C.-H. Wang, C.-L. Liu, and Z.-M. Gao (Taiwan)
Authoring Tools and Methodology, Automatic Item Gen eration, Computer-Assisted Language Learning, Colloca tions, Selectional Preferences, Word Sense Disambigua tion, Natural Language Processing
Computer-assisted item generation allows the creation of large-scale item banks, and further supports Web-based learning and assessment. With the abundant text resources on the Web, one may create cloze items that cover a wide range of topics, thereby increasing the diversity and security of the item bank. We propose a word sense disambiguation-based method for locating sentences in which designated words carry specific senses, and apply collocation-based methods for selecting distractors that are necessary for multiple-choice cloze items. Experimental results indicate that our system was able to produce a us able item for every 1.6 items it returned.
Important Links:
Go Back
