Named Entity Recognition

Edit

428 papers with code • 37 benchmarks • 62 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

Dataset	Best Model	Paper Title	Compare
CoNLL 2003 (English)	ACE + document-context	Automated Concatenation of Embeddings for Structured Prediction	See all
Ontonotes v5 (English)	BERT-MRC+DSC	Dice Loss for Data-imbalanced NLP Tasks	See all
WNUT 2017	CL-KL	Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning	See all
NCBI-disease	BioBERT	BioBERT: a pre-trained biomedical language representation model for biomedical text mining	See all
ACE 2005	Ours: cross-sentence ALB	A Frustratingly Easy Approach for Entity and Relation Extraction	See all
BC5CDR	CL-L2	Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning	See all
GENIA	Biaffine-NER	Named Entity Recognition as Dependency Parsing	See all
JNLPBA	KeBioLM	Improving Biomedical Pretrained Language Models with Knowledge	See all
SciERC	SpERT	Span-based Joint Entity and Relation Extraction with Transformer Pre-training	See all
ACE 2004	Ours: cross-sentence ALB	A Frustratingly Easy Approach for Entity and Relation Extraction	See all
CoNLL++	CL-KL	Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning	See all
CoNLL 2003 (German)	ACE + document-context	Automated Concatenation of Embeddings for Structured Prediction	See all
CoNLL 2002 (Spanish)	ACE + document-context	Automated Concatenation of Embeddings for Structured Prediction	See all
CoNLL 2002 (Dutch)	ACE + document-context	Automated Concatenation of Embeddings for Structured Prediction	See all
BC5CDR-chemical	SciFive-Large	SciFive: a text-to-text transformer model for biomedical literature	See all
WNUT 2016	CL-KL	Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning	See all
CoNLL 2003 (German) Revised	ACE + document-context	Automated Concatenation of Embeddings for Structured Prediction	See all
BC5CDR-disease	BioMegatron	BioMegatron: Larger Biomedical Domain Language Model	See all
LINNAEUS	BLSTM-CNN-Char (SparkNLP)	Biomedical Named Entity Recognition at Scale	See all
NEMO-Corpus (morph,test)	AlephBERT-base Pipeline	AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With	See all
WNUT 2020	mgsohrab	mgsohrab at WNUT 2020 Shared Task-1: Neural Exhaustive Approach for Entity and Relation Recognition Over Wet Lab Protocols	See all
Species-800	SciFive-Base	SciFive: a text-to-text transformer model for biomedical literature	See all
WLPC	DyGIE	A General Framework for Information Extraction using Dynamic Span Graphs	See all
BC4CHEMD	Att-BiLSTM-CRF	An attention-based BiLSTM-CRF approach to document-level chemical named entity recognition	See all
BC2GM	KeBioLM	Improving Biomedical Pretrained Language Models with Knowledge	See all
NEMO-Corpus (token,test)	AlephBERT-base	AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With	See all
WetLab	BiLSTM-CRF with ELMo	Using Similarity Measures to Select Pretraining Data for NER	See all
Code-Switching English-Spanish NER	HME (word + BPE + char)	Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition	See all
CoNLL 2000	SWEM-CRF	Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms	See all
French Treebank	CamemBERT (subword masking)	CamemBERT: a Tasty French Language Model	See all
SoSciSoCi	Bi-LSTM-CRF (SSC->GSC)	Investigating Software Usage in the Social Sciences: A Knowledge Graph Approach	See all
LeNER-Br	LSTM-CRF	LeNER-Br: a Dataset for Named Entity Recognition in Brazilian Legal Text	See all
Species800	BLSTM-CNN-Char (SparkNLP)	Biomedical Named Entity Recognition at Scale	See all
AnatEM	BLSTM-CNN-Char (SparkNLP)	Biomedical Named Entity Recognition at Scale	See all
BioNLP13-CG	BLSTM-CNN-Char (SparkNLP)	Biomedical Named Entity Recognition at Scale	See all
Few-NERD (SUP)	BERT-Tagger	Few-NERD: A Few-Shot Named Entity Recognition Dataset	See all
CMeEE	MacBERT-large	CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark	See all

Show all 37 benchmarks

Collapse benchmarks

Datasets

Subtasks

Cross-Domain Named Entity Recognition

Named Entity Recognition In Vietnamese

Few-shot NER

Multi-Grained Named Entity Recognition

Scientific Concept Extraction

Greatest papers with code

Semi-Supervised Sequence Modeling with Cross-View Training

tensorflow/models • • EMNLP 2018

We therefore propose Cross-View Training (CVT), a semi-supervised learning algorithm that improves the representations of a Bi-LSTM sentence encoder using a mix of labeled and unlabeled data.

Ranked #1 on CCG Supertagging on CCGbank

CCG Supertagging Dependency Parsing +5

70,757

Paper
Code

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

tensorflow/models • • NAACL 2019

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

Ranked #1 on Question Answering on CoQA

Common Sense Reasoning Conversational Response Selection +6

70,754

Paper
Code

DeBERTa: Decoding-enhanced BERT with Disentangled Attention

huggingface/transformers • • ICLR 2021

Recent progress in pre-trained neural language models has significantly improved the performance of many natural language processing (NLP) tasks.

Ranked #1 on Question Answering on Quora Question Pairs

Common Sense Reasoning Coreference Resolution +9

48,998

Paper
Code

CamemBERT: a Tasty French Language Model

huggingface/transformers • • ACL 2020

We show that the use of web crawled data is preferable to the use of Wikipedia data.

Ranked #1 on Dependency Parsing on Spoken Corpus

Dependency Parsing Language Modelling +3

48,998

Paper
Code

FLERT: Document-Level Features for Named Entity Recognition

zalandoresearch/flair • • 13 Nov 2020

Current state-of-the-art approaches for named entity recognition (NER) typically consider text at the sentence-level and thus do not model information that crosses sentence boundaries.

Named Entity Recognition

10,616

Paper
Code

Pooled Contextualized Embeddings for Named Entity Recognition

zalandoresearch/flair • • NAACL 2019

We make all code and pre-trained models available to the research community for use and reproduction.

Ranked #16 on Named Entity Recognition on CoNLL 2003 (English) (using extra training data)

Named Entity Recognition NER

10,616

Paper
Code

FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP

zalandoresearch/flair • • NAACL 2019

We present FLAIR, an NLP framework designed to facilitate training and distribution of state-of-the-art sequence labeling, text classification and language models.

Chunking Named Entity Recognition +1

10,616

Paper
Code

Contextual String Embeddings for Sequence Labeling

zalandoresearch/flair • • COLING 2018

Recent advances in language modeling using recurrent neural networks have made it viable to model language as distributions over characters.

Ranked #2 on Part-Of-Speech Tagging on Penn Treebank

Chunking Language Modelling +3

10,616

Paper
Code

Deep contextualized word representations

zalandoresearch/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).

Ranked #2 on Citation Intent Classification on ACL-ARC (using extra training data)