serge.bibauw.beSerge

Bibauw Search Bibauw Bibauw About Publications Talks Projects Contact Light Dark Automatic Bibauw Assistant Professor of French Language Teaching University of Louvain (UCLouvain) About me I am an Assistant Professor of French Language Teaching at the University of Louvain ( UCLouvain ), in Louvain-la-Neuve, Belgium. I am affiliated with the Institute for the Analysis of Change in Contemporary and Historical Societies ( IACCHOS ) and the Centre de recherche interdisciplinaire sur les pratiques enseignantes et les disciplines scolaires ( Cripedis ). I study conversational AI for language learning, or dialogue-based CALL, more precisely task-oriented dialogue systems (chatbots) for language learning, at the intersection of computer-assisted language learning (CALL) and natural language processing (NLP). My research focuses on the instructional design and the evaluation of the effectiveness of dialogue-based CALL systems for L2 proficiency development, particularly L2 vocabulary and fluency. Interests Conversational AI/chatbots for language learning Quantitatively measuring L2 proficiency L2 writing fluency Foreign language teaching Natural language processing for CALL (ICALL) Education PhD in Linguistics, 2022 KU Leuven Agrégation in Romance Languages, 2007 UCLouvain MA in Romance Languages, 2007 UCLouvain BA in Romance Languages, 2004 Université Saint-Louis Selected publications Bibauw , Wim Van Den Noortgate , Thomas François , Piet Desmet August, 2022 Language Learning & Technology, 26 (1), 1-24 Dialogue systems for language learning: a meta-analysis A meta-analysis of effectiveness studies on dialogue-based CALL, based on 17 studies and $k = 100$ individual effect sizes. We use Morris and DeShon’s (2002) formulas to compute comparable effect sizes across designs, and analyse them through a multilevel random-effects model. Results confirm that dialogue-based CALL practice has a significant medium effect size on L2 proficiency development ($d = 0.59$). Extensive moderator analyses on several learning outcomes of different types and features of dialogue-based CALL (type of interaction, modality, agent embodiment, etc.) confirm the effectiveness of form-focused and goal-oriented systems, system-guided interactions, corrective feedback provision, and gamification features. Significant effects for lower proficiency learners, and on vocabulary, morphosyntax, holistic proficiency and accuracy are established. PDF Cite Dataset Project DOI PDF preprint Journal Bibauw , Thomas François , Piet Desmet February, 2022 In Ziegler & González-Lloret (Eds), The Routledge Handbook of Second Language Acquisition & Technology , 121-134 Dialogue systems for language learning: chatbots and beyond Dialogue systems allow a user to interact, orally or in writing, with an automated interlocutor, whether it is referred to as a chatbot, a robot, a conversational agent or an intelligent personal assistant. We discuss the different typologies of dialogue-based computer-assisted language learning (CALL), the natural language processing (NLP) technology operating those systems, and the issues of their instructional design. We review the scientific findings on the cognitive, behavioral, and emotional effects of dialogue systems. Finally, we provide recommendations for the use of dialogue-based CALL in foreign language learning and teaching, as well as for the development of new conversational applications. Cite Project DOI PDF preprint Book chapter Bibauw , Thomas François , Piet Desmet February, 2019 Computer Assisted Language Learning, 32 (8), 827-877 Discussing with a computer to practice a foreign language: Research synthesis and conceptual framework of dialogue-based CALL This article presents the results of a systematic review of the literature on dialogue-based CALL. Applications allowing a learner to have a conversation in a foreign language with a computer have been studied under different traditions ( intelligent tutoring systems , dialogue systems , conversational agents , chatbots …). We attempt to offer a structured overview of these efforts into a conceptual framework, including an operational definition of dialogue-based CALL and a typology of systems (4 types: narrative, form-focused, goal-oriented and reactive systems) and types of dialogue, with their corresponding interactional, instructional and technological traits. We summarize the main results from empirical studies on such systems, and discuss the impact of dialogue-based CALL on motivation and L2 development. Cite Project DOI PDF postprint Journal Recent publications Find relevant content by filtering publications . Anaïs Tack , Ekaterina Kochmar , Zheng Yuan , Bibauw , Chris Piech (2023). The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues . In Proc. BEA 2023 , 785–795. PDF Cite DOI Proceedings Bibauw , Wim Van Den Noortgate , Thomas François , Piet Desmet (2022). Dialogue systems for language learning: a meta-analysis . Language Learning & Technology, 26 (1), 1-24. PDF Cite Dataset Project DOI PDF preprint Journal Bibauw (2022). Learning with conversational AI: Design and effectiveness of dialogue-based computer-assisted language learning . Doctoral dissertation. KU Leuven. Project Bibauw , Thomas François , Piet Desmet (2022). Dialogue systems for language learning: chatbots and beyond . In Ziegler & González-Lloret (Eds), The Routledge Handbook of Second Language Acquisition & Technology , 121-134. Cite Project DOI PDF preprint Book chapter Bibauw , Thomas François , Piet Desmet (2019). Discussing with a computer to practice a foreign language: Research synthesis and conceptual framework of dialogue-based CALL . Computer Assisted Language Learning, 32 (8), 827-877. Cite Project DOI PDF postprint Journal See all publications Recent and upcoming talks Apprendre les langues à l’ère de ChatGPT : quels rôles pour l’apprenant, l’enseignant et l’IA ? Les avancées récentes des intelligences artificielles (IA) génératives ont donné lieu à de nombreuses discussions sur leur rôle en éducation (Romero et al, 2023), menaçant même pour certains le rôle de l’enseignant. 19 April 2024 14:00 — 14:30 Université de Liège S. Bibauw Slides The Use of Chatbots to Enhance Students’ Speaking Ability 27 March 2024 14:00 — 17:30 UCLouvain Saint-Louis Bruxelles S. Bibauw Language Learning with Conversational AI This breakout session provides a brief overview of scientific research into the use of conversational AI (such as ChatGPT) in language … 20 March 2024 14:15 — 15:00 BUDA Kortrijk A. Tack , S. Bibauw Which interactivity matters in TSLL? Agency, engagement and negotiation in conversational AI Abstract BACKGROUND. Interactivity has been defined in various ways: in instructed SLA, as distinguishing dialogic tasks from monologic ones (Ellis et al., 1994); in game design, as involving agency and user control. 20 October 2023 09:30 — 10:00 Iowa State University S. Bibauw Project Slides Chatbots in het onderwijs: wat is (niet) mogelijk? Deze sessie biedt een beknopt overzicht van het wetenschappelijk onderzoek naar het gebruik van chatbots en generatieve taalmodellen (zoals ChatGPT) in het (taal)onderwijs. De sessie verloopt als volgt: Je krijgt een korte, technische introductie in dialoogsystemen. 5 October 2023 11:15 — 12:45 KU Leuven Kulak A. Tack , S. Bibauw See all events Research projects * All Dialogue systems Current Task-based dialogue systems for language learning Doctoral research project at KU Leuven, funded by a SENESCYT scholarship (Ecuador) Reflexive writing at the high-school to university transition FNRS-FRFC research project from 2008 to 2010 at UCLouvain Popular Topics Active Artificial Intelligence Dialogue Systems dialogue-based CALL Educational Technology En Español En Français Experimental Evaluation Fluency Français Langue Étrangère Interactivity Invited Keynote Language Learning Literature Review Meta-Analysis Neural Networks Reflexive Writing Research Methods...