用可学习的不确定性权重，提升多语言情感连续维度预测效果
LogSigma at SemEval-2026 Task 3: Uncertainty-Weighted Multitask Learning for Dimensional Aspect-Based Sentiment Analysis
- 通过学习每个任务的方差参数，自动调节情感维度的训练权重
- 在五个数据集上取得第一，英语与德语差异达2.18倍
- 适合关注多语言情感分析与模型自适应调参的研究者
本文介绍LogSigma系统，用于SemEval-2026任务3：连续维度方面情感分析（DimABSA）。与传统方面情感分析预测离散情感标签不同，DimABSA需在1-9尺度上预测连续的情感效价（Valence）和唤醒度（Arousal）得分。核心挑战在于不同语言和领域中，效价与唤醒度的预测难度差异显著。为此，我们采用可学习的同方差不确定性方法，模型在训练中自动学习各回归任务的对数方差参数以实现动态平衡。结合语言特定编码器与多种子集成策略，LogSigma在两个赛道的五个数据集上均获第一名。学习到的方差权重在不同语言间差异显著——从德语的0.66倍到英语的2.18倍，表明最优任务平衡依赖语言特性，无法预先确定。
原文摘要 · Abstract (English)
This paper describes LogSigma, our system for SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA). Unlike traditional Aspect-Based Sentiment Analysis (ABSA), which predicts discrete sentiment labels, DimABSA requires predicting continuous Valence and Arousal (VA) scores on a 1-9 scale. A central challenge is that Valence and Arousal differ in prediction difficulty across languages and domains. We address this using learned homoscedastic uncertainty, where the model learns task-specific log-variance parameters to automatically balance each regression objective during training. Combined with language-specific encoders and multi-seed ensembling, LogSigma achieves 1st place on five datasets across both tracks. The learned variance weights vary substantially across languages due to differing Valence-Arousal difficulty profiles-from 0.66x for German to 2.18x for English-demonstrating that optimal task balancing is language-dependent and cannot be determined a priori.
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。