Saved in:
Bibliographic Details
Main Authors: Ngo, Anh, Rollet, Nicolas, Pelachaud, Catherine, Clavel, Chloe
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.24628
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909873983193088
author Ngo, Anh
Rollet, Nicolas
Pelachaud, Catherine
Clavel, Chloe
author_facet Ngo, Anh
Rollet, Nicolas
Pelachaud, Catherine
Clavel, Chloe
contents Maintaining mutual understanding is a key component in human-human conversation to avoid conversation breakdowns, in which repair, particularly Other-Initiated Repair (OIR, when one speaker signals trouble and prompts the other to resolve), plays a vital role. However, Conversational Agents (CAs) still fail to recognize user repair initiation, leading to breakdowns or disengagement. This work proposes a multimodal model to automatically detect repair initiation in Dutch dialogues by integrating linguistic and prosodic features grounded in Conversation Analysis. The results show that prosodic cues complement linguistic features and significantly improve the results of pretrained text and audio embeddings, offering insights into how different features interact. Future directions include incorporating visual cues, exploring multilingual and cross-context corpora to assess the robustness and generalizability.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24628
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle "Mm, Wat?" Detecting Other-initiated Repair Requests in Dialogue
Ngo, Anh
Rollet, Nicolas
Pelachaud, Catherine
Clavel, Chloe
Computation and Language
Maintaining mutual understanding is a key component in human-human conversation to avoid conversation breakdowns, in which repair, particularly Other-Initiated Repair (OIR, when one speaker signals trouble and prompts the other to resolve), plays a vital role. However, Conversational Agents (CAs) still fail to recognize user repair initiation, leading to breakdowns or disengagement. This work proposes a multimodal model to automatically detect repair initiation in Dutch dialogues by integrating linguistic and prosodic features grounded in Conversation Analysis. The results show that prosodic cues complement linguistic features and significantly improve the results of pretrained text and audio embeddings, offering insights into how different features interact. Future directions include incorporating visual cues, exploring multilingual and cross-context corpora to assess the robustness and generalizability.
title "Mm, Wat?" Detecting Other-initiated Repair Requests in Dialogue
topic Computation and Language
url https://arxiv.org/abs/2510.24628