Publications
Please check HAL and my Google Scholar webpage for latest publications.
2023
- Dubuisson Duplessis, G.; Richard, M.; Guénet, A.-L., Segmentation de phases de dialogue dans des retranscriptions de conversations de centres d’appels, Conférence Nationale sur les Applications Pratiques de l’Intelligence Artificielle (APIA), 2023, pp. 4p. [More | Slides]
- Dubuisson Duplessis, G.; Bullier, F.; Guénet, A.-L., Démonstration: exploration sémantique de données texte de la relation client, Conférence Nationale sur les Applications Pratiques de l’Intelligence Artificielle (APIA), 2023, pp. 4p. [More | Slides]
2021
- Dubuisson Duplessis, G.; Langlet, C.; Clavel, C.; Landragin, F., Towards alignment strategies in human-agent interactions based on measures of lexical repetitions, Lang Resources & Evaluation, 2021, 36p. [More | DOI | Code]
2020
- Dubuisson Duplessis, G.; Bartholme, E.; Kerroua, S.; Poulain, M.; Roulier, A.; Guénet, A.-L., Désidentification de données texte produites dans un cadre de relation client, 27ème Conférence sur le Traitement Automatique des Langues Naturelles (démonstration), 2020, pp. 4p. [More]
2019
- Dubuisson Duplessis, G.; Kerroua, S.; Kuznik, L.; Guénet, A.-L., Cameli@ : analyses automatiques d’e-mails pour améliorer la relation client, 26ème Conférence sur le Traitement Automatique des Langues Naturelles (démonstration), 2019 [More]
2018
- van Waterschoot, J.; Dubuisson Duplessis, G.; Gatti, L.; Bruijnes, M.; Heylen, D., HAI Alice - An Information-Providing Closed-Domain Dialog Corpus, International Conference on Language Resources and Evaluation (LREC 2018), 2018 [More]
2017
- Dubuisson Duplessis, G.; Charras, F.; Letard, V.; Ligozat, A.-L.; Rosset, S., Utterance Retrieval based on Recurrent Surface Text Patterns, 39th European Conference on Information Retrieval (ECIR), 2017, pp. 199–211 [More | DOI | Code]
- Garcia, M.; Béchade, L.; Dubuisson Duplessis, G.; Pittaro, G.; Devillers, L., Towards Metrics of Evaluation of Pepper Robot as a Social Companion for Elderly People, International Workshop on Spoken Dialogue Systems (IWSDS), 2017, pp. 8p. [More]
- Devillers, Laurence; Dubuisson Duplessis, Guillaume, Toward a Context-Based Approach to Assess Engagement in Human-Robot Social Interaction, Dialogues with Social Robots, 2017, pp. 293–301 [DOI]
- Louvet, J.-B.; Chaignaud, N.; Vercouter, L.; Dubuisson Duplessis, G.; Kotowicz, J-Ph, Modélisation d’une tâche collaborative à l’aide d’engagements sociaux, Journées Francophones sur les Systèmes Multi-Agents (JFSMA), 2017, pp. 2p. (poster) [More]
- Louvet, J.-B.; Dubuisson Duplessis, G.; Chaignaud, N.; Kotowicz, J-Ph; Vercouter, L., Modeling a Collaborative Task with Social Commitments, 21st International Conference on Knowledge Based and Intelligent Information and Engineering Systems (KES17), 2017, pp. 377–386 [More | DOI]
- Dubuisson Duplessis, G.; Clavel, C.; Landragin, F., Automatic Measures to Characterise Verbal Alignment in Human-Agent Interaction, 18th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), 2017, pp. 71–81 [More | Code | Slides]
- Dubuisson Duplessis, G.; Pauchet, A.; Chaignaud, N.; Kotowicz, J-Ph., A Conventional Dialogue Model based on Dialogue Patterns, International Journal on Artificial Intelligence Tools (IJAIT), 2017, 26, pp. 23p. [More | DOI | Code]
2016
- Charras, F.; Dubuisson Duplessis, G.; Letard, V.; Ligozat, A.-L.; Rosset, S., Un système automatique de sélection de réponse en domaine ouvert intégrable à un système de dialogue social, 23ème Conférence sur le Traitement Automatique des Langues Naturelles (démonstration), 2016, pp. 46–48 [More]
