轻量级多语言模型，通过联合训练与自适应集成提升情感回归精度。
ICT-NLP at SemEval-2026 Task 3: Less Is More -- Multilingual Encoder with Joint Training and Adaptive Ensemble for Dimensional Aspect Sentiment Regression
- 基于多语言预训练编码器，联合跨语言跨领域训练增强泛化能力。
- 引入有界回归变换，确保预测值在有效范围内并提升训练稳定性。
- 采用子集搜索的自适应集成策略，显著降低预测方差，适合多语种场景。
本文介绍我们参与 SemEval-2026 Task 3 Track A Subtask 1 维度化方面情感回归（DimASR）的任务系统。我们提出一个完全基于多语言预训练编码器的轻量级、资源高效系统，不依赖大语言模型或外部语料库。通过联合多语言与多领域训练，促进跨语言迁移并缓解数据稀疏问题；引入有界回归变换，提升训练稳定性并约束预测值在合法范围内；采用基于子集搜索的自适应集成策略，减少预测方差。实验结果表明，我们的系统在 zho-res 上排名第一，在 zho-lap 上排名第二，在 jpn-hot 上排名第三，其余所有数据集均进入参赛团队前半段。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。