Paper: Exploiting Morphological, Grammatical, and Semantic Correlates for Improved Text Difficulty Assessment

ACL ID W14-1819
Title Exploiting Morphological, Grammatical, and Semantic Correlates for Improved Text Difficulty Assessment
Venue Innovative Use of NLP for Building Educational Applications
Session
Year 2014
Authors

We present a low-resource, language- independent system for text difficulty as- sessment. We replicate and improve upon a baseline by Shen et al. (2013) on the Interagency Language Roundtable (ILR) scale. Our work demonstrates that the ad- dition of morphological, information the- oretic, and language modeling features to a traditional readability baseline greatly benefits our performance. We use the Margin-Infused Relaxed Algorithm and Support Vector Machines for experiments on Arabic, Dari, English, and Pashto, and provide a detailed analysis of our results.