Scalable Low-Latency Persistent Neural Machine Translation on CPU Server with Multiple FPGAs.
Eriko NurvitadhiMishali NaikAndrew BoutrosPrerna BudhkarAli JafariDongup KwonDavid SheffieldAbirami PrabhakaranKarthik GururajPranavi AppanaPublished in: FPT (2019)
Keyphrases
- low latency
- machine translation
- high bandwidth
- high speed
- highly efficient
- high throughput
- massive scale
- real time
- natural language processing
- language independent
- information extraction
- cross language information retrieval
- statistical machine translation
- target language
- cross lingual
- virtual machine
- continuous query processing
- stream processing
- chinese english
- language resources
- query translation
- natural language
- machine translation system
- word alignment
- source language
- word level