mlsanityData to 7 Oct 2026

An Improved Baseline for Sentence-level Relation Extraction

arXiv 2102.01373 ↗First posted 2 Feb 2021cs.CLcited by 80

Not on the map. Why?

Abstract (arXiv)

Sentence-level relation extraction (RE) aims at identifying the relationship between two entities in a sentence. Many efforts have been devoted to this problem, while the best performing methods are still far from perfect. In this paper, we revisit two problems that affect the performance of existing RE models, namely entity representation and noisy or ill-defined labels. Our improved RE baseline, incorporated with entity representations with typed markers, achieves an F1 of 74.6% on TACRED, significantly outperforms previous SOTA methods. Furthermore, the presented new baseline achieves an F1 of 91.1% on the refined Re-TACRED dataset, demonstrating that the pretrained language models (PLMs) achieve high performance on this task. We release our code to the community for future research.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). Builds on 24 of its 39 references that are in the map. First posted on arXiv 2 Feb 2021.

Builds on

24 of 39 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  7. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  8. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  10. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  11. 2015Towards Open Set Deep Networkscited by 533
  12. 2019ERNIE: Enhanced Language Representation with Informative Entitiescited by 525
12 more
  1. 2020LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentioncited by 326
  2. 2020K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapterscited by 318
  3. 2019Knowledge Enhanced Contextual Word Representationscited by 294
  4. 2019Matching the Blanks: Distributional Similarity for Relation Learningcited by 271
  5. 2018Reducing Network Agnostophobiacited by 165
  6. 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
  7. 2018Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifierscited by 126
  8. 2020Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Poolingcited by 115
  9. 2020TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Taskcited by 96
  10. 2020Learning from Context or Names? An Empirical Study on Neural Relation Extractioncited by 75
  11. 2020A Frustratingly Easy Approach for Entity and Relation Extractioncited by 37
  12. 2019Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extractioncited by 36

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 27; 2023: 23; 2024: 14; 2025: 7; 2026: 1.

80 papers.

Sort:

By area:

  1. 2021PTR: Prompt Tuning with Rules for Text Classificationcited by 238
  2. 2021KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extractioncited by 180
  3. 2023Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulnesscited by 130
  4. 2023Context-faithful Prompting for Large Language Modelscited by 76
  5. 2023Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Textcited by 59
  6. 2022Revisiting DocRED -- Addressing the False Negative Problem in Relation Extractioncited by 57
  7. 2021Packed Levitated Marker for Entity and Relation Extractioncited by 49
  8. 2021Learning Rich Representation of Keyphrases from Textcited by 36
  9. 2022Summarization as Indirect Supervision for Relation Extractioncited by 31
  10. 2022Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysiscited by 30
  11. 2023How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?cited by 30
  12. 2023Revisiting Large Language Models as Zero-shot Relation Extractorscited by 29
38 more
  1. 2023Primacy Effect of ChatGPTcited by 27
  2. 2022A sequence-to-sequence approach for document-level relation extractioncited by 25
  3. 2022Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learningcited by 25
  4. 2023A Causal View of Entity Bias in (Large) Language Modelscited by 21
  5. 2022A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processingcited by 20
  6. 2022Unified Semantic Typing with Meaningful Label Inferencecited by 18
  7. 2022Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typingcited by 16
  8. 2022TAGPRIME: A Unified Framework for Relational Structure Extractioncited by 15
  9. 2022Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extractioncited by 15
  10. 2022Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuningcited by 13
  11. 2022Generative Prompt Tuning for Relation Classificationcited by 13
  12. 2022Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?cited by 13
  13. 2022Multi-hop Evidence Retrieval for Cross-document Relation Extractioncited by 13
  14. 2022NEREL-BIO: A Dataset of Biomedical Abstracts Annotated with Nested Named Entitiescited by 10
  15. 2022Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extractioncited by 10
  16. 2022Sequence Generation with Label Augmentation for Relation Extractioncited by 9
  17. 2024Retrieval-Augmented Generation-based Relation Extractioncited by 9
  18. 2024On Evaluating Explanation Utility for Human-AI Decision Making in NLPcited by 9
  19. 2021Improving Sentence-Level Relation Extraction through Curriculum Learningcited by 8
  20. 2022Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extractioncited by 7
  21. 2023Think Rationally about What You See: Continuous Rationale Extraction for Relation Extractioncited by 6
  22. 2024Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classificationcited by 6
  23. 2024Recall, Retrieve and Reason: Towards Better In-Context Relation Extractioncited by 6
  24. 2024Relation Extraction with Fine-Tuned Large Language Models in Retrieval Augmented Generation Frameworkscited by 6
  25. 2022Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Studycited by 5
  26. 2023MultiTACRED: A Multilingual Version of the TAC Relation Extraction Datasetcited by 5
  27. 2023How Fragile is Relation Extraction under Entity Replacements?cited by 5
  28. 2022Beyond modeling: NLP Pipeline for efficient environmental policy analysiscited by 4
  29. 2022Not Just Plain Text! Fuel Document-Level Relation Extraction with Explicit Syntax Refinement and Subsentence Modelingcited by 4
  30. 2023Rethinking Document-Level Relation Extraction: A Reality Checkcited by 4
  31. 2023Chain-of-Thought Tuning: Masked Language Models can also Think Step By Step in Natural Language Understandingcited by 4
  32. 2021TREND: Trigger-Enhanced Relation-Extraction Network for Dialoguescited by 3
  33. 2022Improving Distantly Supervised Relation Extraction by Natural Language Inferencecited by 3
  34. 2023Dense Retrieval as Indirect Supervision for Large-space Decision Makingcited by 3
  35. 2023Enhancing Low-Resource Relation Representations through Multi-View Decouplingcited by 3
  36. 2025Bridging Generative and Discriminative Learning: Few-Shot Relation Extraction via Two-Stage Knowledge-Guided Pre-trainingcited by 3
  37. 2022GRAPHCACHE: Message Passing as Caching for Sentence-Level Relation Extractioncited by 2
  38. 2022Continual Contrastive Finetuning Improves Low-Resource Relation Extractioncited by 2

50 most cited of 80 All 80 (JSON)