信息量的重要性：教育对话主动学习中的行动分类（英文版）

英文标题：Does Informativeness Matter? Active Learning for Educational Dialogue Act Classification中文摘要：本文研究了对话行为 (DAs) 分类器的训练方法，发现使用 Active Learning 方法可以减少人力标注成本以及提高标注样本信息性，从而更好地支持对 DA 的分类器。英文摘要：Dialogue Acts (DAs) can be used to explain what expert tutors do and whatstudents know during the tutoring process. Most empirical studies adopt therandom sampling method to obtain sentence samples for manual annotation of DAs,which are then used to train DA classifiers. However, these studies have paidlittl