@inproceedings{belikova-kosenko-2024-deeppavlov,
title = "{D}eep{P}avlov at {S}em{E}val-2024 Task 3: Multimodal Large Language Models in Emotion Reasoning",
author = "Belikova, Julia and
Kosenko, Dmitrii",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.249",
doi = "10.18653/v1/2024.semeval-1.249",
pages = "1747--1757",
abstract = "This paper presents the solution of the DeepPavlov team for the Multimodal Sentiment Cause Analysis competition in SemEval-2024 Task 3, Subtask 2 (Wang et al., 2024). In the evaluation leaderboard, our approach ranks 7th with an F1-score of 0.2132. Large Language Models (LLMs) are transformative in their ability to comprehend and generate human-like text. With recent advancements, Multimodal Large Language Models (MLLMs) have expanded LLM capabilities, integrating different modalities such as audio, vision, and language. Our work delves into the state-of-the-art MLLM Video-LLaMA, its associated modalities, and its application to the emotion reasoning downstream task, Multimodal Emotion Cause Analysis in Conversations (MECAC). We investigate the model{'}s performance in several modes: zero-shot, few-shot, individual embeddings, and fine-tuned, providing insights into their limits and potential enhancements for emotion understanding.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="belikova-kosenko-2024-deeppavlov">
<titleInfo>
<title>DeepPavlov at SemEval-2024 Task 3: Multimodal Large Language Models in Emotion Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Belikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitrii</namePart>
<namePart type="family">Kosenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the solution of the DeepPavlov team for the Multimodal Sentiment Cause Analysis competition in SemEval-2024 Task 3, Subtask 2 (Wang et al., 2024). In the evaluation leaderboard, our approach ranks 7th with an F1-score of 0.2132. Large Language Models (LLMs) are transformative in their ability to comprehend and generate human-like text. With recent advancements, Multimodal Large Language Models (MLLMs) have expanded LLM capabilities, integrating different modalities such as audio, vision, and language. Our work delves into the state-of-the-art MLLM Video-LLaMA, its associated modalities, and its application to the emotion reasoning downstream task, Multimodal Emotion Cause Analysis in Conversations (MECAC). We investigate the model’s performance in several modes: zero-shot, few-shot, individual embeddings, and fine-tuned, providing insights into their limits and potential enhancements for emotion understanding.</abstract>
<identifier type="citekey">belikova-kosenko-2024-deeppavlov</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.249</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.249</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1747</start>
<end>1757</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DeepPavlov at SemEval-2024 Task 3: Multimodal Large Language Models in Emotion Reasoning
%A Belikova, Julia
%A Kosenko, Dmitrii
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F belikova-kosenko-2024-deeppavlov
%X This paper presents the solution of the DeepPavlov team for the Multimodal Sentiment Cause Analysis competition in SemEval-2024 Task 3, Subtask 2 (Wang et al., 2024). In the evaluation leaderboard, our approach ranks 7th with an F1-score of 0.2132. Large Language Models (LLMs) are transformative in their ability to comprehend and generate human-like text. With recent advancements, Multimodal Large Language Models (MLLMs) have expanded LLM capabilities, integrating different modalities such as audio, vision, and language. Our work delves into the state-of-the-art MLLM Video-LLaMA, its associated modalities, and its application to the emotion reasoning downstream task, Multimodal Emotion Cause Analysis in Conversations (MECAC). We investigate the model’s performance in several modes: zero-shot, few-shot, individual embeddings, and fine-tuned, providing insights into their limits and potential enhancements for emotion understanding.
%R 10.18653/v1/2024.semeval-1.249
%U https://aclanthology.org/2024.semeval-1.249
%U https://doi.org/10.18653/v1/2024.semeval-1.249
%P 1747-1757
Markdown (Informal)
[DeepPavlov at SemEval-2024 Task 3: Multimodal Large Language Models in Emotion Reasoning](https://aclanthology.org/2024.semeval-1.249) (Belikova & Kosenko, SemEval 2024)
ACL