A Maximum Entropy Approach to Chinese Word Segmentation

@inproceedings{Low2005AME,
  title={A Maximum Entropy Approach to Chinese Word Segmentation},
  author={Jin Kiat Low and Hwee Tou Ng and Wenyuan Guo},
  booktitle={SIGHAN@IJCNLP 2005},
  year={2005}
}
We participated in the Second International Chinese Word Segmentation Bakeoff. Specifically, we evaluated our Chinese word segmenter in the open track, on all four corpora, namely Academia Sinica (AS), City University of Hong Kong (CITYU), Microsoft Research (MSR), and Peking University (PKU). Based on a maximum entropy approach, our word segmenter achieved the highest F measure for AS, CITYU, and PKU, and the second highest for MSR. We found that the use of an external dictionary and… CONTINUE READING
Highly Influential
This paper has highly influenced 17 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 196 citations. REVIEW CITATIONS

2 Figures & Tables

Topics

Statistics

0102030'06'07'08'09'10'11'12'13'14'15'16'17'18
Citations per Year

197 Citations

Semantic Scholar estimates that this publication has 197 citations based on the available data.

See our FAQ for additional information.