@inproceedings{bylinina-etal-2023-leverage,
title = "Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word Representations",
author = "Tikhonov, Alexey and
Bylinina, Lisa and
Paperno, Denis",
editor = "Palmer, Alexis and
Camacho-collados, Jose",
booktitle = "Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.starsem-1.2",
doi = "10.18653/v1/2023.starsem-1.2",
pages = "11--17",
abstract = "Multimodal embeddings aim to enrich the semantic information in neural representations of language compared to text-only models. While different embeddings exhibit different applicability and performance on downstream tasks, little is known about the systematic representation differences attributed to the visual modality. Our paper compares word embeddings from three vision-and-language models (CLIP, OpenCLIP and Multilingual CLIP, Radford et al. 2021; Ilharco et al. 2021; Carlsson et al. 2022) and three text-only models, with static (FastText, Bojanowski et al. 2017) as well as contextual representations (multilingual BERT Devlin et al. 2018; XLM-RoBERTa, Conneau et al. 2019). This is the first large-scale study of the effect of visual grounding on language representations, including 46 semantic parameters. We identify meaning properties and relations that characterize words whose embeddings are most affected by the inclusion of visual modality in the training data; that is, points where visual grounding turns out most important. We find that the effect of visual modality correlates most with denotational semantic properties related to concreteness, but is also detected for several specific semantic classes, as well as for valence, a sentiment-related connotational property of linguistic expressions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bylinina-etal-2023-leverage">
<titleInfo>
<title>Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Tikhonov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Bylinina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Paperno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal embeddings aim to enrich the semantic information in neural representations of language compared to text-only models. While different embeddings exhibit different applicability and performance on downstream tasks, little is known about the systematic representation differences attributed to the visual modality. Our paper compares word embeddings from three vision-and-language models (CLIP, OpenCLIP and Multilingual CLIP, Radford et al. 2021; Ilharco et al. 2021; Carlsson et al. 2022) and three text-only models, with static (FastText, Bojanowski et al. 2017) as well as contextual representations (multilingual BERT Devlin et al. 2018; XLM-RoBERTa, Conneau et al. 2019). This is the first large-scale study of the effect of visual grounding on language representations, including 46 semantic parameters. We identify meaning properties and relations that characterize words whose embeddings are most affected by the inclusion of visual modality in the training data; that is, points where visual grounding turns out most important. We find that the effect of visual modality correlates most with denotational semantic properties related to concreteness, but is also detected for several specific semantic classes, as well as for valence, a sentiment-related connotational property of linguistic expressions.</abstract>
<identifier type="citekey">bylinina-etal-2023-leverage</identifier>
<identifier type="doi">10.18653/v1/2023.starsem-1.2</identifier>
<location>
<url>https://aclanthology.org/2023.starsem-1.2</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>11</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word Representations
%A Tikhonov, Alexey
%A Bylinina, Lisa
%A Paperno, Denis
%Y Palmer, Alexis
%Y Camacho-collados, Jose
%S Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F bylinina-etal-2023-leverage
%X Multimodal embeddings aim to enrich the semantic information in neural representations of language compared to text-only models. While different embeddings exhibit different applicability and performance on downstream tasks, little is known about the systematic representation differences attributed to the visual modality. Our paper compares word embeddings from three vision-and-language models (CLIP, OpenCLIP and Multilingual CLIP, Radford et al. 2021; Ilharco et al. 2021; Carlsson et al. 2022) and three text-only models, with static (FastText, Bojanowski et al. 2017) as well as contextual representations (multilingual BERT Devlin et al. 2018; XLM-RoBERTa, Conneau et al. 2019). This is the first large-scale study of the effect of visual grounding on language representations, including 46 semantic parameters. We identify meaning properties and relations that characterize words whose embeddings are most affected by the inclusion of visual modality in the training data; that is, points where visual grounding turns out most important. We find that the effect of visual modality correlates most with denotational semantic properties related to concreteness, but is also detected for several specific semantic classes, as well as for valence, a sentiment-related connotational property of linguistic expressions.
%R 10.18653/v1/2023.starsem-1.2
%U https://aclanthology.org/2023.starsem-1.2
%U https://doi.org/10.18653/v1/2023.starsem-1.2
%P 11-17
Markdown (Informal)
[Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word Representations](https://aclanthology.org/2023.starsem-1.2) (Tikhonov et al., *SEM 2023)
ACL