@inproceedings{tee-2026-khaleesiyali,
title = "Khaleesiyali at {S}em{E}val-2026 Task 2: Lexicon-Augmented {R}o{BERT}a for Valence{--}Arousal Regression on Ecological Essays",
author = "Tee, Eleale",
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-1.75/",
pages = "522--527",
ISBN = "979-8-89176-414-9",
abstract = "This paper presents a lexicon-augmentedRoBERTa system for the SemEval-2026 Task2 valence{--}arousal regression challenge. Themodel integrates deep contextual embeddingswith a 6-dimensional feature vector derivedfrom the NRC VAD lexicon, achieving a hightoken coverage rate of 72.05{\%}. Under officialuser-aware evaluation, the system reached acompetitive average composite correlation of0.547, significantly outperforming the ridgeregressionbaseline. The system demonstratedparticular robustness in valence (r = 0.656)and achieved strong generalization to unseenusers (rarousal = 0.519). These findings indicatethat lightweight lexicon-based statisticsprovide valuable complementary cues for longitudinalemotion modeling in modern transformerarchitectures."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tee-2026-khaleesiyali">
<titleInfo>
<title>Khaleesiyali at SemEval-2026 Task 2: Lexicon-Augmented RoBERTa for Valence–Arousal Regression on Ecological Essays</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eleale</namePart>
<namePart type="family">Tee</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 presents a lexicon-augmentedRoBERTa system for the SemEval-2026 Task2 valence–arousal regression challenge. Themodel integrates deep contextual embeddingswith a 6-dimensional feature vector derivedfrom the NRC VAD lexicon, achieving a hightoken coverage rate of 72.05%. Under officialuser-aware evaluation, the system reached acompetitive average composite correlation of0.547, significantly outperforming the ridgeregressionbaseline. The system demonstratedparticular robustness in valence (r = 0.656)and achieved strong generalization to unseenusers (rarousal = 0.519). These findings indicatethat lightweight lexicon-based statisticsprovide valuable complementary cues for longitudinalemotion modeling in modern transformerarchitectures.</abstract>
<identifier type="citekey">tee-2026-khaleesiyali</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.75/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>522</start>
<end>527</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Khaleesiyali at SemEval-2026 Task 2: Lexicon-Augmented RoBERTa for Valence–Arousal Regression on Ecological Essays
%A Tee, Eleale
%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 tee-2026-khaleesiyali
%X This paper presents a lexicon-augmentedRoBERTa system for the SemEval-2026 Task2 valence–arousal regression challenge. Themodel integrates deep contextual embeddingswith a 6-dimensional feature vector derivedfrom the NRC VAD lexicon, achieving a hightoken coverage rate of 72.05%. Under officialuser-aware evaluation, the system reached acompetitive average composite correlation of0.547, significantly outperforming the ridgeregressionbaseline. The system demonstratedparticular robustness in valence (r = 0.656)and achieved strong generalization to unseenusers (rarousal = 0.519). These findings indicatethat lightweight lexicon-based statisticsprovide valuable complementary cues for longitudinalemotion modeling in modern transformerarchitectures.
%U https://aclanthology.org/2026.semeval-1.75/
%P 522-527
Markdown (Informal)
[Khaleesiyali at SemEval-2026 Task 2: Lexicon-Augmented RoBERTa for Valence–Arousal Regression on Ecological Essays](https://aclanthology.org/2026.semeval-1.75/) (Tee, SemEval 2026)
ACL