arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.07119cs.CLcs.AI
收藏

基于多任务学习的预训练语言模型在线对话指令检测

Multi-Task Learning based Online Dialogic Instruction Detection with Pre-trained Language Models

TAL Education Group(好未来教育集团);Michigan State University(密歇根州立大学)

Yang Hao, Hang Li, Wenbiao Ding, Zhongqin Wu, Jiliang Tang, Rose Luckin, Zitao Liu

摘要:

在这项工作中,我们研究了计算方法来检测在线对话指令,这被广泛用于帮助学生理解学习材料,并建立有效的学习习惯。由于对话教学的质量和教学风格差异很大,这项任务相当具有挑战性。为了解决这些挑战,我们利用预先训练的语言模型,并提出了一个多任务范式,通过对比损失扩大类别之间的差距,提高区分不同类别的实例的能力。此外,我们设计了一个策略,充分利用错误分类的例子在训练阶段。在真实世界的在线教育数据集上进行的大量实验表明,与代表性基线相比,我们的方法具有更好的性能。为了鼓励可重复的结果,我们在\url{https://github.com/AIED2021/multitask-dialogic-instruction}上在线提供我们的实施。

英文摘要:

In this work, we study computational approaches to detect online dialogic instructions, which are widely used to help students understand learning materials, and build effective study habits. This task is rather challenging due to the widely-varying quality and pedagogical styles of dialogic instructions. To address these challenges, we utilize pre-trained language models, and propose a multi-task paradigm which enhances the ability to distinguish instances of different classes by enlarging the margin between categories via contrastive loss. Furthermore, we design a strategy to fully exploit the misclassified examples during the training stage. Extensive experiments on a real-world online educational data set demonstrate that our approach achieves superior performance compared to representative baselines. To encourage reproducible results, we make our implementation online available at \url{https://github.com/AIED2021/multitask-dialogic-instruction}.

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。

↑