@inproceedings{strothe-etal-2026-teamlasse,
title = "{T}eam{L}asse at {S}em{E}val-2026 Task 3: A Hybrid Generative-Discriminative Framework for Dimensional Aspect-Based Sentiment Analysis",
author = "Strothe, Lasse and
Kolli, Shaghayegh and
Diesner, Jana",
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-1.273/",
pages = "2155--2162",
ISBN = "979-8-89176-414-9",
abstract = "In this paper, we present our system for SemEval-2026 Task 3 Track A: Dimensional Aspect-Based Sentiment Analysis (DimABSA). The core objective is to extract structural sentiment elements{---}such as aspects, opinions, and categories{---}from text and predict their corresponding continuous Valence-Arousal (VA) scores. The primary challenge lies in simultaneously handling structural extraction and continuous numerical regression across highly imbalanced datasets encompassing multiple languages and domains. To address this complexity, we propose a decoupled, two-stage hybrid generative-discriminative framework. A generative Large Language Model first extracts structured sentiment tuples, while an encoder-based language model performs the continuous VA regression. To foster cross-lingual and cross-domain generalization, we train our models using a targeted data balancing mechanism."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strothe-etal-2026-teamlasse">
<titleInfo>
<title>TeamLasse at SemEval-2026 Task 3: A Hybrid Generative-Discriminative Framework for Dimensional Aspect-Based Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lasse</namePart>
<namePart type="family">Strothe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaghayegh</namePart>
<namePart type="family">Kolli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jana</namePart>
<namePart type="family">Diesner</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>In this paper, we present our system for SemEval-2026 Task 3 Track A: Dimensional Aspect-Based Sentiment Analysis (DimABSA). The core objective is to extract structural sentiment elements—such as aspects, opinions, and categories—from text and predict their corresponding continuous Valence-Arousal (VA) scores. The primary challenge lies in simultaneously handling structural extraction and continuous numerical regression across highly imbalanced datasets encompassing multiple languages and domains. To address this complexity, we propose a decoupled, two-stage hybrid generative-discriminative framework. A generative Large Language Model first extracts structured sentiment tuples, while an encoder-based language model performs the continuous VA regression. To foster cross-lingual and cross-domain generalization, we train our models using a targeted data balancing mechanism.</abstract>
<identifier type="citekey">strothe-etal-2026-teamlasse</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.273/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2155</start>
<end>2162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TeamLasse at SemEval-2026 Task 3: A Hybrid Generative-Discriminative Framework for Dimensional Aspect-Based Sentiment Analysis
%A Strothe, Lasse
%A Kolli, Shaghayegh
%A Diesner, Jana
%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 strothe-etal-2026-teamlasse
%X In this paper, we present our system for SemEval-2026 Task 3 Track A: Dimensional Aspect-Based Sentiment Analysis (DimABSA). The core objective is to extract structural sentiment elements—such as aspects, opinions, and categories—from text and predict their corresponding continuous Valence-Arousal (VA) scores. The primary challenge lies in simultaneously handling structural extraction and continuous numerical regression across highly imbalanced datasets encompassing multiple languages and domains. To address this complexity, we propose a decoupled, two-stage hybrid generative-discriminative framework. A generative Large Language Model first extracts structured sentiment tuples, while an encoder-based language model performs the continuous VA regression. To foster cross-lingual and cross-domain generalization, we train our models using a targeted data balancing mechanism.
%U https://aclanthology.org/2026.semeval-1.273/
%P 2155-2162
Markdown (Informal)
[TeamLasse at SemEval-2026 Task 3: A Hybrid Generative-Discriminative Framework for Dimensional Aspect-Based Sentiment Analysis](https://aclanthology.org/2026.semeval-1.273/) (Strothe et al., SemEval 2026)
ACL