mlsanityData to 14 Oct 2026

Ultra-Fine Entity Typing with Prior Knowledge about Labels: A Simple Clustering Based Strategy

arXiv 2305.12802 ↗First posted 22 May 2023cs.CL cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Ultra-fine entity typing (UFET) is the task of inferring the semantic types, from a large set of fine-grained candidates, that apply to a given entity mention. This task is especially challenging because we only have a small number of training examples for many of the types, even with distant supervision strategies. State-of-the-art models, therefore, have to rely on prior knowledge about the type labels in some way. In this paper, we show that the performance of existing methods can be improved using a simple technique: we use pre-trained label embeddings to cluster the labels into semantic domains and then treat these domains as additional types. We show that this strategy consistently leads to improved results, as long as high-quality label embeddings are used. We furthermore use the label clusters as part of a simple post-processing technique, which results in further performance gains. Both strategies treat the UFET model as a black box and can thus straightforwardly be used to improve a wide range of existing models.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 32 of its 58 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

32 of 58 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  5. 2022WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creationcited by 202
  6. 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
  7. 2021Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoderscited by 88
  8. 2018Ultra-Fine Entity Typingcited by 87
  9. 2020Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Networkcited by 83
  10. 2021LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classificationcited by 61
  11. 2021Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Modelcited by 39
  12. 2021Modeling Fine-Grained Entity Types with Box Embeddingscited by 36
20 more
  1. 2014Context-Dependent Fine-Grained Entity Type Taggingcited by 30
  2. 2020Syntax-Enhanced Pre-trained Modelcited by 30
  3. 2019Learning to Denoise Distantly-Labeled Data for Entity Typingcited by 24
  4. 2019Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typingcited by 22
  5. 2021Fine-grained Entity Typing via Label Reasoningcited by 22
  6. 2022Label Semantics for Few Shot Named Entity Recognitioncited by 21
  7. 2018Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Losscited by 20
  8. 2018Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linkingcited by 18
  9. 2020Hierarchical Entity Typing via Multi-level Learning to Rankcited by 18
  10. 2022Unified Semantic Typing with Meaningful Label Inferencecited by 18
  11. 2022Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inferencecited by 17
  12. 2016Neural Architectures for Fine-grained Entity Type Classificationcited by 15
  13. 2021Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attentioncited by 15
  14. 2022Automatic Noisy Label Correction for Fine-Grained Entity Typingcited by 13
  15. 2021Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learningcited by 12
  16. 2022Modelling Commonsense Properties using Pre-Trained Bi-Encoderscited by 9
  17. 2023Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Modelscited by 8
  18. 2020Modelling General Properties of Nouns by Selectively Averaging Contextualised Embeddingscited by 6
  19. 2022Modeling Label Correlations for Ultra-Fine Entity Typing with Neural Pairwise Conditional Random Fieldcited by 4
  20. 2019Modelling Semantic Categories using Conceptual Neighborhoodcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 1; 2026: 1.

8 papers.

  1. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Modelscited by 8
  2. 2024On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directionscited by 3
  3. 2024All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typingcited by 3
  4. 2024UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entitiescited by 2
  5. 2023What do Deck Chairs and Sun Hats Have in Common? Uncovering Shared Properties in Large Concept Vocabulariescited by 1
  6. 2023Learning to Correct Noisy Labels for Fine-Grained Entity Typing via Co-Prediction Prompt Tuningcited by 0
  7. 2024Modelling Commonsense Commonalities with Multi-Facet Concept Embeddingscited by 0
  8. 2026Narrative-UFET: Narrative Generation for Ultra-Fine Entity Typingcited by 0