@inproceedings{beppu-etal-2026-curiosai,
title = "{C}urios{AI} at {S}em{E}val-2026 Task 2: Predicting Emotion using {R}o{BERT}a-large model",
author = "Beppu, Fumika and
Takushima, Hiroki and
Manoj, Aiswariya and
Yamaga, Daichi and
Shibata, Yuki and
Hori, Takayuki",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.18/",
pages = "121--126",
ISBN = "979-8-89176-414-9",
abstract = "This paper proposes a method for predicting continuous emotion dimensions, namely Valence and Arousal, from text by combining affective intermediate training with multi-task learning. The proposed approach consists of two training phases: an intermediate pre-training phase using external emotion datasets, followed by a multi-task learning phase using task-specific data. RoBERTa-large is employed as the backbone model, and independent regression heads are introduced for each subtask. Experimental results show that the proposed method achieves Pearson correlation coefficients of 0.68 for Valence and 0.45 for Arousal on Subtask 1, demonstrating stable performance, particularly in capturing inter-user differences in emotional expression."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="beppu-etal-2026-curiosai">
<titleInfo>
<title>CuriosAI at SemEval-2026 Task 2: Predicting Emotion using RoBERTa-large model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fumika</namePart>
<namePart type="family">Beppu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Takushima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiswariya</namePart>
<namePart type="family">Manoj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daichi</namePart>
<namePart type="family">Yamaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Shibata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takayuki</namePart>
<namePart type="family">Hori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>This paper proposes a method for predicting continuous emotion dimensions, namely Valence and Arousal, from text by combining affective intermediate training with multi-task learning. The proposed approach consists of two training phases: an intermediate pre-training phase using external emotion datasets, followed by a multi-task learning phase using task-specific data. RoBERTa-large is employed as the backbone model, and independent regression heads are introduced for each subtask. Experimental results show that the proposed method achieves Pearson correlation coefficients of 0.68 for Valence and 0.45 for Arousal on Subtask 1, demonstrating stable performance, particularly in capturing inter-user differences in emotional expression.</abstract>
<identifier type="citekey">beppu-etal-2026-curiosai</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.18/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>121</start>
<end>126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CuriosAI at SemEval-2026 Task 2: Predicting Emotion using RoBERTa-large model
%A Beppu, Fumika
%A Takushima, Hiroki
%A Manoj, Aiswariya
%A Yamaga, Daichi
%A Shibata, Yuki
%A Hori, Takayuki
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F beppu-etal-2026-curiosai
%X This paper proposes a method for predicting continuous emotion dimensions, namely Valence and Arousal, from text by combining affective intermediate training with multi-task learning. The proposed approach consists of two training phases: an intermediate pre-training phase using external emotion datasets, followed by a multi-task learning phase using task-specific data. RoBERTa-large is employed as the backbone model, and independent regression heads are introduced for each subtask. Experimental results show that the proposed method achieves Pearson correlation coefficients of 0.68 for Valence and 0.45 for Arousal on Subtask 1, demonstrating stable performance, particularly in capturing inter-user differences in emotional expression.
%U https://aclanthology.org/2026.semeval-1.18/
%P 121-126
Markdown (Informal)
[CuriosAI at SemEval-2026 Task 2: Predicting Emotion using RoBERTa-large model](https://aclanthology.org/2026.semeval-1.18/) (Beppu et al., SemEval 2026)
ACL