@inproceedings{hotti-etal-2026-building,
title = "Building Multimodal Corpora Using Microtask Pipelines and Local Annotators",
author = "Hotti, Helmiina and
Vazquez, Raul and
Jokipohja, Anna-Kaisa and
Kalliokoski, Timo and
Paakki, Henna and
Suviranta, Rosa and
Hiippala, Tuomo",
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-1.514/",
doi = "10.63317/434uxg6yj2aj",
pages = "6483--6495",
abstract = "Multimodality, or how human communication and interaction combine multiple forms of expression, is studied across diverse fields of research. Many of these fields have underlined the need for large, richly annotated multimodal corpora to support empirical research. While language resources are increasingly annotated using microtask crowdsourcing, multimodal corpora remain largely reliant on expert annotators, which creates a bottleneck for scalability and broad applicability. This paper presents a novel hybrid approach to multimodal corpus annotation, leveraging the efficiency of microtask pipelines while preserving theoretical rigour. Our approach decomposes the annotation process into sequences of simple, well-instructed tasks, which are then performed by locally recruited non-expert annotators. We demonstrate the feasibility of this approach by presenting a pipeline for annotating the multimodal structure of school textbooks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hotti-etal-2026-building">
<titleInfo>
<title>Building Multimodal Corpora Using Microtask Pipelines and Local Annotators</title>
</titleInfo>
<name type="personal">
<namePart type="given">Helmiina</namePart>
<namePart type="family">Hotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raul</namePart>
<namePart type="family">Vazquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna-Kaisa</namePart>
<namePart type="family">Jokipohja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timo</namePart>
<namePart type="family">Kalliokoski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henna</namePart>
<namePart type="family">Paakki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rosa</namePart>
<namePart type="family">Suviranta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tuomo</namePart>
<namePart type="family">Hiippala</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>Multimodality, or how human communication and interaction combine multiple forms of expression, is studied across diverse fields of research. Many of these fields have underlined the need for large, richly annotated multimodal corpora to support empirical research. While language resources are increasingly annotated using microtask crowdsourcing, multimodal corpora remain largely reliant on expert annotators, which creates a bottleneck for scalability and broad applicability. This paper presents a novel hybrid approach to multimodal corpus annotation, leveraging the efficiency of microtask pipelines while preserving theoretical rigour. Our approach decomposes the annotation process into sequences of simple, well-instructed tasks, which are then performed by locally recruited non-expert annotators. We demonstrate the feasibility of this approach by presenting a pipeline for annotating the multimodal structure of school textbooks.</abstract>
<identifier type="citekey">hotti-etal-2026-building</identifier>
<identifier type="doi">10.63317/434uxg6yj2aj</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.514/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>6483</start>
<end>6495</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Multimodal Corpora Using Microtask Pipelines and Local Annotators
%A Hotti, Helmiina
%A Vazquez, Raul
%A Jokipohja, Anna-Kaisa
%A Kalliokoski, Timo
%A Paakki, Henna
%A Suviranta, Rosa
%A Hiippala, Tuomo
%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 hotti-etal-2026-building
%X Multimodality, or how human communication and interaction combine multiple forms of expression, is studied across diverse fields of research. Many of these fields have underlined the need for large, richly annotated multimodal corpora to support empirical research. While language resources are increasingly annotated using microtask crowdsourcing, multimodal corpora remain largely reliant on expert annotators, which creates a bottleneck for scalability and broad applicability. This paper presents a novel hybrid approach to multimodal corpus annotation, leveraging the efficiency of microtask pipelines while preserving theoretical rigour. Our approach decomposes the annotation process into sequences of simple, well-instructed tasks, which are then performed by locally recruited non-expert annotators. We demonstrate the feasibility of this approach by presenting a pipeline for annotating the multimodal structure of school textbooks.
%R 10.63317/434uxg6yj2aj
%U https://aclanthology.org/2026.lrec-1.514/
%U https://doi.org/10.63317/434uxg6yj2aj
%P 6483-6495
Markdown (Informal)
[Building Multimodal Corpora Using Microtask Pipelines and Local Annotators](https://aclanthology.org/2026.lrec-1.514/) (Hotti et al., LREC 2026)
ACL