Combining Lexical and Grammatical Features to Improve Readability Measures for First and Second Language Texts

This work evaluates a system that uses interpolated predictions of reading difficulty that are based on both vocabulary and grammatical features. The combined approach is compared to individual grammar- and language modeling-based approaches. While the vocabulary-based language modeling approach outperformed the grammar-based approach, grammar-based predictions can be combined using confidence scores with the vocabulary-based predictions to produce more accurate predictions of reading difficulty for both first and second language texts. The results also indicate that grammatical features may play a more important role in second language readability than in first language readability.

• Type: Conference
• Year: 2007
• Where: NAACL
• Authors: Michael Heilman, Kevyn Collins-Thompson, Jamie Callan, Maxine Eskenazi
• Keywords: Computational Linguistics, Grammatical Features, NAACL 2007, Predictions, Reading Difficulty