- Devillers, L.; Dubuisson Duplessis, G., Toward a Context-based Approach to Assess Engagement in Human-Robot Social Interaction, International Workshop on Spoken Dialogue Systems (IWSDS), 2016, pp. 8p. [DOI]
- Louvet, J.-B.; Dubuisson Duplessis, G.; Chaignaud, N.; Kotowicz, J-Ph; Vercouter, L., Recherche collaborative de documents : comparaison assistance humaine/automatique., 27ème Journées francophones d’Ingénierie des Connaissances (IC2016), 2016, pp. 6p. [More]
- Dubuisson Duplessis, G.; Letard, V.; Ligozat, A.-L.; Rosset, S., Purely Corpus-based Automatic Conversation Authoring, Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), 2016 [More | Corpus]
- Dubuisson Duplessis, G.; Letard, V.; Ligozat, A.-L.; Rosset, S., Joker Chatterbot – Shared Task Chatbot Description Report, Workshop on Collecting and Generating Resources for Chatbots and Conversational Agents - Development and Evaluation (RE-WOCHAT) @LREC, 2016, pp. 2p. [More]
- Béchade, L.; Delaborde, A.; Dubuisson Duplessis, G.; Devillers, L., Ethical Considerations and Feedback from Social Human-Robot Interaction with Elderly People, ETHics In Corpus collection, Annotation and Application (ETHI-CA2) @LREC, 2016
- Bechade, L.; Dubuisson Duplessis, G.; Devillers, L., Empirical Study of Humor Support in Social Human-Robot Interaction, Distributed, Ambient and Pervasive Interactions: 4th International Conference, DAPI 2016, Held as Part of HCI International 2016, Toronto, ON, Canada, July 17-22, 2016, Proceedings, 2016, pp. 305–316 [More | DOI]
- Charras, F.; Dubuisson Duplessis, G.; Letard, V.; Ligozat, A.-L.; Rosset, S., Comparing System-response Retrieval Models for Open-domain and Casual Conversational Agent, Second Workshop on Chatbots and Conversational Agent Technologies (WOCHAT@IVA2016), 2016, pp. 12p. [More]
2015
- Dubuisson Duplessis, G.; Devillers, L., Towards the Consideration of Dialogue Activities in Engagement Measures for Human-Robot Social Interaction, Designing & Evaluating Social Robots for Public Settings Workshop @ IROS 2015, 2015, pp. 19-24 [More]
- Dubuisson Duplessis, G.; Devillers, L., Towards Engagement Measures Using Dialogue Activities in Social Interaction, 3rd European Symposium on Multimodal Communication, 2015, pp. 2p. [More]
- Dubuisson Duplessis, G.; Béchade, L.; Sehili, M. A.; Delaborde, A.; Letard, V.; Ligozat, A.-L.; Del\ǵlise, P.; Estève, Y.; Rosset, S.; Devillers, L., Nao is doing humour in the CHIST-ERA JOKER project, Interspeech Show & Tell, 2015, pp. 1072-1073 [More]
- Devillers, L.; Rosset, S.; Dubuisson Duplessis, G.; Sehili, M. A.; Béchade, L.; Delaborde, A.; Gossart, C.; Letard, V.; Yang, F.; Yemez, Y.; Türker, B. B.; Sezgin, M.; El Haddad, K.; Dupont, S.; Luzzati, D.; Estève, Y.; Gilmartin, E.; Campbell, N., Multimodal Data Collection of Human-Robot Humorous Interactions in the JOKER Project, 6th International Conference on Affective Computing and Intelligent Interaction (ACII 2015), 2015, pp. 348-354 [DOI]
- Béchade, L.; Dubuisson Duplessis, G.; Sehili, M. A.; Devillers, L., Behavioral and emotional spoken cues related to mental states in Human-Robot social interaction, 17th ACM International Conference on Multimodal Interaction (ICMI 2015), 2015, pp. 347-350 [More | DOI]
