mlsanityData to 14 Oct 2026

Matching the Blanks: Distributional Similarity for Relation Learning

arXiv 1906.03158 ↗First posted 7 Jun 2019cs.CL cs.AIcited by 272

Not on the map. Why?

Abstract (arXiv)

General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that represent relations with their surface forms, or which jointly embed surface forms with relations from an existing knowledge graph. However, both of these approaches are limited in their ability to generalize. In this paper, we build on extensions of Harris' distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. We show that these representations significantly outperform previous work on exemplar based relation extraction (FewRel) even without using any of that task's training data. We also show that models initialized with our task agnostic representations, and then tuned on supervised relation extraction datasets, significantly outperform the previous methods on SemEval 2010 Task 8, KBP37, and TACRED.

Key facts. Cited by 272 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 68; 2022: 90; 2023: 63; 2024: 33; 2025: 12; 2026: 6.

272 papers.

Sort:

By area:

  1. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  2. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 463
  3. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  4. 2021PTR: Prompt Tuning with Rules for Text Classificationcited by 238
  5. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  6. 2021KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extractioncited by 180
  7. 2021Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learnerscited by 115
  8. 2021KLUE: Korean Language Understanding Evaluationcited by 114
  9. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  10. 2021MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extractioncited by 83
  11. 2021An Improved Baseline for Sentence-level Relation Extractioncited by 81
  12. 2023LLMaAA: Making Large Language Models as Active Annotatorscited by 79
38 more
  1. 2021When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Datacited by 75
  2. 2021Re-TACRED: Addressing Shortcomings of the TACRED Datasetcited by 74
  3. 2022ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linkingcited by 74
  4. 2021Prompt-Learning for Fine-Grained Entity Typingcited by 62
  5. 2023GPT-RE: In-context Learning for Relation Extraction using Large Language Modelscited by 62
  6. 2023Empirical Study of Zero-Shot NER with ChatGPTcited by 60
  7. 2021Neural Data Augmentation via Example Extrapolationcited by 54
  8. 2021Packed Levitated Marker for Entity and Relation Extractioncited by 49
  9. 2022DeepStruct: Pretraining of Language Models for Structure Predictioncited by 45
  10. 2022Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completioncited by 44
  11. 2021Mention Memory: incorporating textual knowledge into Transformers through entity mention attentioncited by 43
  12. 2022Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillationcited by 39
  13. 2021CLEVE: Contrastive Pre-training for Event Extractioncited by 36
  14. 2021Learning Rich Representation of Keyphrases from Textcited by 36
  15. 2021Gradient Imitation Reinforcement Learning for Low Resource Relation Extractioncited by 33
  16. 2022UCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic Miningcited by 33
  17. 2022HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extractioncited by 32
  18. 2021Relational World Knowledge Representation in Contextual Language Models: A Reviewcited by 31
  19. 2021Relation Classification with Entity Type Restrictioncited by 31
  20. 2022Knowledge Base Question Answering by Case-based Reasoning over Subgraphscited by 31
  21. 2022Inducing Positive Perspectives with Text Reframingcited by 31
  22. 2022Summarization as Indirect Supervision for Relation Extractioncited by 31
  23. 2023How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?cited by 30
  24. 2022Consistent Representation Learning for Continual Relation Extractioncited by 28
  25. 2021Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemescited by 27
  26. 2021Discriminative Reasoning for Document-level Relation Extractioncited by 25
  27. 2022Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learningcited by 25
  28. 2021Exploring Task Difficulty for Few-Shot Relation Extractioncited by 24
  29. 2021NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task--Next Sentence Predictioncited by 23
  30. 2023The Life Cycle of Knowledge in Big Language Models: A Surveycited by 23
  31. 2021Zero-Shot Information Extraction as a Unified Text-to-Triple Translationcited by 22
  32. 2023A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontierscited by 22
  33. 2022CrossRE: A Cross-Domain Dataset for Relation Extractioncited by 21
  34. 2023Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuningcited by 21
  35. 2022ERGO: Event Relational Graph Transformer for Document-level Event Causality Identificationcited by 19
  36. 2021Reasoning Over Virtual Knowledge Bases With Open Predicate Relationscited by 18
  37. 2022Unified Semantic Typing with Meaningful Label Inferencecited by 18
  38. 2023Improved Logical Reasoning of Language Models via Differentiable Symbolic Programmingcited by 18

50 most cited of 272 All 272 (JSON)