Task-oriented dialog(TOD) aims to assist users in achieving specific goals through multi-turn conversation. Recently, good results have been obtained based on large pre-trained models. However, the labeled-data scarcity hinders the efficient development of TOD systems at scale. In this work, we constructed a weakly supervised dataset based on a teacher/student paradigm that leverages a large collection of unlabelled dialogues. Furthermore, we built a modular dialogue system and integrated coarse-to-fine grained classification for user intent detection. Experiments show that our method can reach the dialog goal with a higher success rate and generate more coherent responses.
翻译:以任务为导向的对话(TOD)旨在帮助用户通过多方向对话实现具体目标。 最近,在大型预先培训模式的基础上取得了良好成果。 然而,标签数据稀缺妨碍了对TOD系统的规模发展。 在这项工作中,我们根据教师/学生模式构建了一个监督薄弱的数据集,该模式利用大量无标签对话。此外,我们建立了一个模块对话系统,并建立了综合粗皮到细骨的分类,用于检测用户的意向。实验表明,我们的方法能够以更高的成功率达到对话目标,并产生更加一致的反应。