ReadNet: A Hierarchical Transformer Framework for Web Article Readability Analysis

TL;DR

ReadNet introduces a hierarchical transformer framework that effectively captures sentence difficulty, semantic content, and article structure to improve web article readability assessment, outperforming existing methods.

Contribution

This paper presents a novel hierarchical self-attention model that integrates sentence difficulty, semantics, and structure for enhanced readability analysis.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively models complex article structures and semantics.

Outperforms strong baseline approaches.

Abstract

Analyzing the readability of articles has been an important sociolinguistic task. Addressing this task is necessary to the automatic recommendation of appropriate articles to readers with different comprehension abilities, and it further benefits education systems, web information systems, and digital libraries. Current methods for assessing readability employ empirical measures or statistical learning techniques that are limited by their ability to characterize complex patterns such as article structures and semantic meanings of sentences. In this paper, we propose a new and comprehensive framework which uses a hierarchical self-attention model to analyze document readability. In this model, measurements of sentence-level difficulty are captured along with the semantic meanings of each sentence. Additionally, the sentence-level features are incorporated to characterize the overall readability of an article with consideration of article structures. We evaluate our proposed approach on three widely-used benchmark datasets against several strong baseline approaches. Experimental results show that our proposed method achieves the state-of-the-art performance on estimating the readability for various web articles and literature.