mlsanityData to 7 Oct 2026

Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning

arXiv 2204.09589 ↗First posted 3 Mar 2022cs.CL cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

In this paper, we study the named entity recognition (NER) problem under distant supervision. Due to the incompleteness of the external dictionaries and/or knowledge bases, such distantly annotated training data usually suffer from a high false negative rate. To this end, we formulate the Distantly Supervised NER (DS-NER) problem via Multi-class Positive and Unlabeled (MPU) learning and propose a theoretically and practically novel CONFidence-based MPU (Conf-MPU) approach. To handle the incomplete annotations, Conf-MPU consists of two steps. First, a confidence score is estimated for each token of being an entity token. Then, the proposed Conf-MPU risk estimation is applied to train a multi-class classifier for the NER task. Thorough experiments on two benchmark datasets labeled by various external knowledge demonstrate the superiority of the proposed Conf-MPU over existing DS-NER methods.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

20 of 32 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Rethinking Pre-training and Self-trainingcited by 352
  3. 2018Learning from positive and unlabeled data: a surveycited by 218
  4. 2017Positive-Unlabeled Learning with Non-Negative Risk Estimatorcited by 217
  5. 2015Named Entity Recognition with Bidirectional LSTM-CNNscited by 201
  6. 2020BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervisioncited by 91
  7. 2020Automated Concatenation of Embeddings for Structured Predictioncited by 86
  8. 2021Improving Named Entity Recognition by External Context Retrieving and Cooperative Learningcited by 76
  9. 2018Learning Named Entity Tagger using Domain-Specific Dictionarycited by 65
  10. 2019Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learningcited by 46
  11. 2018Classification from Positive, Unlabeled and Biased Negative Datacited by 34
  12. 2019Low-Resource Name Tagging Learned with Weakly Labeled Datacited by 32
8 more
  1. 2021Noisy-Labeled NER with Confidence Estimationcited by 28
  2. 2019Named Entity Recognition with Partially Annotated Training Datacited by 27
  3. 2016Estimating the class prior and posterior from noisy positives and unlabeled datacited by 25
  4. 2017Scientific Information Extraction with Semi-supervised Neural Taggingcited by 24
  5. 2021De-biasing Distantly Supervised Named Entity Recognition via Causal Interventioncited by 24
  6. 2014Lexicon Infused Phrase Embeddings for Named Entity Resolutioncited by 16
  7. 2017Unsupervised Aspect Term Extraction with B-LSTM & CRF using Automatically Labelled Datasetscited by 12
  8. 2019End-to-end Named Entity Recognition and Relation Extraction using Pre-trained Language Modelscited by 11

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 8; 2024: 6; 2025: 3.

21 papers.

Sort:

By area:

  1. 2022Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learningcited by 24
  2. 2022Distantly-Supervised Named Entity Recognition with Adaptive Teacher Learning and Fine-grained Student Ensemblecited by 14
  3. 2024Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Stylecited by 11
  4. 2022A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labelingcited by 9
  5. 2024Re-Examine Distantly Supervised NER: A New Benchmark and a Simple Approachcited by 5
  6. 2023SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognitioncited by 4
  7. 2023A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labelingcited by 4
  8. 2023MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognitioncited by 4
  9. 2022Improving Distantly Supervised Relation Extraction by Natural Language Inferencecited by 3
  10. 2023Uncertainty-aware Self-training for Low-resource Neural Sequence Labelingcited by 3
  11. 2023Biomedical Named Entity Recognition via Dictionary-based Synonym Generalizationcited by 3
  12. 2023Better Sampling of Negatives for Distantly Supervised Named Entity Recognitioncited by 2
9 more
  1. 2023Relation-Aware Network with Attention-Based Loss for Few-Shot Knowledge Graph Completioncited by 2
  2. 2025DynClean: Training Dynamics-based Label Cleaning for Distantly-Supervised Named Entity Recognitioncited by 2
  3. 2025Few Dimensions are Enough: Fine-tuning BERT with Selected Dimensions Revealed Its Redundant Naturecited by 1
  4. 2023Do Not Harm Protected Groups in Debiasing Language Representation Modelscited by 0
  5. 2024ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognitioncited by 0
  6. 2024Bridge: A Unified Framework to Knowledge Graph Completion via Language Models and Knowledge Representationcited by 0
  7. 2024Learning from Concealed Labelscited by 0
  8. 2024ESA: Example Sieve Approach for Multi-Positive and Unlabeled Learningcited by 0
  9. 2025Towards DS-NER: Unveiling and Addressing Latent Noise in Distant Annotationscited by 0