基于LSTM网络的中文地址分词法的设计与实现

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。

Design and Implementation of Chinese Address Segmentation Method Based on LSTM Networks

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.