Modeling the Acquisition of English: An Intelligent CALL Approach

In this paper, we present a methodology for the development of a user model for CALL which captures various levels of language acquisition using individualized overlays supported with stereotypes. Our current focus is the empirical analysis of the order of written English grammatical structure acquisition in our learner population used to develop stereotype layers in our model. We are currently developing the system ICICLE (Interactive Computer Identi-cation and Correction of Language Errors) to take a Computer-Assisted Language Learning (CALL) approach toward tutoring deaf students on their written English 12, 13]. Our target learners are native or near-native users of American Sign Language (ASL), a language entirely distinct from English, so we approach the acquisition of skills in written English as a second language (L2) acquisition task. This allows us to develop a system for a population which can greatly beneet from access to individualized, adaptive tutoring 13] while contributing to the eld of CALL a design and methodology which can be also generalized to other L2 learners. Our system is a writing tutor intended to supplement classroom instruction by providing students with detailed feedback on the grammatical errors in their English compositions. Its primary concerns are the correct analysis of student-generated language errors and the production of tutorial feedback to student performance which is both correct and tailored to the student. Its interaction with a user begins when the user submits a composition to the system, which is analyzed for grammatical errors. The system then responds with tutorial feedback aimed at enabling the student to perform corrections. When the student has revised the piece, it can be re-submitted for analysis. As ICICLE is intended to be used by an individual over time and across many pieces of writing, the system should learn as much as it can about a user to perform the language analysis and constructive feedback as accurately as possible.