Named Entity Recognition

639 papers with code • 62 benchmarks • 94 datasets

Named entity recognition (NER) is the task of tagging entities in text with their corresponding type. 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 )

Benchmarks

Add a Result

These leaderboards are used to track progress in Named Entity Recognition

Dataset	Best Model	Compare
CoNLL 2003 (English)	ACE + document-context	See all
Ontonotes v5 (English)	BERT-MRC+DSC	See all
NCBI-disease	Spark NLP	See all
WNUT 2017	CL-KL	See all
ACE 2005	Ours: cross-sentence ALB	See all
BC5CDR	CL-L2	See all
SLUE	W2V2-L-LL60K (pipeline approach, uses LM)	See all
JNLPBA	KeBioLM	See all
GENIA	Biaffine-NER	See all
ACE 2004	Ours: cross-sentence ALB	See all
CoNLL++	Noise-robust Co-regularization + LUKE	See all
BC5CDR-chemical	Spark NLP	See all
SciERC	SpERT	See all
CoNLL 2003 (German)	ACE + document-context	See all
CoNLL 2002 (Spanish)	ACE + document-context	See all
CoNLL 2002 (Dutch)	ACE + document-context	See all
BC5CDR-disease	BioMegatron	See all
WNUT 2016	HGN	See all
CoNLL 2003 (German) Revised	FLERT XLM-R	See all
BC2GM	Spark NLP	See all
Few-NERD (SUP)	PL-Marker	See all
Species-800	SciFive-Base	See all
LINNAEUS	BLSTM-CNN-Char (SparkNLP)	See all
BC4CHEMD	Att-BiLSTM-CRF	See all
NEMO-Corpus (morph,test)	AlephBERT-base Pipeline	See all
WNUT 2020	mgsohrab	See all
WLPC	DyGIE	See all
Species800	BLSTM-CNN-Char (SparkNLP)	See all
AnatEM	BLSTM-CNN-Char (SparkNLP)	See all
BioNLP13-CG	BLSTM-CNN-Char (SparkNLP)	See all
NEMO-Corpus (token,test)	AlephBERT-base	See all
DWIE	KB-both	See all
DaNE	saattrupdan/nbailab-base-ner-scandi	See all
HiNER-original	cfilt/HiNER-original-xlm-roberta-large	See all
HiNER-collapsed	cfilt/HiNER-collapsed-xlm-roberta-large	See all
BC7 NLM-Chem	PubMedBERT+MLP+CRF	See all
MasakhaNER	BERT	See all
WetLab	BiLSTM-CRF with ELMo	See all
Code-Switching English-Spanish NER	HME (word + BPE + char)	See all
CoNLL 2000	SWEM-CRF	See all
French Treebank	CamemBERT (subword masking)	See all
SoSciSoCi	Bi-LSTM-CRF (SSC->GSC)	See all
LeNER-Br	LSTM-CRF	See all
CMeEE	MacBERT-large	See all
IECSIL FIRE-2018 Shared Task	XLM-RoBERTa	See all
LegalNERo	Marcell	See all
WikiNEuRal English	BERT+Bi-LSTM+CRF	See all
WikiNEuRal Italian	BERT+Bi-LSTM+CRF	See all
WikiNEuRal German	BERT+Bi-LSTM+CRF	See all
WikiNEuRal Spanish	BERT+Bi-LSTM+CRF	See all
WikiNEuRal Dutch	BERT+Bi-LSTM+CRF	See all
WikiNEuRal French	BERT+Bi-LSTM+CRF	See all
WikiNEuRal Portuguese	BERT+Bi-LSTM+CRF	See all
WikiNEuRal Polish	BERT+Bi-LSTM+CRF	See all
WikiNEuRal Russian	BERT+Bi-LSTM+CRF	See all
Adverse Drug Events (ADE) Corpus	Spark NLP	See all
i2b2 De-identification Dataset	BiLSTM with ELMo	See all
Broad Twitter Corpus	WORD_GAZ	See all
OntoNotes 5.0	HGN	See all

Show all 62 benchmarks

Collapse benchmarks

Libraries

Use these libraries to find Named Entity Recognition models and implementations

flairNLP/flair

6 papers

11,910

huggingface/transformers

4 papers

67,953

dmlc/gluon-nlp

3 papers

2,431

l3cube-pune/MarathiNLP

3 papers

See all 6 libraries.

Datasets

Subtasks

Few-shot NER

Medical Named Entity Recognition

Multilingual Named Entity Recognition

Cross-Domain Named Entity Recognition

Named Entity Recognition In Vietnamese

Scientific Concept Extraction

Multi-Grained Named Entity Recognition

Most implemented papers

Most implemented Social Latest No code

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

google-research/bert • • NAACL 2019

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.

488

Paper
Code

Neural Architectures for Named Entity Recognition

glample/tagger • NAACL 2016

State-of-the-art named entity recognition systems rely heavily on hand-crafted features and domain-specific knowledge in order to learn effectively from the small, supervised training corpora that are available.

Paper
Code

Deep contextualized word representations

flairNLP/flair • • NAACL 2018

We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e. g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i. e., to model polysemy).

Paper
Code

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

guillaumegenthial/sequence_tagging • • ACL 2016

State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing.

Paper
Code

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

dmis-lab/biobert • • 25 Jan 2019

Biomedical text mining is becoming increasingly important as the number of biomedical documents rapidly grows.

Paper
Code

Named Entity Recognition with Bidirectional LSTM-CNNs

zalandoresearch/flair • • TACL 2016

Named entity recognition is a challenging task that has traditionally required large amounts of knowledge in the form of feature engineering and lexicons to achieve high performance.

Paper
Code