@inproceedings{5ebeedfd1b18415e9f9f9d929cbb17f1,
title = "Chinese Word Segmentation by Mining Maximized Substrings",
abstract = "A major problem in the field of Chinese word segmentation is the identification of out-of-vocabulary words. We propose a simple yet effective approach for extracting maximized substrings, which provide good estimations of unknown word boundaries. We also develop a new semi-supervised segmentation technique that incorporates retrieved substrings using discriminative learning. The effectiveness of this novel approach is demonstrated through experiments using both in-domain and out-of-domain data.",
author = "Mo Shen and Daisuke Kawahara and Sadao Kurohashi",
note = "Publisher Copyright: {\textcopyright} IJCNLP 2013.All right reserved.; 6th International Joint Conference on Natural Language Processing, IJCNLP 2013 ; Conference date: 14-10-2013",
year = "2013",
language = "English",
series = "6th International Joint Conference on Natural Language Processing, IJCNLP 2013 - Proceedings of the Main Conference",
publisher = "Asian Federation of Natural Language Processing",
pages = "171--179",
editor = "Ruslan Mitkov and Park, {Jong C.}",
booktitle = "6th International Joint Conference on Natural Language Processing, IJCNLP 2013 - Proceedings of the Main Conference",
}