mlsanityData to 7 Oct 2026

Denoising Multi-Source Weak Supervision for Neural Text Classification

arXiv 2010.04582 ↗First posted 9 Oct 2020cs.CLcited by 42

Not on the map. Why?

Abstract (arXiv)

We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels are often noisy and incomplete. To address these two challenges, we design a label denoiser, which estimates the source reliability using a conditional soft attention mechanism and then reduces label noise by aggregating rule-annotated weak labels. The denoised pseudo labels then supervise a neural classifier to predicts soft labels for unmatched samples, which address the rule coverage issue. We evaluate our model on five benchmarks for sentiment, topic, and relation classifications. The results show that our model outperforms state-of-the-art weakly-supervised and semi-supervised methods consistently, and achieves comparable performance with fully-supervised methods even without any labeled data. Our code can be found at https://github.com/weakrules/Denoise-multi-weak-sources.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 18; 2023: 7; 2024: 7; 2025: 3; 2026: 1.

42 papers.

Sort:

  1. 2021WRENCH: A Comprehensive Benchmark for Weak Supervisioncited by 95
  2. 2022A Survey on Programmatic Weak Supervisioncited by 66
  3. 2024A Simple but Effective Approach to Improve Structured Language Model Output for Information Extractioncited by 16
  4. 2021BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognitioncited by 15
  5. 2022Nemo: Guiding and Contextualizing Weak Supervision for Interactive Data Programmingcited by 10
  6. 2024The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotatorscited by 10
  7. 2022Understanding Programmatic Weak Supervision via Source-aware Influence Functioncited by 8
  8. 2023Weaker Than You Think: A Critical Look at Weakly Supervised Learningcited by 8
  9. 2023How Many Validation Labels Do You Need? Exploring the Design Space of Label-Efficient Model Rankingcited by 8
  10. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Modelscited by 8
  11. 2021Self-Training with Differentiable Teachercited by 7
  12. 2022Meta Self-Refinement for Robust Learning with Weak Supervisioncited by 7
30 more
  1. 2022AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labelscited by 7
  2. 2022Adaptive Ranking-based Sample Selection for Weakly Supervised Class-imbalanced Text Classificationcited by 7
  3. 2022Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervisioncited by 6
  4. 2023PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Trainingcited by 6
  5. 2023Can Large Language Models Design Accurate Label Functions?cited by 6
  6. 2022Adaptive Mixing of Auxiliary Losses in Supervised Learningcited by 5
  7. 2022Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognitioncited by 4
  8. 2022SepLL: Separating Latent Class Labels from Weak Supervision Noisecited by 4
  9. 2023Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removalcited by 4
  10. 2021Learning to Selectively Learn for Weakly-supervised Paraphrase Generationcited by 3
  11. 2025ScriptoriumWS: A Code Generation Assistant for Weak Supervisioncited by 3
  12. 2021Customer Sentiment Analysis using Weak Supervision for Customer-Agent Chatcited by 2
  13. 2022Binary Classification with Positive Labeling Sourcescited by 2
  14. 2021WALNUT: A Benchmark on Semi-weakly Supervised Learning for Natural Language Understandingcited by 1
  15. 2022Label Augmentation with Reinforced Labeling for Weak Supervisioncited by 1
  16. 2022ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervisioncited by 1
  17. 2022XPASC: Measuring Generalization in Weak Supervision by Explainability and Associationcited by 1
  18. 2024Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglementcited by 1
  19. 2024Convergence Behavior of an Adversarial Weak Supervision Methodcited by 1
  20. 2024Automating Weak Label Generation for Data Programming with Clinicians in the Loopcited by 1
  21. 2024A Weakly Supervised Data Labeling Framework for Machine Lexical Normalization in Vietnamese Social Mediacited by 1
  22. 2025Reliable Programmatic Weak Supervision with Confidence Intervals for Label Probabilitiescited by 1
  23. 2026Structured Exploration and Exploitation of Label Functions for Automated Data Annotationcited by 1
  24. 2022WeaNF: Weak Supervision with Normalizing Flowscited by 0
  25. 2022Integrated Weak Learningcited by 0
  26. 2022Low Resource Pipeline for Spoken Language Understanding via Weak Supervisioncited by 0
  27. 2022BERT-Flow-VAE: A Weakly-supervised Model for Multi-Label Text Classificationcited by 0
  28. 2023Local Boosting for Weakly-Supervised Learningcited by 0
  29. 2023Utilizing Weak Supervision To Generate Indonesian Conservation Datasetcited by 0
  30. 2024Domain Adaptation of Multilingual Semantic Search -- Literature Reviewcited by 0