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. O...

In this paper, we described our Chinese word segmentation system for the 3rd SIGHAN Chinese Language Processing Bakeoff Word Segmentation Task. Our system deal with the Chinese character sequence by using the Maximum Entropy model, which is fully automatically generated from the training data by analyzing the character sequences from the training corpus. We analyze its performance on both close...

Chinese Named Entity Recognition is the fundamental technology in field of Natural Language Process. It extensively adopted into information extraction, intelligent question answering, and knowledge graph. Nevertheless, due to diversity complexity Chinese, most NER methods fail sufficiently capture character granularity semantics, which affects performance NER. In this work, we propose DSKE-Chi...