A New KE-Free Online ICALL System Featuring Error Contingent Feedback
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.015 | 0.008 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".