Named Entity Recognition (NER)
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 )
Papers
Showing 1–10 of 2874 papers
All datasetsCoNLL 2003 (English)Ontonotes v5 (English)NCBI DiseaseWNUT 2017ACE 2005JNLPBABC5CDRGENIABC2GMBC5CDR-chemicalSLUECoNLL++
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | ACE + document-context | F1 | 94.6 | — | Unverified |
| 2 | LUKE 483M | F1 | 94.3 | — | Unverified |
| 3 | Co-regularized LUKE | F1 | 94.22 | — | Unverified |
| 4 | LUKE + SubRegWeigh (K-means) | F1 | 94.2 | — | Unverified |
| 5 | ASP+T5-3B | F1 | 94.1 | — | Unverified |
| 6 | FLERT XLM-R | F1 | 94.09 | — | Unverified |
| 7 | PL-Marker | F1 | 94 | — | Unverified |
| 8 | CL-KL | F1 | 93.85 | — | Unverified |
| 9 | XLNet-GCN | F1 | 93.82 | — | Unverified |
| 10 | RoBERTa + SubRegWeigh (K-means) | F1 | 93.81 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | BERT-MRC+DSC | F1 | 92.07 | — | Unverified |
| 2 | PL-Marker | F1 | 91.9 | — | Unverified |
| 3 | Baseline + BS | F1 | 91.74 | — | Unverified |
| 4 | Biaffine-NER | F1 | 91.3 | — | Unverified |
| 5 | BERT-MRC | F1 | 91.11 | — | Unverified |
| 6 | PIQN | F1 | 90.96 | — | Unverified |
| 7 | HGN | F1 | 90.92 | — | Unverified |
| 8 | Syn-LSTM + BERT (wo doc-context) | F1 | 90.85 | — | Unverified |
| 9 | DiffusionNER | F1 | 90.66 | — | Unverified |
| 10 | W2NER | F1 | 90.5 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | BioBERT | F1 | 89.71 | — | Unverified |
| 2 | SpanModel + SequenceLabelingModel | F1 | 89.6 | — | Unverified |
| 3 | SciFive-Base | F1 | 89.39 | — | Unverified |
| 4 | Spark NLP | F1 | 89.13 | — | Unverified |
| 5 | BLSTM-CNN-Char (SparkNLP) | F1 | 89.13 | — | Unverified |
| 6 | KeBioLM | F1 | 89.1 | — | Unverified |
| 7 | CL-KL | F1 | 88.96 | — | Unverified |
| 8 | BioKMNER + BioBERT | F1 | 88.77 | — | Unverified |
| 9 | BioLinkBERT (large) | F1 | 88.76 | — | Unverified |
| 10 | CompactBioBERT | F1 | 88.67 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | CL-KL | F1 | 60.45 | — | Unverified |
| 2 | RoBERTa + SubRegWeigh (K-means) | F1 | 60.29 | — | Unverified |
| 3 | BERT-CRF (Replicated in AdaSeq) | F1 | 59.69 | — | Unverified |
| 4 | RoBERTa-BiLSTM-context | F1 | 59.61 | — | Unverified |
| 5 | BERT + RegLER | F1 | 58.9 | — | Unverified |
| 6 | TNER -xlm-r-large | F1 | 58.5 | — | Unverified |
| 7 | HGN | F1 | 57.41 | — | Unverified |
| 8 | ASA + RoBERTa | F1 | 57.3 | — | Unverified |
| 9 | BERTweet | F1 | 56.5 | — | Unverified |
| 10 | MINER | F1 | 54.86 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Ours: cross-sentence ALB | F1 | 90.9 | — | Unverified |
| 2 | GoLLIE | F1 | 89.6 | — | Unverified |
| 3 | PromptNER [RoBERTa-large] | F1 | 88.26 | — | Unverified |
| 4 | PIQN | F1 | 87.42 | — | Unverified |
| 5 | PromptNER [BERT-large] | F1 | 87.21 | — | Unverified |
| 6 | DiffusionNER | F1 | 86.93 | — | Unverified |
| 7 | BERT-MRC | F1 | 86.88 | — | Unverified |
| 8 | UniNER-7B | F1 | 86.69 | — | Unverified |
| 9 | Locate and Label | F1 | 86.67 | — | Unverified |
| 10 | BoningKnife | F1 | 85.46 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | KeBioLM | F1 | 82 | — | Unverified |
| 2 | BLSTM-CNN-Char (SparkNLP) | F1 | 81.29 | — | Unverified |
| 3 | Spark NLP | F1 | 81.29 | — | Unverified |
| 4 | BINDER | F1 | 80.3 | — | Unverified |
| 5 | BioMobileBERT | F1 | 80.13 | — | Unverified |
| 6 | BioLinkBERT (large) | F1 | 80.06 | — | Unverified |
| 7 | DistilBioBERT | F1 | 79.97 | — | Unverified |
| 8 | CompactBioBERT | F1 | 79.88 | — | Unverified |
| 9 | BioDistilBERT | F1 | 79.1 | — | Unverified |
| 10 | PubMedBERT uncased | F1 | 79.1 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | BINDER | F1 | 91.9 | — | Unverified |
| 2 | ConNER | F1 | 91.3 | — | Unverified |
| 3 | CL-L2 | F1 | 90.99 | — | Unverified |
| 4 | aimped | F1 | 90.95 | — | Unverified |
| 5 | BertForTokenClassification (Spark NLP) | F1 | 90.89 | — | Unverified |
| 6 | BioLinkBERT (large) | F1 | 90.22 | — | Unverified |
| 7 | ELECTRAMed | F1 | 90.03 | — | Unverified |
| 8 | BLSTM-CNN-Char (SparkNLP) | F1 | 89.73 | — | Unverified |
| 9 | Spark NLP | F1 | 89.73 | — | Unverified |
| 10 | UniNER-7B | F1 | 89.34 | — | Unverified |