Paper: An Analysis of Statistical Models and Features for Reading Difficulty Prediction

ACL ID W08-0909
Title An Analysis of Statistical Models and Features for Reading Difficulty Prediction
Venue Innovative Use of NLP for Building Educational Applications
Session
Year 2008
Authors

A readingdifficulty measurecan be described as a function or model that maps a text to a numerical value corresponding to a difficulty orgradelevel. We describea measureofread- ability that uses a combinationof lexical fea- turesandgrammaticalfeaturesthatarederived from subtrees of syntactic parses. We also tested statistical models for nominal, ordinal, and interval scales of measurement. The re- sults indicate that a model for ordinal regres- sion, such as the proportionalodds model,us- ing a combination of grammaticaland lexical featuresis mosteffective at predictingreading difficulty.