组块分析作为浅层句法分析的代表,既可以满足很多语言信息处理系统对于句法功能的需求,又可以作为子任务,在词法分析和完全句法分析以及语义分析中间架起一座桥梁,为句子进行进一步深入分析提供有力的支持,因此众多的研究将注意力集中于组块分析上。该文主要对组块的定义和分类、组块识别方法、组块的标注和评测以及组块内部关系分析等几方面的研究进展进行详细的综述。最后,探讨了组块分析存在的问题并对未来的发展方向进行了展望。
Chunking, as a typical shallow parsing, serves for many language information processing system for their demands on syntactic information, as well as a bridge between the lexical analysis, syntactic parsing and semantic parsing. This paper surveys the rich researches on chunking in several aspects: the definition and classification of chunks, the chunks identification, the chunks annotation and evaluation, and the internal relationship in chunks. Fi- nally, this paper draws conclusions and discusses the future work.