BriefGPT.xyz
Nov, 2017
机器翻译的反事实学习：退化与解决方案
Counterfactual Learning for Machine Translation: Degeneracies and Solutions
HTML
PDF
Carolin Lawrence, Pratik Gajane, Stefan Riezler
TL;DR
研究了在确定性记录下的反事实学习中逆推估计和重新加权倾向得分估计器的可能退化现象，并将其与最近提出的确定性日志记录下的反事实学习技术联系起来，以提高基于网络的机器翻译服务。
Abstract
counterfactual learning
is a natural scenario to improve
web-based machine translation
services by
offline learning
from feedback logged d
→