Paper: High OOV-Recall Chinese Word Segmenter

ACL ID W10-4135
Title High OOV-Recall Chinese Word Segmenter
Venue Joint Conference on Chinese Language Processing
Session Main Conference
Year 2010

For the competition of Chinese word seg- mentation held in the first CIPS-SIGHNA joint conference. We applied a subword- based word segmenter using CRFs and ex- tended the segmenter with OOV words recognized by Accessor Variety. More- over, we proposed several post-processing rules to improve the performance. Our system achieved promising OOV recall among all the participants.