Description Based Text Classification with Reinforcement Learning

TL;DR

This paper introduces a novel text classification framework that uses label descriptions and reinforcement learning to improve model attention and performance across various classification tasks.

Contribution

It formalizes text classification as a question answering problem with label descriptions, leveraging reinforcement learning for description generation to enhance attention and accuracy.

Findings

Significant performance improvements over strong baselines.

Effective handling of single-label, multi-label, and multi-aspect tasks.

Enhanced model focus on salient text features.

Abstract

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.