Papers by Catherine Pelachaud

6 papers
The ISO Standard for Dialogue Act Annotation, Second Edition (2020.lrec-1)

Copied to clipboard

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations