACE + document-context Automated Concatenation of Embeddings for Structured Prediction code — Compare
Few-NERD (SUP) (6 rows) PL-Marker Packed Levitated Marker for Entity and Relation Extraction code Syntology official (archive's flag): 6 ran · 6 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; 5 where Syntology's instrument failed) · 3 unverified Compare
LINNAEUS (6 rows) BLSTM-CNN-Char (SparkNLP) Biomedical Named Entity Recognition at Scale code — Compare
AnatEM (5 rows) ConNER Enhancing Label Consistency on Document-level Named Entity Recognition code — Compare
CoNLL 2003 (German) Revised (5 rows) FLERT XLM-R FLERT: Document-Level Features for Named Entity Recognition code — Compare
CoNLL03 (5 rows) UniNER-7B UniversalNER: Targeted Distillation from Large Language Models for... code Syntology 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 Compare
CORD-r (4 rows) TPP (LayoutLMv3) Reading Order Matters: Information Extraction from Visually-rich... code — Compare
FUNSD-r (4 rows) TPP (LayoutLMv3) Reading Order Matters: Information Extraction from Visually-rich... code — Compare
Species-800 (4 rows) BioBERT BioBERT: a pre-trained biomedical language representation model... code Syntology official: no sample here; runs from other or unrecorded repositories · 15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified Compare
SemClinBr (3 rows) pucpr/biobertpt-clin BioBERTpt - A Portuguese Neural Language Model for Clinical Named... — — Compare
BioNLP13-CG (3 rows) BLSTM-CNN-Char (SparkNLP) Biomedical Named Entity Recognition at Scale code — Compare
BioRED (3 rows) PubMedBERT-CRF BioRED: A Rich Biomedical Relation Extraction Dataset code — Compare
DWIE (3 rows) REXEL REXEL: An End-to-end Model for Document-Level Relation Extraction... code Syntology official: no sample here; runs from other or unrecorded repositories · 3 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; 2 where Syntology's instrument failed) · 0 unverified Compare
FindVehicle (3 rows) BiLSTM-CRF Bidirectional LSTM-CRF Models for Sequence Tagging code Syntology 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
NEMO-Corpus (morph,test) (3 rows) AlephBERT-base Pipeline AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off... code Syntology community repositories only · 2 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; 2 where Syntology's instrument failed) · 0 unverified Compare
OntoNotes (3 rows) DeepStruct multi-task w/ finetune DeepStruct: Pretraining of Language Models for Structure Prediction code Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
WNUT 2020 (3 rows) mgsohrab mgsohrab at WNUT 2020 Shared Task-1: Neural Exhaustive Approach... code — Compare
CoNLL-2020 (2 rows) LUKE + SubRegWeigh (K-means) SubRegWeigh: Effective and Efficient Annotation Weighing with... code — Compare
ACE2005 (2 rows) DeepStruct multi-task w/ finetune DeepStruct: Pretraining of Language Models for Structure Prediction code Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
BC7 NLM-Chem (2 rows) PubMedBERT+MLP+CRF Chemical identification and indexing in PubMed full-text articles... code — Compare
CMeEE (2 rows) BERT-CRF (Replicated in AdaSeq) Improving Named Entity Recognition by External Context Retrieving... code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
DaNE (2 rows) saattrupdan/nbailab-base-ner-scandi — — — Compare
HiNER-collapsed (2 rows) cfilt/HiNER-collapsed-xlm-roberta-large HiNER: A Large Hindi Named Entity Recognition Dataset code — Compare
HiNER-original (2 rows) cfilt/HiNER-original-xlm-roberta-large HiNER: A Large Hindi Named Entity Recognition Dataset code — Compare
NEMO-Corpus (token,test) (2 rows) AlephBERT-base AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off... code Syntology community repositories only · 2 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; 2 where Syntology's instrument failed) · 0 unverified Compare
OntoNotes 5.0 (2 rows) HGN Hero-Gang Neural Model For Named Entity Recognition code — Compare
Species800 (2 rows) BLSTM-CNN-Char (SparkNLP) Biomedical Named Entity Recognition at Scale code — Compare
WLPC (2 rows) DyGIE A General Framework for Information Extraction using Dynamic Span Graphs code — Compare
NEMO-Corpus (1 row) AlephBERTGimmel-base MTL Large Pre-Trained Models with Extra-Large Vocabularies: A... — — Compare
UNER v1 (Danish) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 (English) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 (Croatian) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 (Portuguese) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 (Slovak) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 (Serbian) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 (Swedish) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 (Chinese) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 (Chinese Simplified) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 - PUD (English) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 - PUD (Portuguese) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 - PUD (Swedish) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
UNER v1 - PUD (Chinese) (1 row) UNER XML-R Universal NER: A Gold-Standard Multilingual Named Entity... code — Compare
WetLab (1 row) BiLSTM-CRF with ELMo Using Similarity Measures to Select Pretraining Data for NER code — Compare
Adverse Drug Events (ADE) Corpus (1 row) Spark NLP Mining Adverse Drug Reactions from Unstructured Mediums at Scale — — Compare
Broad Twitter Corpus (1 row) WORD_GAZ The Utility and Interplay of Gazetteers and Entity Segmentation... — — Compare
Code-Switching English-Spanish NER (1 row) HME (word + BPE + char) Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition code — Compare
CoNLL 2000 (1 row) SWEM-CRF Baseline Needs More Love: On Simple Word-Embedding-Based Models... code — Compare
French Treebank (1 row) CamemBERT (subword masking) CamemBERT: a Tasty French Language Model code — Compare
Gellus (1 row) ConNER Enhancing Label Consistency on Document-level Named Entity Recognition code — Compare
i2b2 De-identification Dataset (1 row) BiLSTM with ELMo MASK: A flexible framework to facilitate de-identification of... code — Compare
IECSIL FIRE-2018 Shared Task (1 row) XLM-RoBERTa Analysis Of Contextual and Non-Contextual Word Embedding Models... code — Compare
LegalNERo (1 row) Marcell Named Entity Recognition in the Romanian Legal Domain code — Compare
LeNER-Br (1 row) LSTM-CRF LeNER-Br: a Dataset for Named Entity Recognition in Brazilian Legal Text code — Compare
NCBI Disease (1 row) UniNER-7B UniversalNER: Targeted Distillation from Large Language Models for... code Syntology 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 Compare
SemEval 2022 - BanglaCoNER (1 row) POS Tagger, Prefix, Suffix, k-Neighbor Words, k-means clustering BanglaCoNER: Towards Robust Bangla Complex Named Entity Recognition code — Compare
SemEval 2022-2023 - BanglaCoNER (1 row) FT-Bangla BERT Large BanglaCoNER: Towards Robust Bangla Complex Named Entity Recognition code — Compare
SoSciSoCi (1 row) Bi-LSTM-CRF (SSC->GSC) Investigating Software Usage in the Social Sciences: A Knowledge... — — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

