Text Guide: Improving the quality of long text classification by a text selection method based on feature importance

TL;DR

This paper introduces Text Guide, a feature importance-based text truncation method that enhances long text classification performance while maintaining low computational costs, especially benefiting models like Longformer.

Contribution

The study proposes a novel text truncation technique leveraging feature importance to improve long text classification accuracy without high computational costs.

Findings

Text Guide outperforms naive truncation methods.

Parameter optimization is crucial for Text Guide effectiveness.

Applicable to models like Longformer for better long text analysis.

Abstract

The performance of text classification methods has improved greatly over the last decade for text instances of less than 512 tokens. This limit has been adopted by most state-of-the-research transformer models due to the high computational cost of analyzing longer text instances. To mitigate this problem and to improve classification for longer texts, researchers have sought to resolve the underlying causes of the computational cost and have proposed optimizations for the attention mechanism, which is the key element of every transformer model. In our study, we are not pursuing the ultimate goal of long text classification, i.e., the ability to analyze entire text instances at one time while preserving high performance at a reasonable computational cost. Instead, we propose a text truncation method called Text Guide, in which the original text length is reduced to a predefined limit in a manner that improves performance over naive and semi-naive approaches while preserving low computational costs. Text Guide benefits from the concept of feature importance, a notion from the explainable artificial intelligence domain. We demonstrate that Text Guide can be used to improve the performance of recent language models specifically designed for long text classification, such as Longformer. Moreover, we discovered that parameter optimization is the key to Text Guide performance and must be conducted before the method is deployed. Future experiments may reveal additional benefits provided by this new method.