Training CHIldren reading Comprehension skills with Adapted Artificial Intelligence (CHICA-AI)

Date: 03/2024 - 04/2028
Funding: ANR
Call: AAPG2023
Partners: Lalilo (Toulouse), IRIT (Toulouse), EMC (Lyon)
URL: https://lium.univ-lemans.fr/en/chica-ai/


The 2019 PISA study shows that 20% of French 15-year-old students have severe difficulties in reading and that socio-economic gaps widen the differences in levels. Lalilo intends to reduce these inequalities by developing an online platform based on artificial intelligence to differentiate reading learning. Reading comprehension is the goal of the reading process, and these skills can be developed through training activities, such as text summarization.

We propose to create a Computer-assisted learning (CAL) system to train children from grades 4-5 to produce qualitative oral summaries, by automatically analyzing their production and providing differentiated feedback. Our system will combine automatic speech recognition (ASR), speech language understanding (SLU), and natural language processing while incorporating cognitive science knowledge. The project is organized in three main tasks.

(1) We will create a set of original texts for the summarizing activity, and an evaluation grid based on psycho-cognitive summary assessment grids. Data will be gathered through the Lalilo platform and annotated to train and evaluate the automatic systems.
(2) We will build several ASR and SLU systems to retrieve detailed information for automatically completing the evaluation grid. Acoustic measures, self-supervised speech representations, robustness to noise, named entity recognition, speech-text sentence-level embeddings, topic modeling, and syntactical analysis, will be investigated for these systems.
(3) The CAL intervention will be implemented and evaluated, by constructing automatic scores for each evaluation criterion, validating them against manual annotations and traditional reading comprehension measures, and designing targeted feedback for students and teachers. Finally, the impact of the CAL intervention on students’ learning will be assessed through in-class randomized controlled trials.

 

 

"Grâce à ce projet, nous avons la chance de pouvoir collaborer avec des chercheurs aux compétences variées issus d’un consortium à 4 partenaires : Lalilo, une entreprise qui propose des solutions d’apprentissage de la lecture assistée par ordinateur adaptées à chaque enfant, le laboratoire EMC de Lyon qui étudie les mécanismes cognitifs et l’IRIT, où une équipe travaille sur le traitement automatiquement de la langue naturelle.

Avec Antoine Laurent, nous apporterons à ce projet nos compétences en traitement automatique de la parole, sur les aspects transcription et compréhension. L’objectif du projet est de proposer une activité de résumé oral offrant un retour formatif aux élèves et un rapport détaillé aux enseignants. De nombreux challenges nous attendent afin d’une part de traiter la parole spontanée des jeunes enfants et d’autre part de produire des critères d’évaluation des résumés produits".

Nathalie CAMELIN | Enseignante-chercheure en informatique