144 search results - page 7 / 29 » Improved Source-Channel Models for Chinese Word Segmentation |
ACL
2008
13 years 9 months ago
2008
IDA
2001
Springer
14 years 10 days ago
2001
Springer
Abstract. We propose a new unsupervised training method for acquiring probability models that accurately segment Chinese character sequences into words. By constructing a core lexi...
ACL
1997
13 years 9 months ago
1997
This paper presents a trainable rule-based algorithm for performing word segmentation. The algorithm provides a simple, language-independent alternative to large-scale lexicai-bas...
ACL
2006
13 years 9 months ago
2006
We proposed a subword-based tagging for Chinese word segmentation to improve the existing character-based tagging. The subword-based tagging was implemented using the maximum entr...
IJCNLP
2004
Springer
14 years 1 months ago
2004
Springer
We present a study of new word identification (NWI) to improve the performance of a Chinese word segmenter. In this paper the distribution and types of new words are discussed emp...