对话中个人事实的标注方案与分类器
An Annotation Scheme and Classifier for Personal Facts in Dialogue
AI总结：
本文提出改进的个人事实分类标注方案，引入新类别和属性以提升对话系统中的事实存储与过滤能力，并训练多头分类器，实现81.6%的宏F1分数，优于现有基线模型。
摘要：
大语言模型的发展使其在个性化对话系统中得到应用。本文提出扩展的个人事实分类标注方案，解决了现有方法特别是PeaCoK的局限性，引入新类别（人口统计学、财产）和属性（持续时间、有效性、后续）以实现结构化存储、质量过滤和对话延续适合的事实识别。我们手动标注了2779个事实来自多会话聊天，并基于transformer编码器训练了多头分类器。结合Gemma-300M编码器，分类器达到81.6±2.6%的宏F1分数，优于所有少样本LLM基线（最佳：GPT-5.4-mini，72.92%），并在计算资源方面显著更少。错误分析揭示了语义边界歧义、时间方面解释和后续评估的持续挑战。该数据集和分类器已公开可用。
英文摘要：
The advancement of Large Language Models (LLMs) has enabled their application in personalized dialogue systems. We present an extended annotation scheme for personal fact classification that addresses limitations in existing approaches, particularly PeaCoK. Our scheme introduces new categories (Demographics, Possessions) and attributes (Duration, Validity, Followup) that enable structured storage, quality filtering, and identification of facts suitable for dialogue continuation. We manually annotated 2,779 facts from Multi-Session Chat and trained a multi-head classifier based on transformer encoders. Combined with the Gemma-300M encoder, the classifier achieves $81.6 \pm 2.6$\% macro F1, outperforming all few-shot LLM baselines (best: GPT-5.4-mini, 72.92\%) by nearly 9 percentage points while requiring substantially fewer computational resources. Error analysis reveals persistent challenges in semantic boundary disambiguation, temporal aspect interpretation, and pragmatic reasoning for followup assessment. The dataset\footnotemark[1] and classifier\footnotemark[2] are publicly available.
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。
