BriefGPT.xyz
Nov, 2018
自然语言处理任务中的不确定性量化
Quantifying Uncertainties in Natural Language Processing Tasks
HTML
PDF
Yijun Xiao, William Yang Wang
TL;DR
本论文提出了新方法来研究自然语言处理（NLP）任务中表征模型和数据不确定性的好处，通过在卷积和循环神经网络模型上的实证实验，展示了明确建模不确定性不仅有利于测量输出置信水平，而且对于提升各种NLP任务中的模型表现也是有用的。
Abstract
Reliable
uncertainty quantification
is a first step towards building explainable, transparent, and accountable artificial intelligent systems. Recent progress in
bayesian deep learning
has made such quantificatio
→