BriefGPT.xyz
Jan, 2020
基于DistanceNet-Bandits的多源领域自适应文本分类
Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits
HTML
PDF
Han Guo, Ramakanth Pasunuru, Mohit Bansal
TL;DR
研究了领域自适应算法在目标域的性能与源域误差和数据分布之间的差异度量函数的关系,提出了一种基于距离度量的方法用于NLP任务,开发了一个DistanceNet模型和DistanceNet-Bandit模型,证明了这些模型在无监督领域适应中的优越性。
Abstract
domain adaptation
performance of a learning algorithm on a target domain is a function of its source domain error and a divergence measure between the data distribution of these two domains. We present a study of various
→