TL;DR研究了一个新的多任务 NLU 结构在小型领域游戏数据集上进行意图识别的表现,发现相比基线方法,Dual Intent and Entity Transformer (DIET) 架构在野外数据上具有较强的鲁棒性。
Abstract
intelligent systems designed for play-based interactions should be
contextually aware of the users and their surroundings. spoken dialogue systems
(SDS) are critical for these interactive agents to carry out effe