@inproceedings{tateishi-etal-2024-word-aware,
title = "Word-Aware Modality Stimulation for Multimodal Fusion",
author = "Tateishi, Shuhei and
Nakatsuji, Makoto and
Osugi, Yasuhito",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1536",
pages = "17664--17674",
abstract = "Multimodal learning is generally expected to make more accurate predictions than text-only analysis. Here, although various methods for fusing multimodal inputs have been proposed for sentiment analysis tasks, we found that they may be inhibiting their fusion methods, which are based on attention-based language models, from learning non-verbal modalities, because non-verbal ones are isolated from the linguistic semantics and contexts and do not include them, meaning that they are unsuitable for applying attention to text modalities during the fusion phase. To address this issue, we propose Word-aware Modality Stimulation Fusion (WA-MSF) for facilitating integration of non-verbal modalities with the text modality. The Modality Stimulation Unit layer (MSU-layer) is the core concept of WA-MSF; it integrates language contexts and semantics into non-verbal modalities, thereby instilling linguistic essence into these modalities. Moreover, WA-MSF uses aMLP in the fusion phase in order to utilize spatial and temporal representations of non-verbal modalities more effectively than transformer fusion. In our experiments, WA-MSF set a new state-of-the-art level of performance on sentiment prediction tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tateishi-etal-2024-word-aware">
<titleInfo>
<title>Word-Aware Modality Stimulation for Multimodal Fusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuhei</namePart>
<namePart type="family">Tateishi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Nakatsuji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuhito</namePart>
<namePart type="family">Osugi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal learning is generally expected to make more accurate predictions than text-only analysis. Here, although various methods for fusing multimodal inputs have been proposed for sentiment analysis tasks, we found that they may be inhibiting their fusion methods, which are based on attention-based language models, from learning non-verbal modalities, because non-verbal ones are isolated from the linguistic semantics and contexts and do not include them, meaning that they are unsuitable for applying attention to text modalities during the fusion phase. To address this issue, we propose Word-aware Modality Stimulation Fusion (WA-MSF) for facilitating integration of non-verbal modalities with the text modality. The Modality Stimulation Unit layer (MSU-layer) is the core concept of WA-MSF; it integrates language contexts and semantics into non-verbal modalities, thereby instilling linguistic essence into these modalities. Moreover, WA-MSF uses aMLP in the fusion phase in order to utilize spatial and temporal representations of non-verbal modalities more effectively than transformer fusion. In our experiments, WA-MSF set a new state-of-the-art level of performance on sentiment prediction tasks.</abstract>
<identifier type="citekey">tateishi-etal-2024-word-aware</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1536</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>17664</start>
<end>17674</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word-Aware Modality Stimulation for Multimodal Fusion
%A Tateishi, Shuhei
%A Nakatsuji, Makoto
%A Osugi, Yasuhito
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F tateishi-etal-2024-word-aware
%X Multimodal learning is generally expected to make more accurate predictions than text-only analysis. Here, although various methods for fusing multimodal inputs have been proposed for sentiment analysis tasks, we found that they may be inhibiting their fusion methods, which are based on attention-based language models, from learning non-verbal modalities, because non-verbal ones are isolated from the linguistic semantics and contexts and do not include them, meaning that they are unsuitable for applying attention to text modalities during the fusion phase. To address this issue, we propose Word-aware Modality Stimulation Fusion (WA-MSF) for facilitating integration of non-verbal modalities with the text modality. The Modality Stimulation Unit layer (MSU-layer) is the core concept of WA-MSF; it integrates language contexts and semantics into non-verbal modalities, thereby instilling linguistic essence into these modalities. Moreover, WA-MSF uses aMLP in the fusion phase in order to utilize spatial and temporal representations of non-verbal modalities more effectively than transformer fusion. In our experiments, WA-MSF set a new state-of-the-art level of performance on sentiment prediction tasks.
%U https://aclanthology.org/2024.lrec-main.1536
%P 17664-17674
Markdown (Informal)
[Word-Aware Modality Stimulation for Multimodal Fusion](https://aclanthology.org/2024.lrec-main.1536) (Tateishi et al., LREC-COLING 2024)
ACL
- Shuhei Tateishi, Makoto Nakatsuji, and Yasuhito Osugi. 2024. Word-Aware Modality Stimulation for Multimodal Fusion. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 17664–17674, Torino, Italia. ELRA and ICCL.