Automatic text decomposition and structuring
Information Processing and Management: an International Journal
On the relative expressiveness of description logics and predicate logics
Artificial Intelligence
Statistical Models for Text Segmentation
Machine Learning - Special issue on natural language learning
Multi-paragraph segmentation of expository text
ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
An automatic method of finding topic boundaries
ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
Automatic analysis of questions in e-learning environment
Proceedings of the 2005 conference on Artificial Intelligence in Education: Supporting Learning through Intelligent and Socially Informed Technology
| Hi-index | 0.00 |
This paper presents a method for comparing a student essay andthe text of a course. We first show that the comparison of complex semantic representations is better done with sub-symbolic formalisms than symbolic ones. Then we present a method which rely on Latent Semantic Analysis for representing the meaning of texts. We describe the implementation of an algorithm for partitionning the student essay into coherent segments before comparing it with the text of a course. We show that this pre-processing enhances the semantic comparison. An experiment was performedon 30 student essays. An interesting correlation between the teacher grades and our data was found. This method aims at being included in distance learning environments.