Chinese Named Entity Recognition with a Multi-Phase Model

Abstract

Chinese named entity recognition is one of the difficult and challenging tasks of NLP. In this paper, we present a Chinese named entity recognition system using a multi-phase model. First, we segment the text with a character-level CRF model. Then we apply three word-level CRF models to the labeling person names, location names and organization names in the segmentation results, respectively. Our systems participated in the NER tests on open and closed tracks of Microsoft Research (MSRA). The actual evaluation results show that our system performs well on both the open tracks and closed tracks.