3. Natural language processing tools and CALL
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
Dans ce chapitre, nous nous proposons d’examiner la contribution du Traitement Automatique du Langage (TAL) en Apprentissage des Langues Assisté par Ordinateur (ALAO) avec une perspective sur l’enseignement du français. Le chapitre comporte deux sections principales. Dans la première, nous traitons de Tuteurs Intelligents (TI) puis, nous nous concentrons sur les TIs dédiés à l’apprentissage de la langue. On verra que dans ces systèmes d’Apprentissage des Langues Intelligemment Assisté par Ordinateur (ALIAO), les techniques de TAL occupent une place centrale, notamment celle de ‘parsing’. Notre deuxième section est consacrée à la description d’un système d’ALIAO nommé FreeText, qui vise des apprenants du français langue seconde de niveau intermédiaire à avancé. Il s’agit d’un riche environnement d’ALAO qui comprend un ensemble d’outils de TAL, lesquels ont été adaptés pour permettre de fournir aux apprenants un diagnostic ‘astucieux’ de leur intrant langagier. Nous concluons ce chapitre en discutant des avantages, dans le contexte de l’apprentissage d’une langue, du contact des apprenants avec les outils de TAL tels ceux développés dans FreeText. This chapter examines the contribution of Natural Language Processing (NLP) in Computer-Assisted Language Learning (CALL), in the perspective of French language instruction. It is divided into two main sections. The first presents an overview on Intelligent Tutoring Systems (ITS) and then describes a specific type of ITS, the Intelligent Language Tutor (ILT), where Natural Language Processing techniques, namely parsing, are core. The second main section focuses on one such ILT system called FreeText which is dedicated to intermediate-advanced learners of French as a second language. It is an enhanced CALL environment comprising a set of NLP tools, which have been adapted to provide FSL learners with a ‘smart’ diagnosis of their language input. The chapter concludes with a look at the overall benefit, within a language learning context, of learners’ exposure to the use of NLP tools, such as those found in FreeText.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.007 |
| 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