Papers › A sequence-to-sequence approach for document-level relation extraction

A sequence-to-sequence approach for document-level relation extraction

3 Apr 2022BioNLP (ACL) 2022 5arXiv:2204.01098archive 2025-07-28

John Giorgi, Gary D. Bader, Bo wang

Motivated by the fact that many relations cross the sentence boundary, there has been increasing interest in document-level relation extraction (DocRE). DocRE requires integrating information within and across sentences, capturing complex interactions between mentions of entities. Most existing methods are pipeline-based, requiring entities as input. However, jointly learning to extract entities and relations can improve performance and be more efficient due to shared parameters and training steps. In this paper, we develop a sequence-to-sequence approach, seq2rel, that can learn the subtasks of DocRE (entity extraction, coreference resolution and relation extraction) end-to-end, replacing a pipeline of task-specific components. Using a simple strategy we call entity hinting, we compare our approach to existing pipeline-based methods on several popular biomedical datasets, in some cases exceeding their performance. We also report the first end-to-end results on these datasets for future comparison. Finally, we demonstrate that, under our model, an end-to-end approach outperforms a pipeline-based approach. Our code, data and trained models are available at {\url{https://github.com/johngiorgi/seq2rel}}. An online demo is available at {\url{https://share.streamlit.io/johngiorgi/seq2rel/main/demo.py}}.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

johngiorgi/seq2rel officialmentioned in papermentioned on GitHub report

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

Coreference ResolutionDocument-level Relation ExtractionJoint Entity and Relation ExtractionRelation ExtractionSentencecoreference-resolution

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Joint Entity and Relation Extraction CDR seq2rel Relation F1 40.2 #1 of 1 Archive leaderboard report
Joint Entity and Relation Extraction DocRED seq2rel Relation F1 38.2 #6 of 6 Archive leaderboard report
Joint Entity and Relation Extraction GDA seq2rel Relation F1 55.2 #1 of 1 Archive leaderboard report
Relation Extraction CDR seq2rel (entity hinting) F1 67.2 #8 of 10 Archive leaderboard report
Relation Extraction GDA seq2rel (entity hinting) F1 84.9 #5 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLSTMLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSeq2SeqSigmoid ActivationSoftmaxTanh ActivationTransformer

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