Neural net machine translation method and device

• Main Authors: GUAN HANJU, CAO YING, ZHANG KEFENG, CHEN ZHIJIE, YAN CHUNWEI, TONG-MU CHENXUAN, HUANG WEI
• Format: Patent
• Language: Chinese; English
• Published: 10.08.2018
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a neural net machine translation method and device. The method includes the following steps: obtaining source statements to be translated; converting the source statements to vector sequences; and determining candidate objects corresponding to the vector sequences according to a pre-obtained prefix tree established on the basis of a target statement database, and determining target statements as a translation result according to the candidate objects. The translation speed can be improved by using the scheme of the invention. 本发明公开了神经网络机器翻译方法和装置，所述方法包括：获取待翻译的源语句；将源语句转换为向量序列；根据预先得到的、基于目标语句数据库所构建的前缀树，确定出向量序列对应的候选对象，根据候选对象确定出作为翻译结果的目标语句。应用本发明所述方案，能够提升翻译速度等。