mlsanityData to 14 Oct 2026

Relation Classification with Entity Type Restriction

arXiv 2105.08393 ↗First posted 18 May 2021cs.CLcited by 31

Not on the map. Why?

Abstract (arXiv)

Relation classification aims to predict a relation between two entities in a sentence. The existing methods regard all relations as the candidate relations for the two entities in a sentence. These methods neglect the restrictions on candidate relations by entity types, which leads to some inappropriate relations being candidate relations. In this paper, we propose a novel paradigm, RElation Classification with ENtity Type restriction (RECENT), which exploits entity types to restrict candidate relations. Specially, the mutual restrictions of relations and entity types are formalized and introduced into relation classification. Besides, the proposed paradigm, RECENT, is model-agnostic. Based on two representative models GCN and SpanBERT respectively, RECENT_GCN and RECENT_SpanBERT are trained in RECENT. Experimental results on a standard dataset indicate that RECENT improves the performance of GCN and SpanBERT by 6.9 and 4.4 F1 points, respectively. Especially, RECENT_SpanBERT achieves a new state-of-the-art on TACRED.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 12 of its 19 references that are in the map. First posted on arXiv 18 May 2021.

Builds on

12 of 19 references.

References · 12

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  3. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 834
  4. 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
  5. 2020LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentioncited by 326
  6. 2020K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapterscited by 319
  7. 2019Knowledge Enhanced Contextual Word Representationscited by 296
  8. 2019Matching the Blanks: Distributional Similarity for Relation Learningcited by 272
  9. 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
  10. 2019Attention Guided Graph Convolutional Networks for Relation Extractioncited by 82
  11. 2020Improved Natural Language Generation via Loss Truncationcited by 75
  12. 2020Relation Classification as Two-way Span-Predictioncited by 9

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 14; 2023: 8; 2024: 5; 2025: 2.

31 papers.

Sort:

  1. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  2. 2022GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Recordscited by 238
  3. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 90
  4. 2022Summarization as Indirect Supervision for Relation Extractioncited by 31
  5. 2022Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysiscited by 30
  6. 2023How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?cited by 30
  7. 2022Unified Semantic Typing with Meaningful Label Inferencecited by 18
  8. 2022TAGPRIME: A Unified Framework for Relational Structure Extractioncited by 15
  9. 2022Generative Prompt Tuning for Relation Classificationcited by 13
  10. 2022Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extractioncited by 10
  11. 2021Improving Sentence-Level Relation Extraction through Curriculum Learningcited by 8
  12. 2022Why only Micro-F1? Class Weighting of Measures for Relation Classificationcited by 8
19 more
  1. 2022Multilingual Relation Classification via Efficient and Effective Promptingcited by 7
  2. 2024FCDS: Fusing Constituency and Dependency Syntax into Document-Level Relation Extractioncited by 5
  3. 2024GAMedX: Generative AI-based Medical Entity Data Extractor Using Large Language Modelscited by 5
  4. 2022Not Just Plain Text! Fuel Document-Level Relation Extraction with Explicit Syntax Refinement and Subsentence Modelingcited by 4
  5. 2022REKnow: Enhanced Knowledge for Joint Entity and Relation Extractioncited by 3
  6. 2024On the use of Silver Standard Data for Zero-shot Classification Tasks in Information Extractioncited by 3
  7. 2021Do Models Learn the Directionality of Relations? A New Evaluation: Relation Direction Recognitioncited by 2
  8. 2022GRAPHCACHE: Message Passing as Caching for Sentence-Level Relation Extractioncited by 2
  9. 2022Continual Contrastive Finetuning Improves Low-Resource Relation Extractioncited by 2
  10. 2023CORE: A Few-Shot Company Relation Classification Dataset for Robust Domain Adaptationcited by 2
  11. 2023LabelPrompt: Effective Prompt-based Learning for Relation Classificationcited by 1
  12. 2023Sentence-Level Relation Extraction via Contrastive Learning with Descriptive Relation Promptscited by 1
  13. 2023About Evaluation of F1 Score for RECENT Relation Extraction Systemcited by 1
  14. 2025COMM:Concentrated Margin Maximization for Robust Document-Level Relation Extractioncited by 1
  15. 2022Learning with Silver Standard Data for Zero-shot Relation Extractioncited by 0
  16. 2023A Few-Shot Learning Focused Survey on Recent Named Entity Recognition and Relation Classification Methodscited by 0
  17. 2024A Two Dimensional Feature Engineering Method for Relation Extractioncited by 0
  18. 2024Empowering Few-Shot Relation Extraction with The Integration of Traditional RE Methods and Large Language Modelscited by 0
  19. 2025CPTuning: Contrastive Prompt Tuning for Generative Relation Extractioncited by 0