mlsanityData to 7 Oct 2026

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

arXiv 1909.07755 ↗First posted 17 Sep 2019cs.CL cs.LGcited by 132

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 132 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 26; 2023: 31; 2024: 25; 2025: 13; 2026: 11.

132 papers.

Sort:

By area:

  1. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  2. 2023Revisiting Relation Extraction in the era of Large Language Modelscited by 100
  3. 2022DeepStruct: Pretraining of Language Models for Structure Predictioncited by 45
  4. 2022Autoregressive Structured Prediction with Language Modelscited by 43
  5. 2021A Partition Filter Network for Joint Entity and Relation Extractioncited by 42
  6. 2021An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learningcited by 31
  7. 2021Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extractionwith Rich Syntactic Knowledgecited by 31
  8. 2022DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysiscited by 27
  9. 2021A Trigger-Sense Memory Flow Framework for Joint Entity and Relation Extractioncited by 26
  10. 2022Boundary Smoothing for Named Entity Recognitioncited by 21
  11. 2023A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontierscited by 21
  12. 2021Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inferencecited by 19
38 more
  1. 2022KPI-BERT: A Joint Named Entity Recognition and Relation Extraction Model for Financial Reportscited by 19
  2. 2021A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table Fillingcited by 16
  3. 2022Global Pointer: Novel Efficient Span-based Approach for Named Entity Recognitioncited by 15
  4. 2021A Simple but Effective Bidirectional Framework for Relational Triple Extractioncited by 14
  5. 2024Efficient Knowledge Infusion via KG-LLM Alignmentcited by 13
  6. 2023Distilling Large Language Models for Biomedical Knowledge Extraction: A Case Study on Adverse Drug Eventscited by 11
  7. 2023Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networkscited by 11
  8. 2025GLiREL -- Generalist Model for Zero-Shot Relation Extractioncited by 11
  9. 2025R1-RE: Cross-Domain Relation Extraction with RLVRcited by 11
  10. 2021Extracting Fine-Grained Knowledge Graphs of Scientific Claims: Dataset and Transformer-Based Resultscited by 10
  11. 2022Towards Relation Extraction From Speechcited by 10
  12. 2023Jointly Extracting Interventions, Outcomes, and Findings from RCT Reports with LLMscited by 10
  13. 2021Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learningcited by 9
  14. 2022KPI-EDGAR: A Novel Dataset and Accompanying Metric for Relation Extraction from Financial Documentscited by 9
  15. 2023On the Evolution of Knowledge Graphs: A Survey and Perspectivecited by 9
  16. 2021A Data Bootstrapping Recipe for Low Resource Multilingual Relation Classificationcited by 8
  17. 2023WebIE: Faithful and Robust Information Extraction on the Webcited by 8
  18. 2023Prompt-based Extraction of Social Determinants of Health Using Few-shot Learningcited by 8
  19. 2023BioREx: Improving Biomedical Relation Extraction by Leveraging Heterogeneous Datasetscited by 8
  20. 2021Improving Adverse Drug Event Extraction with SpanBERT on Different Text Typologiescited by 7
  21. 2022An Embarrassingly Easy but Strong Baseline for Nested Named Entity Recognitioncited by 7
  22. 2022Leveraging Natural Language Processing to Augment Structured Social Determinants of Health Data in the Electronic Health Recordcited by 7
  23. 2023FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extractioncited by 7
  24. 2024CHisIEC: An Information Extraction Corpus for Ancient Chinese Historycited by 7
  25. 2021HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extractioncited by 6
  26. 2023An Information Extraction Study: Take In Mind the Tokenization!cited by 6
  27. 2022AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First -- Using Relation Extraction to Identify Entitiescited by 5
  28. 2023DiffusionNER: Boundary Diffusion for Named Entity Recognitioncited by 5
  29. 2024An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extractioncited by 5
  30. 2024Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representationcited by 5
  31. 2025LOCORE: Image Re-ranking with Long-Context Sequence Modelingcited by 5
  32. 2025Event Extraction in Large Language Modelcited by 5
  33. 2022Extracting Medication Changes in Clinical Narratives using Pre-trained Language Modelscited by 4
  34. 2022Deep Span Representations for Named Entity Recognitioncited by 4
  35. 2023ReOnto: A Neuro-Symbolic Approach for Biomedical Relation Extractioncited by 4
  36. 2023Dynamic Multi-Scale Context Aggregation for Conversational Aspect-Based Sentiment Quadruple Analysiscited by 4
  37. 2024Extracting Social Determinants of Health from Pediatric Patient Notes Using Large Language Models: Novel Corpus and Methodscited by 4
  38. 2024A Benchmark Dataset with Larger Context for Non-Factoid Question Answering over Islamic Textcited by 4

50 most cited of 132 All 132 (JSON)