University of Cambridge > Talks.cam > NLIP Seminar Series > Deep NLP in language tutoring

Deep NLP in language tutoring

Add to your list(s) Download to your calendar using vCal

  • UserFrancis Bond, Associate Professor at the Division of Linguistics and Multilingual Studies, Nanyang Technological University, Singapore
  • ClockFriday 16 June 2017, 15:00-16:00
  • HouseFW11, Computer Laboratory.

If you have a question about this talk, please contact Anita Verő.

Technology-Enabled Education is an increasingly important part of higher education. But due to the complexity of natural languages, the available technology to teach, drill, and evaluate language courses is still rudimentary. Therefore second language learners still depend heavily on human instructors for attention and constructive feedback.

In this talk I show how computational resources (lexicons and grammars) can be used to help language learners. In particular I introduce a cross-lingual vocabulary learning game, and a new kind of language tutoring system targeted at second language learners. It makes use of language technology to provide tailored feedback based on the student’s grammatical errors. The system is bilingual, using machine translation (MT) technology to provide accurate feedback in the student’s first language.

Ungrammatical sentences can be corrected in many ways, depending on their intended meaning. For each ungrammatical sentence provided by a student, the system checks if it is well-formed using a computational grammar. If there is some error, it uses special rules (mal-rules) to identify both the intended meaning and the error. When necessary, it uses MT to ask students what was meant in their first language. Finally, it gives hints about the errors.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity