2018
NAACL
NAACL 2018
Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation
Abstract
AbstractWe address the problem of simultaneous translation by modifying the Neural MT decoder to operate with dynamically built encoder and attention. We propose a tunable agent which decides the best segmentation strategy for a user-defined BLEU loss and Average Proportion (AP) constraint. Our agent outperforms previously proposed Wait-if-diff and Wait-if-worse agents (Cho and Esipova, 2016) on BLEU with a lower latency. Secondly we proposed data-driven changes to Neural MT training to better match the incremental decoding framework.
🌉
Interdisciplinary Bridge
— Deep Learning and Machine Learning and Natural Language Processing
🧭
Keyword Pioneer
— latency constraint
🐣
Hot Topic Early Bird
— simultaneous translation
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio