ImprovChat: An AI-enabled Dialogue Assistant Chatbot for English Language Learners (ELL)
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This thesis asks, how can an AI-enabled Dialogue Assistant in the form of a chatbot suggest new and unexpected forms of response to English Language Learners? The thesis draws upon theories of improvisation and play, alongside computer science to facilitate text-based conversation in English for non-native speakers. ImprovChat is a digital solution for communication issues that I encounter every day. My experience with improvisational theatre also informs the ImprovChat project. For my thesis research-creation, I developed the web application by implementing API powered by machine learning to generate AI phrases. The phrase generation model is pre-trained using the Twitter feeds created by people who speak English as a first language. ImprovChat dialogue assistant will provide phrase suggestions; these could potentially be used in online chatting scenarios where the participants have two different native languages. It can also be used to inspire unexpected and playful forms of response.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.002 | 0.006 |
| Open science | 0.009 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it