@inbook{24c5635067454604ab2677c8b1f08150,
title = "A Study of Chinese Word Segmentation Based on the Characteristics of Chinese",
abstract = "This paper introduces the research on Chinese word segmentation (CWS). The word segmentation of Chinese expressions is difficult due to the fact that there is no word boundary in Chinese expressions and that there are some kinds of ambiguities that could result in different segmentations. To distinguish itself from the conventional research that usually emphasizes more on the algorithms employed and the workflow designed with less contribution to the discussion of the fundamental problems of CWS, this paper firstly makes effort on the analysis of the characteristics of Chinese and several categories of ambiguities in Chinese to explore potential solutions. The selected conditional random field models are trained with a quasi-Newton algorithm to perform the sequence labeling. To consider as much of the contextual information as possible, an augmented and optimized set of features is developed. The experiments show promising evaluation scores as compared to some related works.",
keywords = ": Natural language processing, Chinese word segmentation, Characteristics of Chinese, Optimized features",
author = "Lifeng Han and Wong, {Derek F.} and Chao, {Lidia S.} and Liangye He and Ling Zhu and Shuo Li",
year = "2013",
month = aug,
day = "21",
doi = "10.1007/978-3-642-40722-2_12",
language = "English",
isbn = "9783642407215",
series = "Lecture Notes in Computer Science",
publisher = "Springer Berlin",
pages = "111--118",
editor = "Iryna Gurevych and Chris Biemann and Torsten Zesch",
booktitle = "Language Processing and Knowledge in the Web",
address = "Germany",
}