Papers › REBEL: Relation Extraction By End-to-end Language generation

REBEL: Relation Extraction By End-to-end Language generation

29 Oct 2021Findings (EMNLP) 2021 11archive 2025-07-28

Pere-Lluis Huguet Cabot, Roberto Navigli

Extracting relation triplets from raw text is a crucial task in Information Extraction, enabling multiple applications such as populating or validating knowledge bases, factchecking, and other downstream tasks. However, it usually involves multiple-step pipelines that propagate errors or are limited to a small number of relation types. To overcome these issues, we propose the use of autoregressive seq2seq models. Such models have previously been shown to perform well not only in language generation, but also in NLU tasks such as Entity Linking, thanks to their framing as seq2seq tasks. In this paper, we show how Relation Extraction can be simplified by expressing triplets as a sequence of text and we present REBEL, a seq2seq model based on BART that performs end-to-end relation extraction for more than 200 different relation types. We show our model's flexibility by fine-tuning it on an array of Relation Extraction and Relation Classification benchmarks, with it attaining state-of-the-art performance in most of them.

PaperPDFConference PDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Entity LinkingJoint Entity and Relation ExtractionRelation ClassificationRelation ExtractionText Generation

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

REBEL

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Joint Entity and Relation Extraction DocRED REBEL+pretraining Relation F1 47.1 #1 of 6 Archive leaderboard report
Joint Entity and Relation Extraction DocRED REBEL Relation F1 41.8 #2 of 6 Archive leaderboard report
Relation Extraction Adverse Drug Events (ADE) Corpus REBEL (including overlapping entities) RE+ Macro F1 82.2 #6 of 15 Archive leaderboard report
Relation Extraction CoNLL04 REBEL RE+ Macro F1 76.65 #1 of 16 Archive leaderboard report
Relation Extraction CoNLL04 REBEL RE+ Micro F1 75.4 #1 of 16 Archive leaderboard report
Relation Extraction NYT REBEL (no pre-training) F1 93.1 #5 of 8 Archive leaderboard report
Relation Extraction Re-TACRED REBEL (no entity type marker) F1 90.4 #4 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionBARTBPEDense ConnectionsDropoutLSTMLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSeq2SeqSigmoid ActivationSoftmaxTanh Activation

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