arXiv 2607.046902026-07-07cs.CLcs.LG

PAST-TIDE：用于立场检测的基于主题不变归一化的原型锚定语句微调

PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection

Department of Computer Science and Engineering, Khulna University of Engineering & Technology（库尔纳工程技术大学计算机科学与工程系）；Department of Electrical and Computer Engineering, University of Waterloo（滑铁卢大学电气与计算机工程系）；Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学机器学习系）

Md. Shakhoyat Rahman Shujon, MD Jahid Hasan Jim, Md. Milon Islam, Md Rezwanul Haque, Fakhri Karray

备注：: Published in The Fifteenth Language Resources and Evaluation Conference (LREC 2026)
DOI：: 10.63317/4an3eqwpdtpf

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

PAST-TIDE是用于立场检测的系统，通过语句微调，将立场重新定义为完形填空式掩码语言建模，并用原型对比学习及主题条件层归一化补充，在低资源设置中表现有竞争力。

摘要：

我们介绍了PAST-TIDE，这是我们在NakbaNLP@LREC-COLING 2026会议的StanceNakba共享任务的两个子任务中使用的立场检测系统。主要思想是语句微调。我们将立场重新定义为完形填空式掩码语言建模，通过预训练的MLM头部让一个言语化器将标签词映射到立场类别，而不是附加一个随机初始化的分类头部。我们用原型对比学习来补充这一点，它使用可学习的类原型进行与批次大小无关的对比训练，以及用主题条件层归一化进行跨主题阿拉伯语立场检测。PAST-TIDE在官方排行榜上，子任务A的宏F1分数为0.75，子任务B的宏F1分数为0.74，这表明对预训练模型进行最小的架构添加在低资源设置中仍能保持竞争力。

英文摘要：

We introduce PAST-TIDE, our stance detection system addressing both subtasks of the StanceNakba Shared Task at NakbaNLP@LREC-COLING 2026. The main idea is statement tuning. We redefine stance as cloze-style masked language modeling (MLM), letting a verbalizer map label words to stance categories through the pre-trained MLM head rather than appending a randomly initialized classification head. We complement this with prototypical contrastive learning, which uses learnable class prototypes for batch-size independent contrastive training, and topic-conditional layer normalization for cross-topic Arabic stance detection. PAST-TIDE achieves macro-F1 scores of 0.75 for Subtask A and 0.74 for Subtask B on the official leaderboard, indicating that minimal architectural additions to a pre-trained model can remain competitive in low-resource settings.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。