mlsanityData to 14 Oct 2026

Type-enriched Hierarchical Contrastive Strategy for Fine-Grained Entity Typing

arXiv 2208.10081 ↗First posted 22 Aug 2022cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Fine-grained entity typing (FET) aims to deduce specific semantic types of the entity mentions in text. Modern methods for FET mainly focus on learning what a certain type looks like. And few works directly model the type differences, that is, let models know the extent that one type is different from others. To alleviate this problem, we propose a type-enriched hierarchical contrastive strategy for FET. Our method can directly model the differences between hierarchical types and improve the ability to distinguish multi-grained similar types. On the one hand, we embed type into entity contexts to make type information directly perceptible. On the other hand, we design a constrained contrastive strategy on the hierarchical structure to directly model the type differences, which can simultaneously perceive the distinguishability between types at different granularity. Experimental results on three benchmarks, BBN, OntoNotes, and FIGER show that our method achieves significant performance on FET by effectively modeling type differences.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 42 of its 67 references that are in the map. First posted on arXiv 22 Aug 2022.

Builds on

42 of 67 references.

References · 42

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  7. 2019Language Models as Knowledge Bases?cited by 1,936
  8. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  9. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  10. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 938
  11. 2021GPT Understands, Toocited by 716
  12. 2018A Simple Method for Commonsense Reasoningcited by 223
30 more
  1. 2019Commonsense Knowledge Mining from Pretrained Modelscited by 189
  2. 2020CERT: Contrastive Self-supervised Learning for Language Understandingcited by 169
  3. 2021SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarizationcited by 132
  4. 2021Supporting Clustering with Contrastive Learningcited by 90
  5. 2018Ultra-Fine Entity Typingcited by 87
  6. 2021Prompt-Learning for Fine-Grained Entity Typingcited by 62
  7. 2021Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classificationcited by 43
  8. 2021Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Modelcited by 39
  9. 2019Fine-Grained Entity Typing for Domain Independent Entity Linkingcited by 36
  10. 2021Modeling Fine-Grained Entity Types with Box Embeddingscited by 36
  11. 2014Context-Dependent Fine-Grained Entity Type Taggingcited by 30
  12. 2020Syntax-Enhanced Pre-trained Modelcited by 30
  13. 2020A Fully Hyperbolic Neural Model for Hierarchical Multi-Class Classificationcited by 23
  14. 2019Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typingcited by 22
  15. 2021Fine-grained Entity Typing via Label Reasoningcited by 22
  16. 2021Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statementcited by 21
  17. 2018Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Losscited by 20
  18. 2019Zero-Shot Open Entity Typing as Type-Compatible Groundingcited by 19
  19. 2018Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linkingcited by 18
  20. 2020Hierarchical Entity Typing via Multi-level Learning to Rankcited by 18
  21. 2022Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inferencecited by 17
  22. 2016Neural Architectures for Fine-grained Entity Type Classificationcited by 15
  23. 2022Automatic Noisy Label Correction for Fine-Grained Entity Typingcited by 13
  24. 2020MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typingcited by 12
  25. 2022TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrievalcited by 8
  26. 2017Fine-Grained Entity Type Classification by Jointly Learning Representations and Label Embeddingscited by 5
  27. 2016Building a Fine-Grained Entity Typing System Overnight for a New X (X = Language, Domain, Genre)cited by 4
  28. 2018Fine-grained Entity Typing through Increased Discourse Context and Adaptive Classification Thresholdscited by 4
  29. 2019Improving Distantly-supervised Entity Typing with Compact Latent Space Clusteringcited by 4
  30. 2017Fine-Grained Entity Typing with High-Multiplicity Assignmentscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulnesscited by 130
  2. 2023Calibrated Seq2seq Models for Efficient and Generalizable Ultra-fine Entity Typingcited by 5