# Label Confusion Learning to Enhance Text Classification Models

arXiv: https://arxiv.org/abs/2012.04987 · HTML: https://mlsanity.com/paper/2012.04987/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2020.

## Built on by (most cited first, 16 of 16)

- [Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning](https://mlsanity.com/paper/2106.03103/) (2021)
- [Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2208.03763/) (2022)
- [Understanding and Improving Ensemble Adversarial Defense](https://mlsanity.com/paper/2310.18477/) (2023)
- [A Survey on Deep Learning Event Extraction: Approaches and Applications](https://mlsanity.com/paper/2107.02126/) (2021)
- [The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation](https://mlsanity.com/paper/2206.07359/) (2022)
- [Leveraging Label Semantics and Meta-Label Refinement for Multi-Label Question Classification](https://mlsanity.com/paper/2411.01841/) (2024)
- [Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers](https://mlsanity.com/paper/2112.02353/) (2021)
- [Emotion-Anchored Contrastive Learning Framework for Emotion Recognition in Conversation](https://mlsanity.com/paper/2403.20289/) (2024)
- [Adversarial Ensemble Training by Jointly Learning Label Dependencies and Member Models](https://mlsanity.com/paper/2206.14477/) (2022)
- [Description-Enhanced Label Embedding Contrastive Learning for Text Classification](https://mlsanity.com/paper/2306.08817/) (2023)
- [Automatic tagging of knowledge points for K12 math problems](https://mlsanity.com/paper/2208.09867/) (2022)
- [IDEA: Interactive DoublE Attentions from Label Embedding for Text Classification](https://mlsanity.com/paper/2209.11407/) (2022)
- [Feature Weaken: Vicinal Data Augmentation for Classification](https://mlsanity.com/paper/2211.10944/) (2022)
- [Harnessing label semantics to extract higher performance under noisy label for Company to Industry matching](https://mlsanity.com/paper/2212.01685/) (2022)
- [Posterior Label Smoothing for Node Classification](https://mlsanity.com/paper/2406.00410/) (2024)
- [Picturized and Recited with Dialects: A Multimodal Chinese Representation Framework for Sentiment Analysis of Classical Chinese Poetry](https://mlsanity.com/paper/2505.13210/) (2025)

## Abstract (arXiv)

Representing a true label as a one-hot vector is a common practice in training text classification models. However, the one-hot representation may not adequately reflect the relation between the instances and labels, as labels are often not completely independent and instances may relate to multiple labels in practice. The inadequate one-hot representations tend to train the model to be over-confident, which may result in arbitrary prediction and model overfitting, especially for confused datasets (datasets with very similar labels) or noisy datasets (datasets with labeling errors). While training models with label smoothing (LS) can ease this problem in some degree, it still fails to capture the realistic relation among labels. In this paper, we propose a novel Label Confusion Model (LCM) as an enhancement component to current popular text classification models. LCM can learn label confusion to capture semantic overlap among labels by calculating the similarity between instances and labels during training and generate a better label distribution to replace the original one-hot label vector, thus improving the final classification performance. Extensive experiments on five text classification benchmark datasets reveal the effectiveness of LCM for several widely used deep learning classification models. Further experiments also verify that LCM is especially helpful for confused or noisy datasets and superior to the label smoothing method.