郑州大学学报（理学版）2018，Vol.50Issue(2)：97-101,5.DOI:10.13705/j.issn.1671-6841.2017169
基于定长序列的双向LSTM分词优化方法
A Optimization Method of Bidirectional LSTM Based on Fixed Length Sequence for Word Segmentation
摘要
Abstract
The method of center character enhancement and the method of reverse sequence enhancement were proposed based on fixed length sequence BLSTM.The experimental results on Bakeoff 2005 Mi-crosoft Asia Research Institute showed that, the segmentation effect of the optimization method was im-proved.The proposed optimization model could be used as a reference for other tasks.关键词
深度学习/LSTM/中文分词Key words
deep learning/LSTM/Chinese word segment分类
信息技术与安全科学引用本文复制引用
郭正斌,张仰森..基于定长序列的双向LSTM分词优化方法[J].郑州大学学报（理学版）,2018,50(2):97-101,5.基金项目
国家自然科学基金项目(61370139,61602044) （61370139,61602044）
北京市教委科研计划一般项目(KM201711232022). （KM201711232022）
