BriefGPT.xyz
Oct, 2020
基于实例的含义预测及观测者
Example-Driven Intent Prediction with Observers
HTML
PDF
Shikib Mehri, Mihail Eric, Dilek Hakkani-Tur
TL;DR
本论文旨在提出一种有效的适应新领域的可扩展模型,该模型使用观察者和基于示例的训练方法提高了话语分类模型的概括能力,并实现在银行,CLINC150和HWU64上进行的语言意图识别中,采用以上方法获得了最先进的结果。
Abstract
A key challenge of
dialog systems
research is to effectively and efficiently adapt to new domains. A scalable paradigm for adaptation necessitates the development of generalizable models that perform well in
few-shot se
→