Chi Lu

Automated Scoring Using A Hybrid Feature Identification Technique

This study exploits statistical redundancy inherent in natural language to automatically predict scores for essays. We use a hybrid feature identification method, including syntactic structure analysis, rhetorical structure analysis, and topical analysis, to score essay responses from test-takers of the Graduate Management Admissions Test (GMAT) and the Test of Written English (TWE). For each essay question, a stepwise linear regression analysis is run on a training set (sample of human scored essay responses) to extract a weighted set of predictive features for each test question. Score prediction for cross-validation sets is calculated from the set of predictive features. Exact or adjacent agreement between the Electronic Essay Rater (e-rater) score predictions and human rater scores ranged from 87% to 94% across the 15 test questions.

Using Lexical Semantic Techniques to Classify Free-Responses

The education community wants to include more performance-based assessments on standardized exams. The research described in i;his paper shows the use of lexical semantic techniques for automated scoring of short-answer and essay responses from performance-based test items. We use lexical semantic techniques in order to identify the meaningful content of free-text responses for small data sets. The research demonstrates applications of lexical semantic techniques for free-text responses of varying length and in different subject domains. Prototype designs, and the results of the different prototype applications are discussed.

An Automatic Scoring System For Advanced Placement Biology Essays

This paper describes a prototype for automatically scoring College Board Advanced Placement (AP) Biology essays.1. The scoring technique used in this study was based on a previous method used to score sentence-length responses (Burstein, et al, 1996). One hundred training essays were used to build an example-based lexicon and concept grammars. The prototype accesses information from the lexicon and concept grammars to score essays by assigning a classification of Excellent or Poor based on the number of points assigned during scoring. Final computer-based essay scores are based on the systems recognition of conceptual information in the essays. Conceptual analysis in essays is essential to provide a classification based on the essay content. In addition, computer-generated information about essay content can be used to produce diagnostic feedback. The set of essays used in this study had been scored by human raters. The results reported in the paper show 94% agreement on exact or adjacent scores between human rater scores and computer-based scores for 105 test essays. The methods underlying this application could be used in a number of applications involving rapid semantic analysis of textual materials, especially with regard to scientific or other technical text.