Semi-Supervised Joint Estimation of Word and Document Readability

TL;DR

This paper introduces a semi-supervised graph convolutional network approach to jointly estimate word and document readability, leveraging their recursive relationship for improved accuracy and robustness with limited labeled data.

Contribution

It presents a novel semi-supervised GCN method that jointly models word and document difficulty, outperforming existing baselines.

Findings

Higher accuracy than strong baselines

Robust performance with less labeled data

Effective joint estimation of word and document difficulty

Abstract

Readability or difficulty estimation of words and documents has been investigated independently in the literature, often assuming the existence of extensive annotated resources for the other. Motivated by our analysis showing that there is a recursive relationship between word and document difficulty, we propose to jointly estimate word and document difficulty through a graph convolutional network (GCN) in a semi-supervised fashion. Our experimental results reveal that the GCN-based method can achieve higher accuracy than strong baselines, and stays robust even with a smaller amount of labeled data.