- Dubuisson Duplessis, G.; Pauchet, A.; Chaignaud, N.; Kotowicz, J-Ph., A Conventional Dialogue Model based on Empirically Specified Dialogue Games, 27th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2015), 2015, pp. 997-1004 [More | DOI | Code]
2013
- Dubuisson Duplessis, G.; Chaignaud, N.; Kotowicz, J-Ph.; Pauchet, A., Spécification empirique de jeux de dialogue pour un agent interactif., Septième Journées Francophones sur les Mod\l̀es Formels d’Interaction (MFI-2013), 2013 [More]
- Dubuisson Duplessis, G.; Chaignaud, N.; Kotowicz, J-Ph.; Pauchet, A.; Pécuchet, J-P., Empirical Specification of Dialogue Games for an Interactive Agent, Proceedings of the 11th International Conference on Practical Applications of Agents and Multi-Agent Systems (PAAMS), 2013, LNAI 7879, pp. 49–60 [More | DOI]
2012
- Ales, Z.; Dubuisson Duplessis, G.; Serban, O.; Pauchet, A., A Methodology to Design Human-Like Embodied Conversational Agents, AAMAS 2012 Workshop, Human-Agent Interaction Design and Models, 2012, pp. 34–49 [More]
- Loisel, A.; Dubuisson Duplessis, G.; Chaignaud, N.; Kotowicz, J-Ph, A Conversational Agent for Information Retrieval Based on a Study of Human Dialogues, Proceedings of the 4th International Conference on Agents and Artificial Intelligence, 2012, 1, pp. 312-317 [More]
2011
- Loisel, A.; Dubuisson Duplessis, G.; Chaignaud, N.; Kotowicz, J-Ph, Un système de dialogue fondé sur l’\t́ude d’interactions humaines., Sixième Journées Francophones sur les Mod\l̀es Formels d’Interaction (MFI-2011), 2011 [More]
PhD thesis
My PhD thesis is written in French. Its title can be translated in English as follows: “A Conventional Communicative Behaviour Model for an Agent Interacting with Humans”.
- Dubuisson Duplessis, G., Modèle de comportement communicatif conventionnel pour un agent en interaction avec des humains : approche par jeux de dialogue, PhD thesis, INSA de Rouen, 2014 [More].
Thesis Jury
- Frédéric Landragin
- Nicolas Sabouret
- Catherine Pelachaud
- Jean-Christophe Routier
- Jean-Pierre Pécuchet
- Nathalie Chaignaud
- Jean-Philippe Kotowicz
Abstract
This research work aims at improving the communicative behaviour of software agents interacting with humans. To this purpose, we present a data-driven methodology based on the study of a task-oriented corpus consisting of Human-Human interactions. This corpus is processed in two main steps : its enrishment through an annotation phase and a regularity extraction phase. Our research work focuses on interaction patterns, that is to say regularities observed at the level of dialogical interaction. We study high-level structures that can be specified from these patterns. These structures form the basis of the interaction model for an agent that can be integrated into a deliberative process. We present a framework to specify dialogue games from these patterns based on the notion of social commitments and conversational gameboard. This framework is independent of the private states of interacting agents. We exemplify the specification of dialogue games by implementing all the steps of our methodology on a task-oriented corpus. The produced games are validated by showing that they appropriately describe the patterns appearing in a reference corpus. Eventually, we show that an agent can take advantage of our model to regulate its conventional communicative behaviour on both interpretative and generative levels. We implement this model into Dogma, a module that can be used by an agent to manage its communicative behaviour in a two-interlocutor dialogue.