Datasets › CoNLL04

CoNLL04

archive 2025-07-28

The CoNLL04 dataset is a benchmark dataset used for relation extraction tasks. It contains 1,437 sentences, each of which has at least one relation. The sentences are annotated with information about entities and their corresponding relation types.

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

		First row (archive order)	Paper	Code
Relation Extraction	CoNLL04	REBEL RE+ Macro F1 76.65	REBEL: Relation Extraction By End-to-end Language generation	Babelscape/rebel	16	Compare
Joint Entity and Relation Extraction	CoNLL04	DeepStruct multi-task w/ finetune Entity F1 90.7	DeepStruct: Pretraining of Language Models for Structure...	cgraywang/deepstruct	3	Compare
Cross-Domain Named Entity Recognition	CoNLL04	BiLSTM w/ MTL and MoEE F1 70.04	Zero-Resource Cross-Domain Named Entity Recognition	Siddharthss500/zero-resource	1	Compare

Papers archive 2025-07-28

18 shown of 18 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 19. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
ReLiK: Retrieve and LinK, Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget	2	1	31 Jul 2024	not harvested
Autoregressive Structured Prediction with Language Models	1	1	26 Oct 2022	not harvested
DeepStruct: Pretraining of Language Models for Structure Prediction	1	3	21 May 2022	ran 7 of 13 samples (6 unverified)
REBEL: Relation Extraction By End-to-end Language generation	1	1	29 Oct 2021	not harvested
A Trigger-Sense Memory Flow Framework for Joint Entity and Relation Extraction	1	1	25 Jan 2021	not harvested
Structured Prediction as Translation between Augmented Natural Languages	2	1	14 Jan 2021	not harvested
Named Entity Recognition and Relation Extraction using Enhanced Table Filling by Contextualized Representations	1	1	15 Oct 2020	not harvested
Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders	2	1	8 Oct 2020	ran 0 of 3 samples (3 unverified; 3 pointer-only for licence)
Deeper Task-Specificity Improves Joint Entity and Relation Extraction	1	1	15 Feb 2020	not harvested
Zero-Resource Cross-Domain Named Entity Recognition	1	1	14 Feb 2020	not harvested
Span-based Joint Entity and Relation Extraction with Transformer Pre-training	3	1	17 Sep 2019	not harvested
Neural Metric Learning for Fast End-to-End Relation Extraction	0	1	17 May 2019	not harvested
Entity-Relation Extraction as Multi-Turn Question Answering	1	1	14 May 2019	not harvested
End-to-end neural relation extraction using deep biaffine attention	1	1	29 Dec 2018	not harvested
Adversarial training for multi-context joint entity and relation extraction	1	1	21 Aug 2018	not harvested
Joint entity recognition and relation extraction as a multi-head selection problem	6	1	20 Apr 2018	not harvested
End-to-End Neural Relation Extraction with Global Optimization	0	1	1 Sep 2017	not harvested
Modeling Joint Entity and Relation Extraction with Table Representation	0	1	1 Oct 2014	not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Relation Extraction Joint Entity and Relation Extraction Cross-Domain Named Entity Recognition

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

CoNLL04

1 variant name, as the archive lists them.

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