Papers › Span-based Joint Entity and Relation Extraction with Transformer Pre-training

Span-based Joint Entity and Relation Extraction with Transformer Pre-training

17 Sep 2019arXiv:1909.07755archive 2025-07-28

Markus Eberts, Adrian Ulges

We introduce SpERT, an attention model for span-based joint entity and relation extraction. Our key contribution is a light-weight reasoning on BERT embeddings, which features entity recognition and filtering, as well as relation classification with a localized, marker-free context representation. The model is trained using strong within-sentence negative samples, which are efficiently extracted in a single BERT pass. These aspects facilitate a search over all spans in the sentence. In ablation studies, we demonstrate the benefits of pre-training, strong negative sampling and localized context. Our model outperforms prior work by up to 2.6% F1 score on several datasets for joint entity and relation extraction.

PaperPDFCode

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

Code

markus-eberts/spert officialmentioned in papermentioned on GitHubpytorch report
lavis-nlp/spert mentioned on GitHubpytorchMIT 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

Joint Entity and Relation ExtractionNamed Entity Recognition (NER)Relation ClassificationRelation ExtractionSentence

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 SciERC SpERT (with overlap) Cross Sentence No #4 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC SpERT (with overlap) Entity F1 70.3 #4 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC SpERT (with overlap) Relation F1 50.84 #4 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC SpERT Cross Sentence No #9 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC SpERT Entity F1 70.33 #9 of 11 Archive leaderboard report
Named Entity Recognition (NER) SciERC SpERT F1 70.33 #2 of 7 Archive leaderboard report
Relation Extraction Adverse Drug Events (ADE) Corpus SpERT (without overlap) NER Macro F1 89.25 #11 of 15 Archive leaderboard report
Relation Extraction Adverse Drug Events (ADE) Corpus SpERT (without overlap) RE+ Macro F1 79.24 #11 of 15 Archive leaderboard report
Relation Extraction Adverse Drug Events (ADE) Corpus SpERT (with overlap) NER Macro F1 89.28 #12 of 15 Archive leaderboard report
Relation Extraction Adverse Drug Events (ADE) Corpus SpERT (with overlap) RE+ Macro F1 78.84 #12 of 15 Archive leaderboard report
Relation Extraction CoNLL04 SpERT NER Macro F1 86.25 #3 of 16 Archive leaderboard report
Relation Extraction CoNLL04 SpERT NER Micro F1 88.94 #3 of 16 Archive leaderboard report
Relation Extraction CoNLL04 SpERT RE+ Macro F1 72.87 #3 of 16 Archive leaderboard report
Relation Extraction CoNLL04 SpERT RE+ Micro F1 71.47 #3 of 16 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

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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