@inproceedings{e5e73f359d7a43a7a8715f8bee7d5a85,
title = "正體中文斷詞系統應用於大型語料庫之多方評估研究",
abstract = "This study aims to evaluate three most popular word segmentation tool for a large Traditional Chinese corpus in terms of their efficiency, resource consumption, and cost. Specifically, we compare the performances of Jieba, CKIP, and MONPA on word segmentation, part-of-speech tagging and named entity recognition through extensive experiments. Experimental results show that MONPA using GPU for batch segmentation can greatly reduce the processing time of massive datasets. In addition, its features such as word segmentation, part-of-speech tagging, and named entity recognition are beneficial to downstream applications.",
keywords = "Chinese Word Segmentation, NER, NLP, POS",
author = "Yeh, {Wen Chao} and Hsieh, {Yu Lun} and Chang, {Yung Chun} and Hsu, {Wen Lian}",
note = "Publisher Copyright: {\textcopyright} 2022 the Association for Computational Linguistics and Chinese Language Processing (ACLCLP).; 34th Conference on Computational Linguistics and Speech Processing, ROCLING 2022 ; Conference date: 21-11-2022 Through 22-11-2022",
year = "2022",
language = "中文",
series = "ROCLING 2022 - Proceedings of the 34th Conference on Computational Linguistics and Speech Processing",
publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)",
pages = "193--199",
editor = "Yung-Chun Chang and Yi-Chin Huang and Jheng-Long Wu and Ming-Hsiang Su and Hen-Hsen Huang and Yi-Fen Liu and Lung-Hao Lee and Chin-Hung Chou and Yuan-Fu Liao",
booktitle = "ROCLING 2022 - Proceedings of the 34th Conference on Computational Linguistics and Speech Processing",
}