@inproceedings{rynowiecki-van-der-goot-2026-team,
title = "Team {BOBW} (Best Of Both Worlds) at {S}em{E}val-2026 Task 3: Modular Cross-Attention Encoders for Dimensional Aspect-Based Sentiment Analysis",
author = "Rynowiecki, Michal and
Van Der Goot, Rob",
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-1.179/",
pages = "1385--1390",
ISBN = "979-8-89176-414-9",
abstract = "This paper presents our system for SemEval-2026 Task 3, which identifies four-part opiniondetails in product reviews. We used a sequenceof pairs of BERT encoder models connectedby cross-attention layers. The cross-attentionmechanism provided marginally better resultsthan a self-attention equivalent, failing to show-case a significant improvement. Error propaga-tion through the pipeline hurt the correctness ofthe outputs, with certain stages collapsing thescores. The pipeline architecture{'}s performancewas largely independent of model size, sug-gesting that small modular encoders for down-stream tasks are an efficient alternative to largedecoder models. Our best model got a cF1score of 0.53 on restaurant data and 0.26 onlaptop data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rynowiecki-van-der-goot-2026-team">
<titleInfo>
<title>Team BOBW (Best Of Both Worlds) at SemEval-2026 Task 3: Modular Cross-Attention Encoders for Dimensional Aspect-Based Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Rynowiecki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">Van Der Goot</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 our system for SemEval-2026 Task 3, which identifies four-part opiniondetails in product reviews. We used a sequenceof pairs of BERT encoder models connectedby cross-attention layers. The cross-attentionmechanism provided marginally better resultsthan a self-attention equivalent, failing to show-case a significant improvement. Error propaga-tion through the pipeline hurt the correctness ofthe outputs, with certain stages collapsing thescores. The pipeline architecture’s performancewas largely independent of model size, sug-gesting that small modular encoders for down-stream tasks are an efficient alternative to largedecoder models. Our best model got a cF1score of 0.53 on restaurant data and 0.26 onlaptop data.</abstract>
<identifier type="citekey">rynowiecki-van-der-goot-2026-team</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.179/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1385</start>
<end>1390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team BOBW (Best Of Both Worlds) at SemEval-2026 Task 3: Modular Cross-Attention Encoders for Dimensional Aspect-Based Sentiment Analysis
%A Rynowiecki, Michal
%A Van Der Goot, Rob
%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 rynowiecki-van-der-goot-2026-team
%X This paper presents our system for SemEval-2026 Task 3, which identifies four-part opiniondetails in product reviews. We used a sequenceof pairs of BERT encoder models connectedby cross-attention layers. The cross-attentionmechanism provided marginally better resultsthan a self-attention equivalent, failing to show-case a significant improvement. Error propaga-tion through the pipeline hurt the correctness ofthe outputs, with certain stages collapsing thescores. The pipeline architecture’s performancewas largely independent of model size, sug-gesting that small modular encoders for down-stream tasks are an efficient alternative to largedecoder models. Our best model got a cF1score of 0.53 on restaurant data and 0.26 onlaptop data.
%U https://aclanthology.org/2026.semeval-1.179/
%P 1385-1390
Markdown (Informal)
[Team BOBW (Best Of Both Worlds) at SemEval-2026 Task 3: Modular Cross-Attention Encoders for Dimensional Aspect-Based Sentiment Analysis](https://aclanthology.org/2026.semeval-1.179/) (Rynowiecki & Van Der Goot, SemEval 2026)
ACL