# Text Classification Using Label Names Only: A Language Model Self-Training Approach

arXiv: https://arxiv.org/abs/2010.07245 · HTML: https://mlsanity.com/paper/2010.07245/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2020.

## Built on by (most cited first, 30 of 32)

- [Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations](https://mlsanity.com/paper/2202.04582/) (2022)
- [TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters](https://mlsanity.com/paper/2201.06771/) (2022)
- [TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision](https://mlsanity.com/paper/2403.00165/) (2024)
- [Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data](https://mlsanity.com/paper/2109.10856/) (2021)
- [LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification](https://mlsanity.com/paper/2205.12528/) (2022)
- [Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification](https://mlsanity.com/paper/2202.05932/) (2022)
- [MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information](https://mlsanity.com/paper/2111.04022/) (2021)
- [Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation](https://mlsanity.com/paper/2206.13746/) (2022)
- [Resolving label uncertainty with implicit posterior models](https://mlsanity.com/paper/2202.14000/) (2022)
- [A Survey on Retrieval And Structuring Augmented Generation with Large Language Models](https://mlsanity.com/paper/2509.10697/) (2025)
- [PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners](https://mlsanity.com/paper/2205.09229/) (2022)
- [WOT-Class: Weakly Supervised Open-world Text Classification](https://mlsanity.com/paper/2305.12401/) (2023)
- [LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training](https://mlsanity.com/paper/2112.01404/) (2021)
- [DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation](https://mlsanity.com/paper/2212.08724/) (2022)
- [Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding](https://mlsanity.com/paper/2304.04099/) (2023)
- [Adaptive Multi-view Rule Discovery for Weakly-Supervised Compatible Products Prediction](https://mlsanity.com/paper/2206.13749/) (2022)
- [Personal Attribute Prediction from Conversations](https://mlsanity.com/paper/2209.09619/) (2022)
- [Unsupervised Sentence Representation Learning with Frequency-induced Adversarial Tuning and Incomplete Sentence Filtering](https://mlsanity.com/paper/2305.08655/) (2023)
- [Seed Word Selection for Weakly-Supervised Text Classification with Unsupervised Error Estimation](https://mlsanity.com/paper/2104.09765/) (2021)
- [RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical Rules](https://mlsanity.com/paper/2403.02932/) (2024)
- [Weakly Supervised Text Classification on Free Text Comments in Patient-Reported Outcome Measures](https://mlsanity.com/paper/2308.06199/) (2023)
- [Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement](https://mlsanity.com/paper/2404.11036/) (2024)
- [Variational Weakly Supervised Sentiment Analysis with Posterior Regularization](https://mlsanity.com/paper/2104.08779/) (2021)
- [Weakly Supervised Prototype Topic Model with Discriminative Seed Words: Modifying the Category Prior by Self-exploring Supervised Signals](https://mlsanity.com/paper/2112.03009/) (2021)
- [IDEA: Interactive DoublE Attentions from Label Embedding for Text Classification](https://mlsanity.com/paper/2209.11407/) (2022)
- [BERT-Flow-VAE: A Weakly-supervised Model for Multi-Label Text Classification](https://mlsanity.com/paper/2210.15225/) (2022)
- [Contrastive Bootstrapping for Label Refinement](https://mlsanity.com/paper/2306.04544/) (2023)
- [Prompting Encoder Models for Zero-Shot Classification: A Cross-Domain Study in Italian](https://mlsanity.com/paper/2407.20654/) (2024)
- [A Similarity-Based Oversampling Method for Multi-label Imbalanced Text Data](https://mlsanity.com/paper/2411.01013/) (2024)
- [Detecting Vulnerabilities from Issue Reports for Internet-of-Things](https://mlsanity.com/paper/2511.01941/) (2025)

## Abstract (arXiv)

Current text classification methods typically require a good number of human-labeled documents as training data, which can be costly and difficult to obtain in real applications. Humans can perform classification without seeing any labeled examples but only based on a small set of words describing the categories to be classified. In this paper, we explore the potential of only using the label name of each class to train classification models on unlabeled data, without using any labeled documents. We use pre-trained neural language models both as general linguistic knowledge sources for category understanding and as representation learning models for document classification. Our method (1) associates semantically related words with the label names, (2) finds category-indicative words and trains the model to predict their implied categories, and (3) generalizes the model via self-training. We show that our model achieves around 90% accuracy on four benchmark datasets including topic and sentiment classification without using any labeled documents but learning from unlabeled data supervised by at most 3 words (1 in most cases) per class as the label name.