Abstract：Chunk parsing is an effective method to decrease the difficulty of language parsing. This paper proposes a formal description representing the characteristics of Chinese chunks. Based on the description , a statistical algorithm is accomplished to recognize definite levels of Chinese chunks. The experiments have proved that the algorithm gives a high accuracy for shallow parsing of real Chinese texts with robustness.
[1] Abney S. Parsing by chunks. In :Berwick R ,Abney S , Tenny C et al. Principle-Based Parsing. Dordrecht : Kluwer Academic Publishers ,1991 [2] Steven Abney. Parsing by chunks. In : Robert Berwick , Steven Abney ,Carol Tenny. Principle-Based Parsing. Dordrecht . Kluwer Acahemic Publishers ,1991 [3] 赵军,黄昌宁. 结合句法组成模板识别汉语基本名词短语的概率模型. 计算机研究与发展,1999 ,36 (11) [4] Peh Li Shiuan ,Christoppher Ting Hian Ann. A Divide-Conquer Strategy for Parsing. In :Proceedings of the ACL/SIGPARSE 5th Inernational Workshop on Parsing Technologies ,1996 [5] 周强,孙茂松,黄昌宁. 汉语句子的组块分析体系. 计算机学报,1999 ,22 (11) [6] Wojciech Skut , Thorsten Brants , Chunk Tagger. Statistical Recongnition of Noun Phrases. In :ESSLLI - 98 Workshop on Automated Acpuisiton of Syntax and Parsing , Saarbrvcken ,1998 [7] Eric Brill. A Simple Rule-Based Part-Of-Speech Tagger. In : Proc. of the Third Conference on Applied Computational Linguistics ,Trento , Italy ,1992
2000, Vol. 14 
