Home // eKNOW 2023, The Fifteenth International Conference on Information, Process, and Knowledge Management // View article
Authors:
Adel Jebali
Keywords: French L2; Object pronoun clitics; deep learning; CamemBERT; model
Abstract:
Object clitic pronouns (particularly third person pronouns) in French are problematic for second and foreign language learners. As a result, several researchers, such as [1], have observed that French second language (L2) learners frequently use avoidance strategies to avoid using these forms, even when doing so allows them to lighten their discourse (written or oral) by avoiding repetition. This is one of the reasons we were interested in technological tools that could assist these learners in comprehending these clitics. We therefore conducted a study with a tripartite goal: to uncover a corpus of L2 French productions focusing on clitics, to use this corpus to train a state-of-the-art deep learning model (CamemBERT), and to implement the trained model to detect learners' errors when producing the forms under study. This model was found to be over 99% reliable when tested. Furthermore, when evaluated on sentences with different turns of phrase than those encountered during training, the model detects errors with the same degree of reliability. This model constitutes a significant advancement in the automatic processing of interlanguage and can be used to develop tools for French L2 learners.
Pages: 28 to 32
Copyright: Copyright (c) IARIA, 2023
Publication date: April 24, 2023
Published in: conference
ISSN: 2308-4375
ISBN: 978-1-68558-082-7
Location: Venice, Italy
Dates: from April 24, 2023 to April 28, 2023