2019/07/04 by Tsz Kin Lam, Lam, Tsz Kin, Shigehiko Schamoni +3 · 5 citations
Chemistry · Computer Science · Neuroscience · Psychology · #Artificial intelligence #Chemistry #Computation and Language (cs.CL) #Computer science #FOS: Computer and information sciences #Imitation #Machine translation #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Neuroscience #Psychology #Reinforcement #Reinforcement learning #Social psychology #Topic Modeling #Translation (biology) #cs.CL
paper · pdf · doi:10.48550/arxiv.1907.02326
published in arXiv (Cornell University) (Cornell University) · Machine Translation Summit 2019 (MTSUMMIT XVII), Dublin, Ireland
openalex publication_date 2019/07/04 · arxiv created 2019/07/05 · arxiv updated 2019/07/08 · openalex created_date 2019/07/12 · openalex updated_date 2026/07/28
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.