# Description Based Text Classification with Reinforcement Learning

arXiv: https://arxiv.org/abs/2002.03067 · HTML: https://mlsanity.com/paper/2002.03067/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2020.

## Built on by (most cited first, 27 of 27)

- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Text Classification via Large Language Models](https://mlsanity.com/paper/2305.08377/) (2023)
- [BertGCN: Transductive Text Classification by Combining GCN and BERT](https://mlsanity.com/paper/2105.05727/) (2021)
- [ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information](https://mlsanity.com/paper/2106.16038/) (2021)
- [Paradigm Shift in Natural Language Processing](https://mlsanity.com/paper/2109.12575/) (2021)
- [Defending Against Backdoor Attacks in Natural Language Generation](https://mlsanity.com/paper/2106.01810/) (2021)
- [A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems](https://mlsanity.com/paper/2204.06923/) (2022)
- [Cross-Domain Label-Adaptive Stance Detection](https://mlsanity.com/paper/2104.07467/) (2021)
- [Layer-wise Model Pruning based on Mutual Information](https://mlsanity.com/paper/2108.12594/) (2021)
- [Interpreting Deep Learning Models in Natural Language Processing: A Review](https://mlsanity.com/paper/2110.10470/) (2021)
- [Y-Tuning: An Efficient Tuning Paradigm for Large-Scale Pre-Trained Models via Label Representation Learning](https://mlsanity.com/paper/2202.09817/) (2022)
- [Dependency Parsing as MRC-based Span-Span Prediction](https://mlsanity.com/paper/2105.07654/) (2021)
- [kFolden: k-Fold Ensemble for Out-Of-Distribution Detection](https://mlsanity.com/paper/2108.12731/) (2021)
- [Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification](https://mlsanity.com/paper/2202.05932/) (2022)
- [Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning](https://mlsanity.com/paper/2204.02725/) (2022)
- [Fine-Grained Emotion Prediction by Modeling Emotion Definitions](https://mlsanity.com/paper/2107.12135/) (2021)
- [Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models](https://mlsanity.com/paper/2406.07001/) (2024)
- [A Review on Text-Based Emotion Detection -- Techniques, Applications, Datasets, and Future Directions](https://mlsanity.com/paper/2205.03235/) (2022)
- [Long-tailed Extreme Multi-label Text Classification with Generated Pseudo Label Descriptions](https://mlsanity.com/paper/2204.00958/) (2022)
- [The Benefits of Label-Description Training for Zero-Shot Text Classification](https://mlsanity.com/paper/2305.02239/) (2023)
- [Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers](https://mlsanity.com/paper/2306.14003/) (2023)
- [An MRC Framework for Semantic Role Labeling](https://mlsanity.com/paper/2109.06660/) (2021)
- [RLJP: Legal Judgment Prediction via First-Order Logic Rule-enhanced with Large Language Models](https://mlsanity.com/paper/2505.21281/) (2025)
- [Why Do Time Series Models Need Long Context Windows?](https://mlsanity.com/paper/2606.01999/) (2026)
- [LaSQuE: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum Learning](https://mlsanity.com/paper/2212.09104/) (2022)
- [Are We Really Making Much Progress in Text Classification? A Comparative Review](https://mlsanity.com/paper/2204.03954/) (2022)

## Abstract (arXiv)

The task of text classification is usually divided into two stages: it text feature extraction and it classification. In this standard formalization categories are merely represented as indexes in the label vocabulary, and the model lacks for explicit instructions on what to classify. Inspired by the current trend of formalizing NLP problems as question answering tasks, we propose a new framework for text classification, in which each category label is associated with a category description. Descriptions are generated by hand-crafted templates or using abstractive/extractive models from reinforcement learning. The concatenation of the description and the text is fed to the classifier to decide whether or not the current label should be assigned to the text. The proposed strategy forces the model to attend to the most salient texts with respect to the label, which can be regarded as a hard version of attention, leading to better performances. We observe significant performance boosts over strong baselines on a wide range of text classification tasks including single-label classification, multi-label classification and multi-aspect sentiment analysis.