The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task

2017/08/03 by Sharaf, Amr, Feng, Shi, Nguyen, Khanh +2
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC)

paper · doi:10.48550/arxiv.1708.01318

Abstract

We describe the University of Maryland machine translation systems submitted to the WMT17 German-English Bandit Learning Task. The task is to adapt a translation system to a new domain, using only bandit feedback: the system receives a German sentence to translate, produces an English sentence, and only gets a scalar score as feedback. Targeting these two challenges (adaptation and bandit learning), we built a standard neural machine translation system and extended it in two ways: (1) robust reinforcement learning techniques to learn effectively from the bandit feedback, and (2) domain adaptation using data selection from a large corpus of parallel data.

Related

• Machine Translation System Selection from Bandit Feedback
• A Shared Task on Bandit Learning for Machine Translation
• Reinforcement Learning for Bandit Neural Machine Translation with\n Simulated Human Feedback
• Can Neural Machine Translation be Improved with User Feedback?
• The University of Cambridge's Machine Translation Systems for WMT18