@inproceedings{sukhodolsky-etal-2026-bertkittens,
title = "{B}ert{K}ittens at {S}em{E}val-2026 Task 3: Multi-Domain Aspect Sentiment with {BERT}/{D}e{BERT}a Ensembles for {VA} Regression and Aspect{--}Opinion{--}{VA} Triplets",
author = "Sukhodolsky, Arseny and
Salimgareev, Ruslan and
Ianshina, Tatiana",
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-1.380/",
pages = "3027--3034",
ISBN = "979-8-89176-414-9",
abstract = "Our system is built on transformer encoders (BERT and DeBERTa) fine-tuned in a multi-task learning framework. For the regression subtask (evaluated with RMSE), we jointly predict Valence{--}Arousal (VA) scores and token-level opinion spans using a shared encoder with task-specific output heads. This formulation introduces auxiliary supervision at the token level, which stabilizes training and improves regression accuracy compared to single-task optimization.When gold abstracts and opinion annotations are provided, our models achieve strong performance. However, in fully end-to-end settings requiring automatic span extraction, performance degrades substantially due to error propagation from token-level predictions.Our findings highlight the benefits of joint affective regression and span modeling, while exposing the limitations of transformer-based sequence labeling under strict end-to-end evaluation constraints."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sukhodolsky-etal-2026-bertkittens">
<titleInfo>
<title>BertKittens at SemEval-2026 Task 3: Multi-Domain Aspect Sentiment with BERT/DeBERTa Ensembles for VA Regression and Aspect–Opinion–VA Triplets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arseny</namePart>
<namePart type="family">Sukhodolsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Salimgareev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Ianshina</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>Our system is built on transformer encoders (BERT and DeBERTa) fine-tuned in a multi-task learning framework. For the regression subtask (evaluated with RMSE), we jointly predict Valence–Arousal (VA) scores and token-level opinion spans using a shared encoder with task-specific output heads. This formulation introduces auxiliary supervision at the token level, which stabilizes training and improves regression accuracy compared to single-task optimization.When gold abstracts and opinion annotations are provided, our models achieve strong performance. However, in fully end-to-end settings requiring automatic span extraction, performance degrades substantially due to error propagation from token-level predictions.Our findings highlight the benefits of joint affective regression and span modeling, while exposing the limitations of transformer-based sequence labeling under strict end-to-end evaluation constraints.</abstract>
<identifier type="citekey">sukhodolsky-etal-2026-bertkittens</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.380/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3027</start>
<end>3034</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BertKittens at SemEval-2026 Task 3: Multi-Domain Aspect Sentiment with BERT/DeBERTa Ensembles for VA Regression and Aspect–Opinion–VA Triplets
%A Sukhodolsky, Arseny
%A Salimgareev, Ruslan
%A Ianshina, Tatiana
%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 sukhodolsky-etal-2026-bertkittens
%X Our system is built on transformer encoders (BERT and DeBERTa) fine-tuned in a multi-task learning framework. For the regression subtask (evaluated with RMSE), we jointly predict Valence–Arousal (VA) scores and token-level opinion spans using a shared encoder with task-specific output heads. This formulation introduces auxiliary supervision at the token level, which stabilizes training and improves regression accuracy compared to single-task optimization.When gold abstracts and opinion annotations are provided, our models achieve strong performance. However, in fully end-to-end settings requiring automatic span extraction, performance degrades substantially due to error propagation from token-level predictions.Our findings highlight the benefits of joint affective regression and span modeling, while exposing the limitations of transformer-based sequence labeling under strict end-to-end evaluation constraints.
%U https://aclanthology.org/2026.semeval-1.380/
%P 3027-3034
Markdown (Informal)
[BertKittens at SemEval-2026 Task 3: Multi-Domain Aspect Sentiment with BERT/DeBERTa Ensembles for VA Regression and Aspect–Opinion–VA Triplets](https://aclanthology.org/2026.semeval-1.380/) (Sukhodolsky et al., SemEval 2026)
ACL