HMM and CRF Based Hybrid Model for Chinese Lexical Analysis

This paper presents the Chinese lexical analysis systems developed by Natural Language Processing Laboratory at Dalian University of Technology, which were evaluated in the 4th International Chinese Language Processing Bakeoff. The HMM and CRF hybrid model, which combines character-based model with word-based model in a directed graph, is adopted in system developing. Both the closed and open tracks regarding to Chinese word segmentation, POS tagging and Chinese Named Entity Recognition are involved in our systems’ evaluation, and good performance are achieved. Especially, in the open track of Chinese word segmentation on SXU, our system ranks 1st.