Supervised and Unsupervised Neural Approaches to Text Readability
This addresses the problem of automating readability classification for documents, offering a more flexible alternative to feature engineering, though it appears incremental in advancing neural methods for this task.
The paper tackles text readability assessment by developing novel neural supervised and unsupervised approaches, showing that the unsupervised method is robust and transferable across languages, with performance compared to state-of-the-art feature-based methods.
We present a set of novel neural supervised and unsupervised approaches for determining the readability of documents. In the unsupervised setting, we leverage neural language models, whereas in the supervised setting, three different neural classification architectures are tested. We show that the proposed neural unsupervised approach is robust, transferable across languages and allows adaptation to a specific readability task and data set. By systematic comparison of several neural architectures on a number of benchmark and new labelled readability datasets in two languages, this study also offers a comprehensive analysis of different neural approaches to readability classification. We expose their strengths and weaknesses, compare their performance to current state-of-the-art classification approaches to readability, which in most cases still rely on extensive feature engineering, and propose possibilities for improvements.