Team BOBW (Best Of Both Worlds) at SemEval-2026 Task 3: Modular Cross-Attention Encoders for Dimensional Aspect-Based Sentiment Analysis
Year: 2026
Type: conference-paper
Abstract: This paper presents our system for SemEval-2026 Task 3, which identifies four-part opinion tuples in product reviews.We used a sequence of pairs of BERT encoder models connected by cross-attention layers.The cross-attention mechanism provided marginally better results than a self-attention equivalent, failing to showcase a significant improvement.Error propagation through the pipeline hurt the correctness of the outputs, with certain stages collapsing the scores.The pipeline architecture's performance was largely independent of model size, suggesting that small modular encoders for downstream tasks are an efficient alternative to large decoder models.Our best model got a cF1 score of 0.53 on restaurant data and 0.26 on laptop data.
Authors: Michal Rynowiecki, Rob Van Der Goot
Institution: IT University of Copenhagen
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166809414