@inproceedings{brutti-pustejovsky-2026-oh,
title = "More than ``Oh'': Grounding Observable Events with Grunts in Multimodal Dialogue",
author = "Brutti, Richard A. and
Pustejovsky, James",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.132/",
doi = "10.63317/43opy9tsucf3",
pages = "1677--1687",
abstract = "Conversational grunts (minimal vocalizations like oh, mm-hm, and uh-huh) ground information and coordinate understanding in human dialogue, yet computational systems typically treat them as noise rather than meaningful communicative acts. We present a systematic annotation and analysis of 497 grunts across 3 hours of multimodal collaborative tasks, introducing an annotation scheme that captures grunts, their antecedents, and dialogue act functions. Our analysis reveals that grunts respond to speech and observable events at nearly equal rates, demonstrating that non-verbal events function as conversational contributions requiring acknowledgment. Tokens exhibit functional specialization: mm-hm predominantly acknowledges speech, while oh preferentially acknowledges events. Prosodic analysis shows speakers systematically modulate duration and pitch based on antecedent type, with event responses typically longer and having greater range. These findings have implications for dialogue state tracking, multimodal grounding, and turn-taking in conversational AI systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brutti-pustejovsky-2026-oh">
<titleInfo>
<title>More than “Oh”: Grounding Observable Events with Grunts in Multimodal Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Brutti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conversational grunts (minimal vocalizations like oh, mm-hm, and uh-huh) ground information and coordinate understanding in human dialogue, yet computational systems typically treat them as noise rather than meaningful communicative acts. We present a systematic annotation and analysis of 497 grunts across 3 hours of multimodal collaborative tasks, introducing an annotation scheme that captures grunts, their antecedents, and dialogue act functions. Our analysis reveals that grunts respond to speech and observable events at nearly equal rates, demonstrating that non-verbal events function as conversational contributions requiring acknowledgment. Tokens exhibit functional specialization: mm-hm predominantly acknowledges speech, while oh preferentially acknowledges events. Prosodic analysis shows speakers systematically modulate duration and pitch based on antecedent type, with event responses typically longer and having greater range. These findings have implications for dialogue state tracking, multimodal grounding, and turn-taking in conversational AI systems.</abstract>
<identifier type="citekey">brutti-pustejovsky-2026-oh</identifier>
<identifier type="doi">10.63317/43opy9tsucf3</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.132/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1677</start>
<end>1687</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T More than “Oh”: Grounding Observable Events with Grunts in Multimodal Dialogue
%A Brutti, Richard A.
%A Pustejovsky, James
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F brutti-pustejovsky-2026-oh
%X Conversational grunts (minimal vocalizations like oh, mm-hm, and uh-huh) ground information and coordinate understanding in human dialogue, yet computational systems typically treat them as noise rather than meaningful communicative acts. We present a systematic annotation and analysis of 497 grunts across 3 hours of multimodal collaborative tasks, introducing an annotation scheme that captures grunts, their antecedents, and dialogue act functions. Our analysis reveals that grunts respond to speech and observable events at nearly equal rates, demonstrating that non-verbal events function as conversational contributions requiring acknowledgment. Tokens exhibit functional specialization: mm-hm predominantly acknowledges speech, while oh preferentially acknowledges events. Prosodic analysis shows speakers systematically modulate duration and pitch based on antecedent type, with event responses typically longer and having greater range. These findings have implications for dialogue state tracking, multimodal grounding, and turn-taking in conversational AI systems.
%R 10.63317/43opy9tsucf3
%U https://aclanthology.org/2026.lrec-1.132/
%U https://doi.org/10.63317/43opy9tsucf3
%P 1677-1687
Markdown (Informal)
[More than "Oh": Grounding Observable Events with Grunts in Multimodal Dialogue](https://aclanthology.org/2026.lrec-1.132/) (Brutti & Pustejovsky, LREC 2026)
ACL