Papers by Catherine Pelachaud
The ISO Standard for Dialogue Act Annotation, Second Edition (2020.lrec-1)
Copied to clipboard
Harry Bunt, Volha Petukhova, Emer Gilmartin, Catherine Pelachaud, Alex Fang, Simon Keizer, Laurent Prévot
| Challenge: | ISO standard 24617-2 for dialogue act annotation has been used in corpus annotation and in the design of components for spoken and multimodal interactive systems. |
| Approach: | ISO standard 24617-2 for dialogue act annotation is proposed for a second edition . this second edition allows a more accurate annotation of dependence relations and rhetorical relations in dialogue. |
| Outcome: | The proposed second edition of ISO 24617-2 for dialogue act annotation addresses some inaccuracies and undesirable limitations. |
Multimodal Analysis of Cohesion in Multi-party Interactions (2020.lrec-1)
Copied to clipboard
Reshmashree Bangalore Kantharaju, Caroline Langlet, Mukesh Barange, Chloé Clavel, Catherine Pelachaud
| Challenge: | Existing studies have associated group cohesion with performance, team satisfaction and adherence. |
| Approach: | They propose to use 16 two-minute segments annotated with group cohesion from the AMI corpus to analyze their impact on perceived level of cohesicity. |
| Outcome: | The proposed analysis shows that laughter and interruption are higher in high cohesive segments. |
From analysis to modeling of engagement as sequences of multimodal behaviors (L18-1)
Copied to clipboard
| Challenge: | Embodied Conversational Agents (ECAs) are virtual characters that can interact with a user. |
| Approach: | They propose to endow an Embodied Conversational Agent with engagement capabilities . they use a corpus of expert-novice interactions to analyze user's engagement level . |
| Outcome: | The proposed approach analyzes user's engagement level and controls agent's behavior. |
“Mm, Wat?” Detecting Other-initiated Repair Requests in Dialogue (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current conversational agents (CAs) do not recognize repair initiation, leading to breakdowns or disengagement. |
| Approach: | They propose a multimodal model to automatically detect repair initiation in Dutch dialogues by integrating linguistic and prosodic features grounded in Conversation Analysis. |
| Outcome: | The proposed model integrates linguistic and prosodic features grounded in Conversation Analysis to detect repair initiation in Dutch dialogues. |
Beyond Words: Decoding Facial Expression Dynamics in Motivational Interviewing (2024.lrec-main)
Copied to clipboard
| Challenge: | Motivational Interviewing (MI) is a directive, clientcentered therapeutic approach designed to facilitate behaviour change by enhancing individuals' intrinsic motivation. |
| Approach: | They propose to decode facial expressions of both client and therapist in the context of Motivational Interviewing using an annotation system. |
| Outcome: | The proposed method identifies facial expressions of both interlocutors and client over a counseling session and reveals the correlation between the facial expression and the different types of talk, as well as the interplay between interlocutetors’ expressions. |
Annotating Interruption in Dyadic Human Interaction (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing interruption and turn switch classification methods are not yet available. |
| Approach: | They propose a new interruption annotation schema that integrates existing interruption and turn switch classification methods to annotate different types of interruptions. |
| Outcome: | The proposed method can distinguish smooth turn exchange, backchannel and interruption (including interruption types) and to annotate dyadic conversation. |