针对阴谋论检测，提出边界感知的跨度提取与分类方法。
UCSC NLP at SemEval-2026 Task 10: Boundary-Aware Span Extraction and RoBERTa Classification for Conspiracy Detection
- 用边界感知表示和高重叠率正样本筛选跨度提取
- 实体类角色检测准确，抽象角色受边界影响大
- 适合需要精准识别阴谋论关键表述的研究者
我们介绍了参与 SemEval-2026 Task 10（PsyCoMark）的系统，解决阴谋论标记物提取（子任务1）和文档级阴谋论检测（子任务2）。对于标记物提取，将任务建模为枚举候选跨度的多标签跨度分类，采用 IoU ≥ 0.95 的正样本标注、硬负样本采样及基于包含关系的非极大值抑制（NMS），并引入边界感知跨度表示。文档分类独立建模，使用带标签平滑的序列分类器和分层训练-验证划分。分析表明，实体类角色（如参与者、受害者）检测稳健，而抽象角色（如行为、效果、证据）对边界标准敏感。在官方测试集上，系统在子任务1中排名第7（宏平均F1=0.2251），子任务2中排名第11（加权F1=0.7694）。
原文摘要 · Abstract (English)
We present our systems for SemEval-2026 Task 10 (PsyCoMark), addressing conspiracy marker extraction (Subtask 1) and document-level conspiracy detection (Subtask 2). For marker extraction, we formulate the task as multi-label span classification over enumerated candidate spans, using IoU >= 0.95 positive labeling, hard-negative sampling, and containment-based non-maximum suppression (NMS) with boundary-aware span representations. Document classification is modeled independently using a sequence classifier with label smoothing and a stratified train-validation split. Analysis shows that entity-like roles (Actor, Victim) are detected robustly, while abstract roles (Action, Effect, Evidence) remain sensitive to boundary criteria. On the official test set, our systems rank 7th in Subtask 1 (0.2251 macro F1) and 11th in Subtask 2 (0.7694 weighted F1).
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。