130 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 130 until expanded.

CoNLL 2003PubMedQAOntoNotes 5.0BC5CDRCoNLLFUNSDNCBI DiseaseSciERCBLUEWNUT 2017GENIACORDRadGraphFew-NERDWikiANNCoNLL 2002ACE 2005CoNLL++MasakhaNERACE 2004MedMentionsMultiCoNERFINIPM NELWikiCorefBioREDSLUEKLUELinCEJNLPBAXFUNDNNEWNUT 2016 NERDWIEGroningen Meaning BankIndicGLUECrossNERAdverse Drug Events (ADE) CorpusBC2GMGUMBroad Twitter CorpusEarnings-21NCBI DatasetsCMeEEPolyglot-NERGeoWebNews2018 n2c2 (Track 2) - Adverse Drug Events and Medication ExtractionBBCoNLL-2000PEYMAWinogender SchemasBC4CHEMDDaNElegal_NERMEDIANaamapadamPGRWikiNEuRalWNUT 2020AMALGUMDaN+Europeana NewspapersLINNAEUSSoMeSciSpecies-800FindVehicleFineri2b2 De-identification DatasetLegalNERoRONECBUSTERCORD-rCOVID-QDR.BENCHE-NERFUNSD-rKINDLeNER-BrNEMO-CorpusParsTwinerPhoNER COVID19ShARe/CLEF 2014: Task 2 DisordersThe QUAERO French Medical CorpusViMQBarNERBC7 NLM-ChemBiographicalChinese GigawordCLUENER2020CoNLL-2020Dataset of Legal DocumentsInLegalNERKazNERDMobIEPcMSPpioNERRare Diseases Mentions in MIMIC-IIISemClinBrTHYME-2016ArendtBaitBuster-Bangla: A Comprehensive Dataset for Clickbait Detection in Bangla with Multi-Feature and Multi-Modal AnalysisBusiness LicenseCareerCoach 2022Chem-FINESEChinese Literature NER REDiaKGESG-DLT-NERFinancial Language Understanding EvaluationFirst HAREMGSAP-NERHengamCorpusHiNER-collapsedHiNER-originalIECSIL FIRE-2018 Shared TaskLPSCMASCMedical Case Report CorpusMini HAREMMSNERScienceExamCERSturmSumeCzech-NERTASTEsetTwitter Cyberthreat Detection DatasetUNER v1VietMed-NERPOPCORNSecond HAREMSIGARRA News CorpusSTEM-ECR

Subtasks archive 2025-07-28

13 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 2,874 · with a code link: 955 · where Syntology ran a sample: 119 (97 with a run with no instrument failure, 22 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (119 of 2,874 tagged: 97 with a run with no instrument failure, 22 where every run was a failure of Syntology's instrument)

Page 1 of 29: papers 1 to 100 of 2,874, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 36 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections