What question did this study set out to answer?

This research aims to improve Chinese word segmentation through a machine-learning technique.

February 1, 2003

Chinese Word Segmentation as Character Tagging

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates high precision and recall in Chinese word segmentation using a machine-learning approach.

This research aims to improve Chinese word segmentation through a machine-learning technique.
Utilized a maximum entropy tagger for processing Chinese characters (hanzi)
Trained on a manually annotated dataset of 237K words
Converted tagged output into segmented text for evaluation
Achieved precision of 95.01% and recall of 94.94%
Competitive performance compared to existing supervised segmenters
Demonstrated effectiveness on a sizable training set

Nianwen Xue (2003) studied this question.

View Full Paper

Ask AI

Bookmark