mlsanityData to 7 Oct 2026

PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasets

arXiv 2211.14838 ↗First posted 27 Nov 2022cs.CL cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Much of named entity recognition (NER) research focuses on developing dataset-specific models based on data from the domain of interest, and a limited set of related entity types. This is frustrating as each new dataset requires a new model to be trained and stored. In this work, we present a ``versatile'' model -- the Prompting-based Unified NER system (PUnifiedNER) -- that works with data from different domains and can recognise up to 37 entity types simultaneously, and theoretically it could be as many as possible. By using prompt learning, PUnifiedNER is a novel approach that is able to jointly train across multiple corpora, implementing intelligent on-demand entity recognition. Experimental results show that PUnifiedNER leads to significant prediction benefits compared to dataset-specific models with impressively reduced model deployment costs. Furthermore, the performance of PUnifiedNER can achieve competitive or even better performance than state-of-the-art domain-specific methods for some datasets. We also perform comprehensive pilot and ablation studies to support in-depth analysis of each component in PUnifiedNER.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 30 of its 46 references that are in the map. First posted on arXiv 27 Nov 2022.

Builds on

30 of 46 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  7. 2021Grounded Language-Image Pre-trainingcited by 1,147
  8. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  9. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  10. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  11. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 475
  12. 201912-in-1: Multi-Task Vision and Language Representation Learningcited by 278
18 more
  1. 2022Unified Structure Generation for Universal Information Extractioncited by 220
  2. 2020Named Entity Recognition as Dependency Parsingcited by 150
  3. 2021A Unified Generative Framework for Various NER Subtaskscited by 141
  4. 2021Unified Named Entity Recognition as Word-Word Relation Classificationcited by 89
  5. 2018Chinese NER Using Lattice LSTMcited by 81
  6. 2019TENER: Adapting Transformer Encoder for Named Entity Recognitioncited by 69
  7. 2020FLAT: Chinese NER Using Flat-Lattice Transformercited by 67
  8. 2021Locate and Label: A Two-stage Identifier for Nested Named Entity Recognitioncited by 60
  9. 2022BigBIO: A Framework for Data-Centric Biomedical Natural Language Processingcited by 36
  10. 2021Lexicon Enhanced Chinese Sequence Labeling Using BERT Adaptercited by 34
  11. 2021A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognitioncited by 33
  12. 2022A Rationale-Centric Framework for Human-in-the-loop Machine Learningcited by 27
  13. 2019Simplify the Usage of Lexicon in Chinese NERcited by 23
  14. 2020CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinesecited by 19
  15. 2022In-BoXBART: Get Instructions into Biomedical Multi-Task Learningcited by 16
  16. 2022Domain-Specific NER via Retrieving Correlated Samplescited by 11
  17. 2022SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learningcited by 8
  18. 2021BERT-Beta: A Proactive Probabilistic Approach to Text Moderationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 2; 2026: 1.

10 papers.

  1. 2024A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understandingcited by 57
  2. 2023PromptNER: Prompting For Named Entity Recognitioncited by 35
  3. 2025Advancing Sequential Numerical Prediction in Autoregressive Modelscited by 26
  4. 2024PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognitioncited by 6
  5. 2024Balancing Speciality and Versatility: A Coarse to Fine Framework for Mitigating Catastrophic Forgetting in Large Language Modelscited by 3
  6. 2026HACHIMI: Scalable and Controllable Student Persona Generation via Orchestrated Agentscited by 2
  7. 2023Unified Model Learning for Various Neural Machine Translationcited by 0
  8. 2023Redefining Developer Assistance: Through Large Language Models in Software Ecosystemcited by 0
  9. 2024Multi-BERT: Leveraging Adapters and Prompt Tuning for Low-Resource Multi-Domain Adaptationcited by 0
  10. 2025RetrieveAll: A Multilingual Named Entity Recognition Framework with Large Language Modelscited by 0