基于LSTM网络的中文地址分词法的设计与实现 |
| |
引用本文: | 张文豪.基于LSTM网络的中文地址分词法的设计与实现[J].计算机应用研究,2018,35(12). |
| |
作者姓名: | 张文豪 |
| |
作者单位: | 武汉邮电科学研究院 |
| |
基金项目: | 国家高技术研究发展计划(863计划);国家自然科学基金资助项目 |
| |
摘 要: | 当前中文地址的分词法主要采用基于规则和传统机器学习的方法。这些方法需要人工长期维护词典和提取特征。为避免特征工程和减少人工维护,提出了将长短时记忆(long short-term memory,LSTM)网络和双向长短时记忆(bi-directional long short-term memory,Bi-LSTM)网络分别应用在中文地址分词任务中,并采用四词位标注法以及增加未标记数据集的方法提升分词性能。在自建数据集上的实验结果表明:中文地址分词任务应用Bi-LSTM网络结构能得到较好性能,在增加未标记数据集的情况下,可以有效提升模型的性能。
|
关 键 词: | 中文地址 分词 LSTM 未标记数据集 |
收稿时间: | 2017/8/28 0:00:00 |
修稿时间: | 2018/11/5 0:00:00 |
Design and Implementation of Chinese Address Segmentation Method Based on LSTM Networks |
| |
Affiliation: | Wuhan Research Institute of Posts and Telecommunications |
| |
Abstract: | Currently most methods for Chinese address segmentation are mainly based on rules and traditional machine learning technology. However, these methods maintain dictionary and extract features with artificial maintenance for a long time. In order to avoid feature engineering and reduce artificial maintenance, this paper compared the performance between LSTM(long short-term memory) and bidirectional LSTM applied to Chinese address segmentation,with four-tag-set and character embedding. This paper also added abundant unlabeled Chinese address to enhance the performance. The result on self-built set shows that both LSTM and bidirectional LSTM neural networks work well, and bidirectional LSTM has a bit good performance. Also, adding extra unlabeled set can great improve the performance. |
| |
Keywords: | |
|
| 点击此处可从《计算机应用研究》浏览原始摘要信息 |
|
点击此处可从《计算机应用研究》下载全文 |