mlsanityData to 14 Oct 2026

Contrastive Learning with Hard Negative Entities for Entity Set Expansion

arXiv 2204.07789 ↗First posted 16 Apr 2022cs.CL cs.IRcited by 26

Not on the map. Why?

Abstract (arXiv)

Entity Set Expansion (ESE) is a promising task which aims to expand entities of the target semantic class described by a small seed entity set. Various NLP and IR applications will benefit from ESE due to its ability to discover knowledge. Although previous ESE methods have achieved great progress, most of them still lack the ability to handle hard negative entities (i.e., entities that are difficult to distinguish from the target entities), since two entities may or may not belong to the same semantic class based on different granularity levels we analyze on. To address this challenge, we devise an entity-level masked language model with contrastive learning to refine the representation of entities. In addition, we propose the ProbExpan, a novel probabilistic ESE framework utilizing the entity representation obtained by the aforementioned language model to expand entities. Extensive experiments and detailed analyses on three datasets show that our method outperforms previous state-of-the-art methods.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 21 of its 39 references that are in the map. First posted on arXiv 16 Apr 2022.

Builds on

21 of 39 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  6. 2020Supervised Contrastive Learningcited by 2,829
  7. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  8. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
  9. 2020Contrastive Learning with Hard Negative Samplescited by 628
  10. 2019ERNIE: Enhanced Language Representation with Informative Entitiescited by 528
  11. 2014word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding methodcited by 112
  12. 2021Self-Guided Contrastive Learning for BERT Sentence Representationscited by 103
9 more
  1. 2020ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learningcited by 72
  2. 2022The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checkingcited by 56
  3. 2021CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understandingcited by 50
  4. 2019SetExpan: Corpus-Based Set Expansion via Context Feature Selection and Rank Ensemblecited by 25
  5. 2020Empower Entity Set Expansion via Language Model Probingcited by 25
  6. 2020Guiding Corpus-based Set Expansion by Auxiliary Sets Generation and Co-Expansioncited by 13
  7. 2018Term Set Expansion based NLP Architect by Intel AI Labcited by 11
  8. 2020SynSetExpan: An Iterative Framework for Joint Entity Set Expansion and Synonym Discoverycited by 10
  9. 2020A Two-Stage Masked LM Method for Term Set Expansioncited by 8

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 11; 2024: 6; 2025: 5.

26 papers.

Sort:

By area:

  1. 2023EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commercecited by 49
  2. 2022Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checkingcited by 31
  3. 2023Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characterscited by 22
  4. 2025DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokenscited by 22
  5. 2022Automatic Context Pattern Generation for Entity Set Expansioncited by 21
  6. 2023Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph Alignmentcited by 19
  7. 2023A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Checkcited by 15
  8. 2023MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entitiescited by 13
  9. 2022Embracing Ambiguity: Improving Similarity-oriented Tasks with Contextual Synonym Knowledgecited by 12
  10. 2022Active Relation Discovery: Towards General and Label-aware Open Relation Extractioncited by 10
  11. 2024ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questionscited by 10
  12. 2024A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansioncited by 8
14 more
  1. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Modelscited by 8
  2. 2023Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linkingcited by 7
  3. 2024Mitigating Catastrophic Forgetting in Multi-domain Chinese Spelling Correction by Multi-stage Knowledge Transfer Frameworkcited by 4
  4. 2025From Token to Line: Enhancing Code Generation with a Long-Term Perspectivecited by 4
  5. 2023From Retrieval to Generation: Efficient and Effective Entity Set Expansioncited by 3
  6. 2024Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansioncited by 3
  7. 2025MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuningcited by 3
  8. 2023Retrieval-Augmented Meta Learning for Low-Resource Text Classificationcited by 2
  9. 2024UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entitiescited by 2
  10. 2025Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learningcited by 2
  11. 2023Investigating Graph Structure Information for Entity Alignment with Dangling Casescited by 1
  12. 2023Prompt Learning With Knowledge Memorizing Prototypes For Generalized Few-Shot Intent Detectioncited by 1
  13. 2023An Anchor Learning Approach for Citation Field Learningcited by 0
  14. 2024A Debiased Nearest Neighbors Framework for Multi-Label Text Classificationcited by 0