@inproceedings{hsieh-etal-2026-nycu,
    title = "{NYCU} Speech Lab at {S}em{E}val-2026 Task 3: Heterogeneous Model Ensemble with Adaptive Weighted Voting for Dimensional Aspect Sentiment Quadruplet Extraction",
    author = "Hsieh, Hao-Chun  and
      Wu, Cheng-En  and
      Liao, Yuan-Fu",
    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://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.203/",
    pages = "1568--1574",
    ISBN = "979-8-89176-414-9",
    abstract = "SemEval-2026 Task 3 (DimABSA) includes Dimensional Aspect Sentiment Quadruplet Extraction (DimASQP), which requires extracting structured tuples{---}aspect term, aspect category, and opinion term{---}together with continuous valence{--}arousal (VA) values from reviews (Yu et al., 2026a). In this work, we participate in Track A, Subtask 3. We describe NYCU Speech Lab{'}s submission for the Chinese Restaurant and Laptop domains. Our system is a post-processing ensemble over heterogeneous architectures: LoRA/QLoRA fine-tuned decoder-only LLMs, a fine-tuned encoder-only model, and (optionally) prompted API-based LLMs. To improve robustness under the continuous F1 (cF1) metric, we use validation-calibrated weighted voting for tuple selection and weighted VA fusion for numerical aggregation, with strict output validation to enforce task constraints. Experiments on a held-out validation split show consistent gains over single models and clarify the precision{--}recall trade-offs induced by the voting threshold. On the organizers' released (tentative) test leaderboard snapshot, our submission ranks first in both domains."
}