Automatic scoring of handwritten essays is a task that involves the integration of several artificial intelligence technologies.
The design of a system for taking as input scanned images of hand written student essays in reading comprehension tests and to produce as output scores for the answers which are analogous to those provided by human scorers is described.
The system is based on integrating two technologies of optical hand writing recognition (OHR) and automated essay scoring (AES)
The OHR system performs several preprocessing steps such as forms removal, rule-line removal and segmentation of text lines and words.
The final recognition step which is tuned to the task of reading comprehension evaluation in a primary education setting is performed using a lexicon derived from the passage to be read.
The AES system is based on the approach of latent semantic analysis where a set of human-scored answers are used to determine scoring system parameters using a machine learning approach.
System performance is compared to scoring done by human raters.
No comments:
Post a Comment