Head-driven statistical models for natural language parsing
Head-driven statistical models for natural language parsing
Computer-aided generation of multiple-choice tests
HLT-NAACL-EDUC '03 Proceedings of the HLT-NAACL 03 workshop on Building educational applications using natural language processing - Volume 2
A computer-aided environment for generating multiple-choice test items
Natural Language Engineering
Hi-index | 0.00 |
This paper describes a language technology based system for providing computer-aided design of test items. Plain text instructional materials are being processed with various tools for POS tagging, constituency parsing and term extraction and lexical and syntactic information is being collected. The system compiles a list of terms which are central for the instructional materials, creates drafts of fill-in-the-blank questions and suggests possible distractors. The experiment is carried out on textbooks in geography, biology and history of Bulgarian high-schools.