@inproceedings{huang-etal-2026-ict,
    title = "{ICT}-{NLP} at {S}em{E}val-2026 Task 3: Less Is More {---} Multilingual Encoder with Joint Training and Adaptive Ensemble for Dimensional Aspect Sentiment Regression",
    author = "Huang, Liyuan  and
      He, Jiawei  and
      Shen, Wutao  and
      Li, Lin  and
      Zhang, Jin",
    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-1.131/",
    pages = "950--957",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper describes our system to SemEval-2026 Task 3 Track A Subtask 1 on Dimensional Aspect Sentiment Regression (DimASR). We propose a lightweight and resource-efficient system built entirely on multilingual pre-trained encoders, without relying on LLMs or external corpora. We adopt joint multilingual and multi-domain training to facilitate cross-lingual transfer and alleviate data sparsity, introduce a bounded regression transformation that improves training stability while constraining predictions within the valid range, and employ an adaptive ensemble strategy via subset search to reduce prediction variance. Experimental results demonstrate that our system achieves strong and consistent performance, ranking 1st on zho-res, 2nd on zho-lap, and 3rd on jpn-hot, with all remaining datasets placed within the top half of participating teams."
}