Text Classification: A Sequential Reading Approach

TL;DR

This paper introduces a novel sequential reading approach to text classification, modeling it as a Markov Decision Process and using reinforcement learning to improve classification efficiency and accuracy, especially with limited training data.

Contribution

It presents a new reinforcement learning-based method that models text classification as a sequential decision process, allowing adaptive reading and decision-making.

Findings

Performs comparably to SVM on large datasets

Outperforms SVM on small datasets

Automatically adapts reading process based on training data quantity

Abstract

We propose to model the text classification process as a sequential decision process. In this process, an agent learns to classify documents into topics while reading the document sentences sequentially and learns to stop as soon as enough information was read for deciding. The proposed algorithm is based on a modelisation of Text Classification as a Markov Decision Process and learns by using Reinforcement Learning. Experiments on four different classical mono-label corpora show that the proposed approach performs comparably to classical SVM approaches for large training sets, and better for small training sets. In addition, the model automatically adapts its reading process to the quantity of training information provided.