Abstract

The learner model for an intelligent tutoring system for second language learning must be based upon the inference of the learner's knowledge of grammar and lexicon. An incomplete grammar and an incomplete lexicon are appropriate models of the learner’s knowledge. It is shown that an Incomplete grammar and lexicon can be inferred from the parsing of ungrammatical (and grammatical) input. Productions of the Incomplete Grammar are synthesized from the output of a robust parser. The synthesized productions become hypotheses in the learner model. A system of belief support is used to maintain the learner model. When productions of the incomplete grammar are synthesized, they are assigned an initial confidence factor. Confidence factors of the hypotheses are adjusted when new hypotheses are included in the learner model.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.