Chinese Chunking with Another Type of Spec
Hongqiao Li, Changning Huang, Jianfeng Gao, Xiaozhong Fan · Meeting of the Association for Computational Linguistics · 2004
Spec is a critical issue for automatic chunking. This paper proposes a solution of Chinese chunking with another type of spec, which is not derived from a complete syntactic tree but only based on the un-bracketed, POS tagged corpus. With this spec, a chunked data is built and HMM is used to build the chunker. TBLbased error correction is used to further improve chunking performance. The average chunk length is about 1.38 tokens, F measure of chunking achieves 91.13%, labeling accuracy alone achieves 99.80% and the ratio of crossing brackets is 2.87%. We also find that the hardest point of Chinese chunking is to identify the chunking boundary inside noun-noun sequences1.