计算机工程与应用2019，Vol.55Issue(10)：30-35,66,7.DOI:10.3778/j.issn.1002-8331.1810-0063
机器翻译方法研究与发展综述
Review of Studies and Developments on Machine Translation Methodology
摘要
Abstract
First of all, machine translation methods are streamlined into three types based on their ways to knowledge pro-cessing, i.e. rule-based methods, corpus-based methods, and hybrid methods, and their merits and demerits are compared. Then, the latest study trends mainly comprise computational complexity reducing, words alignment enhancing, prior knowledge and constraints incorporating, and historical memory improving, attention-based neural networks, as the cur-rent mainstream methods of machine translation, are captured. Finally, the future development orientations are prospected, particularly, networks integration deepening, data processing parallelizing and training methods diversifying of machine translation methods.关键词
机器翻译/机器翻译方法/语料库法/神经网络法Key words
machine translation/machine translation methods/corpus-based methods/neural network methods分类
社会科学引用本文复制引用
侯强,侯瑞丽..机器翻译方法研究与发展综述[J].计算机工程与应用,2019,55(10):30-35,66,7.基金项目
国家自然科学基金(No.61772357,No.61672371,No.61502329,No.61876217) （No.61772357,No.61672371,No.61502329,No.61876217）
江苏省"333工程"科研项目 （）
六大人才高峰项目(No.DZXX-010) （No.DZXX-010）
苏州市科技项目(No.SNG201610,No.SYG201704,No.SZS201609) （No.SNG201610,No.SYG201704,No.SZS201609）
苏州科技大学研究生创新工程项目(No.SKSJ18_011). （No.SKSJ18_011）
