A5037949367- Natural Language Processing Techniques
- Second Language Acquisition and Learning
- Text Readability and Simplification
- French Language Learning Methods
- Linguistics and Discourse Analysis
- Topic Modeling
- Linguistics, Language Diversity, and Identity
- Second Language Learning and Teaching
- Lexicography and Language Studies
- EFL/ESL Teaching and Learning
- Advanced Text Analysis Techniques
- linguistics and terminology studies
- Sentiment Analysis and Opinion Mining
- Educational Technology and Assessment
- Historical Linguistics and Language Studies
- Linguistic Variation and Morphology
- Discourse Analysis in Language Studies
- Online Learning and Analytics
- Educational Tools and Methods
- Translation Studies and Practices
- Language, Metaphor, and Cognition
- Cognitive Computing and Networks
- Linguistic and Sociocultural Studies
- Social Sciences and Governance
- Semantic Web and Ontologies
Université de Rennes
2018-2024
Université Rennes 2
2018-2024
Laboratoire de Linguistique et Didactique des Langues Etrangères et Maternelles
2011-2023
Laboratoire de Linguistique Formelle
2014-2020
Université Paris Cité
2013-2020
Ollscoil na Gaillimhe – University of Galway
2018-2019
Insight (China)
2018
Laboratoire de Recherche sur la Croissance Cellulaire, la Réparation et la Régénération Tissulaires
2013
Abstract This paper focuses on automatically assessing language proficiency levels according to linguistic complexity in learner English. We implement a supervised learning approach as part of an automatic essay scoring system. The objective is uncover Common European Framework Reference for Languages (CEFR) criterial features writings by learners English foreign language. Our method relies the concept microsystems with related learner-specific systems which several forms operate...
Abstract This paper discusses machine learning techniques for the prediction of Common European Framework Reference (CEFR) levels in a learner corpus. We summarise CAp 2018 Machine Learning (ML) competition, classification task six CEFR levels, which map linguistic competence foreign language onto reference levels. The goal this competition was to produce system predict learners’ from written productions comprising between 20 and 300 words set characteristics computed each text extracted...
This paper analyses the contribution of language metrics and, potentially, linguistic structures, to classify French learners English according levels Common European Framework Reference for Languages (CEFRL). The purpose is build a model prediction learner as function complexity features. We used EFCAMDAT corpus, database one million written assignments by learners. After applying on texts, we built representation matching texts their assigned CEFRL levels. Lexical and syntactic were...
This paper focuses on aspect extraction which is a sub-task of Aspect-based Sentiment Analysis. The goal to report an method financial aspects in microblog messages. Our approach uses stock-investment taxonomy for the identification explicit and implicit aspects. We compare supervised unsupervised methods assign predefined categories at message level. Results 7 classes show 0.71 accuracy, while 32 class classification gives 0.82 accuracy messages containing 0.35
Cet article analyse les caractéristiques distributionnelles des deux démonstratifs « this » et that afin d’identifier usages spécifiques en fonction de domaines spécialisés l’anglais. Les données sont collectées dans le corpus ICE-GB. L’étude consiste à échantillonner sous-corpus, du domaine spécialisé mode écrit ou oral textes. sous-corpus relevant l’anglais général distingués ceux (médecine, science technologie). Pour chaque l’outil ICECUP est utilisé pour effectuer requêtes extraire...
This paper focuses on the creation of LLM-based artificial learners. Motivated by capability language models to encode representation, we evaluate such in predicting masked tokens learner corpora. We pre-trained two models, one a training set EFCAMDAT (natural model) and another C4200m dataset (syntehtic model), evaluating them against native model using an external corpora English for Specific purposes corpus French undergraduates (CELVA) as test set. measured metrics related accuracy,...
Cet article aborde la problématique de construction d’un didacticiel d’apprentissage l’anglais dans le cadre mise en place programme d’auto-formation guidée conjuguant travail à distance et présentiel. L’objectif est proposer une approche novatrice conception scénario d’apprentissage, savoir nécessité combiner un déroulement pédagogique lequel l’apprenant puise sens son travail, linguistique assurant l’assimilation compétences linguistiques. L’approche défend l’idée que processus...