A New KE-Free Online ICALL System Featuring Error Contingent Feedback

Abstract

As a first step towards implementing a human language teacher, we have developed a new template-based on-line ICALL (intelligent computer assisted language learning) system capable of automatically diagnosing learners' free-format translated inputs and returning error contingent feedback. The system architecture we have adopted allows language teachers to build their own expertise into the system without the help of KEs (knowledge engineers), thus alleviating the long-standing KE bottlenecks associated with conventional expert-systems-based ITS (intelligent tutoring system) or ICALL (Murray, 1999). The core of the system comprises a unique FSA (finite state automaton)-based template knowledge base system, a robust and global HCS (heaviest common sequence)-based diagnostic engine, a POST(part-of speech-tagged) parser and related learners' model as well as an easy-to-use VTAT (visual template authoring tool). To simplify the task of authoring often quite complex template patterns, we have developed two sets of simpler rules; the first group of rules allows language teachers to manipulate complex sentence patterns with ease by constructing a template-template representation from which numerous separate templates can be extracted. The second group of buggy rules can be used to automatically generate syntactic bugs for learners by replacing part of the correct syntactic rules with plausible buggy rules. Using participants' responses extracted into the system templates, we present some convincing experimental verifications that the diagnostic engine is capable of providing error-contingent feedback and diagnosis applicable to a wide range of learners with differing educational backgrounds.