Chinese Named Entity Recognition and Word Segmentation Based on Character.

Chinese word segmentation and named entity recognition (NER) are both important tasks in Chinese information processing. This paper presents a character-based Conditional Random Fields (CRFs) model for such two tasks. In The SIGHAN Bakeoff 2007, this model participated in all closed tracks for both Chinese NER and word segmentation tasks, and turns out to perform well. Our system ranks 2nd in the closed track on NER of MSRA, and 4th in the closed track on word segmentation of SXU.