@inproceedings{b720c6884691495f8e6ea98e1ae6d444,
title = "Word Segmentation for Chinese Judicial Documents",
abstract = "Word segmentation is an integral step in many knowledge discovery applications. However, existing word segmentation methods have problems when applying to Chinese judicial documents: (1) existing methods rely on large-scale labeled data which is typically unavailable in judicial documents, and (2) judicial document has its own language features and writing formats. In this paper, a word segmentation method is proposed for Chinese judicial documents. The proposed method consists of two steps: (1) automatically generating some labeled data as legal dictionaries, and (2) applying a hybrid multi-layer neural networks to do word segmentation incorporating legal dictionaries. Experiments are conducted on a dataset of Chinese judicial documents showing that the proposed model can achieve better results than the existing methods.",
keywords = "Chinese word segmentation, Judicial documents, Knowledge discovery",
author = "Linxia Yao and Jidong Ge and Chuanyi Li and Yuan Yao and Zhenhao Li and Jin Zeng and Bin Luo and Victor Chang",
note = "Publisher Copyright: {\textcopyright} Springer Nature Singapore Pte Ltd. 2019.; 5th International Conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2019 ; Conference date: 20-09-2019 Through 23-09-2019",
year = "2019",
doi = "10.1007/978-981-15-0118-0_36",
language = "English",
isbn = "9789811501173",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "466--478",
editor = "Xiaohui Cheng and Weipeng Jing and Xianhua Song and Zeguang Lu",
booktitle = "Data Science - 5th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2019, Proceedings",
}