Semi-Supervised Joint Estimation of Word and Document Readability
This work addresses readability estimation for educational or content adaptation purposes, but it is incremental as it builds on existing GCN methods.
The paper tackles the joint estimation of word and document readability by proposing a graph convolutional network (GCN) approach, achieving higher accuracy than strong baselines and maintaining robustness with limited labeled data.
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.