AI Paper Atlas

Research map / Benchmarks / CoNLL-2003

CoNLL-2003 leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CoNLL-2003. Best F1: 95.4 (TA-VAT, AAAI 2021).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CoNLL-2003 · F1

14 papers, each with its best reported number for its own method; higher is better.

#F1 ↑MethodPaperTopic
195.4TA-VAT
BERT
Token-Aware Virtual Adversarial Training in Natural Language Understanding
AAAI 2021 · Table 3
Attacks on text and graphs
294.04SGT
RoBERTa-base
Span Graph Transformer for Document-Level Named Entity Recognition
AAAI 2024 · Table 2
Knowledge and temporal graphs
393.42Our Model
BERT
Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition
ICLR 2021 · Table 2
Recognition and long-tail
493.37Hierarchical Contextualized Representation + BERT
Hierarchical Contextualized Representation
Hierarchical Contextualized Representation for Named Entity Recognition
AAAI 2020 · CoNLL-2003 results table
Recognition and long-tail
593.09MEID
flair
Leveraging Multi-Token Entities in Document-Level Named Entity Recognition
AAAI 2020 · Table 3
Recognition and long-tail
693.07W²NER
BERT
Unified Named Entity Recognition as Word-Word Relation Classification
AAAI 2022 · Table 2
Recognition and long-tail
791.8KAWR+BiLSTM+CRF
BERT
Knowledge-Graph Augmented Word Representations for Named Entity Recognition
AAAI 2020 · Table 3
Knowledge and temporal graphs
891.77ELECTRA_base + AD-Drop
ELECTRA_base
AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning
NeurIPS 2022 · Appendix Table: CoNLL-2003
Pruning and efficient tuning
991.56LSTM with dynamic skip
LSTM
Long Short-Term Memory with Dynamic Skip Connections
AAAI 2019 · Table 1
RNNs and normalization
1091.44GRNGRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition
AAAI 2019 · Table 2
RNNs and normalization
4 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.