@inproceedings{viridiano-etal-2022-case,
title = "The Case for Perspective in Multimodal Datasets",
author = "Viridiano, Marcelo and
Timponi Torrent, Tiago and
Czulo, Oliver and
Lorenzi, Arthur and
Matos, Ely and
Belcavello, Frederico",
editor = "Abercrombie, Gavin and
Basile, Valerio and
Tonelli, Sara and
Rieser, Verena and
Uma, Alexandra",
booktitle = "Proceedings of the 1st Workshop on Perspectivist Approaches to NLP @LREC2022",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.nlperspectives-1.14",
pages = "108--116",
abstract = "This paper argues in favor of the adoption of annotation practices for multimodal datasets that recognize and represent the inherently perspectivized nature of multimodal communication. To support our claim, we present a set of annotation experiments in which FrameNet annotation is applied to the Multi30k and the Flickr 30k Entities datasets. We assess the cosine similarity between the semantic representations derived from the annotation of both pictures and captions for frames. Our findings indicate that: (i) frame semantic similarity between captions of the same picture produced in different languages is sensitive to whether the caption is a translation of another caption or not, and (ii) picture annotation for semantic frames is sensitive to whether the image is annotated in presence of a caption or not.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="viridiano-etal-2022-case">
<titleInfo>
<title>The Case for Perspective in Multimodal Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcelo</namePart>
<namePart type="family">Viridiano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiago</namePart>
<namePart type="family">Timponi Torrent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Czulo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arthur</namePart>
<namePart type="family">Lorenzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ely</namePart>
<namePart type="family">Matos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederico</namePart>
<namePart type="family">Belcavello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Perspectivist Approaches to NLP @LREC2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gavin</namePart>
<namePart type="family">Abercrombie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Tonelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verena</namePart>
<namePart type="family">Rieser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Uma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper argues in favor of the adoption of annotation practices for multimodal datasets that recognize and represent the inherently perspectivized nature of multimodal communication. To support our claim, we present a set of annotation experiments in which FrameNet annotation is applied to the Multi30k and the Flickr 30k Entities datasets. We assess the cosine similarity between the semantic representations derived from the annotation of both pictures and captions for frames. Our findings indicate that: (i) frame semantic similarity between captions of the same picture produced in different languages is sensitive to whether the caption is a translation of another caption or not, and (ii) picture annotation for semantic frames is sensitive to whether the image is annotated in presence of a caption or not.</abstract>
<identifier type="citekey">viridiano-etal-2022-case</identifier>
<location>
<url>https://aclanthology.org/2022.nlperspectives-1.14</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>108</start>
<end>116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Case for Perspective in Multimodal Datasets
%A Viridiano, Marcelo
%A Timponi Torrent, Tiago
%A Czulo, Oliver
%A Lorenzi, Arthur
%A Matos, Ely
%A Belcavello, Frederico
%Y Abercrombie, Gavin
%Y Basile, Valerio
%Y Tonelli, Sara
%Y Rieser, Verena
%Y Uma, Alexandra
%S Proceedings of the 1st Workshop on Perspectivist Approaches to NLP @LREC2022
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F viridiano-etal-2022-case
%X This paper argues in favor of the adoption of annotation practices for multimodal datasets that recognize and represent the inherently perspectivized nature of multimodal communication. To support our claim, we present a set of annotation experiments in which FrameNet annotation is applied to the Multi30k and the Flickr 30k Entities datasets. We assess the cosine similarity between the semantic representations derived from the annotation of both pictures and captions for frames. Our findings indicate that: (i) frame semantic similarity between captions of the same picture produced in different languages is sensitive to whether the caption is a translation of another caption or not, and (ii) picture annotation for semantic frames is sensitive to whether the image is annotated in presence of a caption or not.
%U https://aclanthology.org/2022.nlperspectives-1.14
%P 108-116
Markdown (Informal)
[The Case for Perspective in Multimodal Datasets](https://aclanthology.org/2022.nlperspectives-1.14) (Viridiano et al., NLPerspectives 2022)
ACL
- Marcelo Viridiano, Tiago Timponi Torrent, Oliver Czulo, Arthur Lorenzi, Ely Matos, and Frederico Belcavello. 2022. The Case for Perspective in Multimodal Datasets. In Proceedings of the 1st Workshop on Perspectivist Approaches to NLP @LREC2022, pages 108–116, Marseille, France. European Language Resources Association.