Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition
Hai Yan Zhao, Chunyu Kit · 2008
This paper describes a novel character tag-ging approach to Chinese word segmenta-tion and named entity recognition (NER) for our participation in Bakeoff-4.1 It integrates unsupervised segmentation and conditional random fields (CRFs) learning successfully, using similar character tags and feature tem-plates for both word segmentation and NER. It ranks at the top in all closed tests of word segmentation and gives promising results for all closed and open NER tasks in the Bake-off. Tag set selection and unsupervised seg-mentation play a critical role in this success. 1