Interactive-Predictive Neural Machine Translation through Reinforcement and Imitation

2019/07/04 by Tsz Kin Lam, Lam, Tsz Kin, Shigehiko Schamoni +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1907.02326

openalex publication_date 2019/07/04 · openalex created_date 2019/07/12 · openalex updated_date 2026/07/28

Abstract

We propose an interactive-predictive neural machine translation framework for easier model personalization using reinforcement and imitation learning. During the interactive translation process, the user is asked for feedback on uncertain locations identified by the system. Responses are weak feedback in the form of "keep" and "delete" edits, and expert demonstrations in the form of "substitute" edits. Conditioning on the collected feedback, the system creates alternative translations via constrained beam search. In simulation experiments on two language pairs our systems get close to the performance of supervised training with much less human effort.

Citations

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Achieving Human Parity on Automatic Chinese to English News Translation
• 10. Reinforcement learning
• A Reduction of Imitation Learning and Structured Prediction to No-Regret\n Online Learning

Related

• A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation
• Online Learning for Effort Reduction in Interactive Neural Machine Translation
• Reinforcement Learning for Bandit Neural Machine Translation with\n Simulated Human Feedback
• Extending Multilingual Machine Translation through Imitation Learning
• Can Neural Machine Translation be Improved with User Feedback?