Modern Chinese Language Dictionary Pos Tagging Study

The part-of-speech label is always a difficult problem which writers of Chinese dictionaries can not solve perfectly. In recent years, with the development of theories of Chinese grammar and theories of dictionary, this problem is paid more attention, many dictionaries are started to label the part-of-speech.The compartment of part-of-speech about the modern Chinese , or the part-of-speech label on the Chinese dictionary which only depends on the enumeration of self-examination can neither reflect the function of phrase completely, nor label the part-of-speech explicitly. Based on the large-scale databases, the research on the part-of-speech is inevitable, but there are few fruits about it. The research can not only provide the reference for the development of the theory of modern Chinese grammar and compartment of part-of-speech ,but for the research on the dictionary compilation,foreign Chinese teaching and Chinese information processing, it can bring great social benefits.Exactly owing to the thought, at the beginning of September, 2004, we decided to form a《Database about the part-of-speech of Modern Chinese language》which based on the《The modern Chinese electronic dictionary》which we have cooperated with the Chin Hua university, it contains 110,000 phrases, we also refered to the《Modern Chinese Grammar information dictionary》which the Peking University had developed. We Selected four dictionaries:《Modern Chinese norm Dictionary》,《Application Chinese Dictionary》,《Dictionary of new Chinese-to-English of new century》and《Student's Chinese Dictionary of Multi-function》, which are the present representative Modern Chinese Dictionaries about the part-of-speech label, recording into all articles of word,vocabulary,phrase that four dictionaries accept in . The text, which is based on the corpus and takes the research of part-of-speech about The Modern Chinese as the guide, mainly analyses the problems which still exist in the part-of-speech label on The Modern Chinese dictionary presently: there are many differences about the labeling on the part of word,speech,phrase in different dictionaries. By analyzing the phrase which have differences in the part-of-speech, we attribute the differences to five aspects: the dissimilarity of the phrase system and the inconformity of the dictionary style; the diversity of the grammar function or the different standard which may lead to different labels; the system of part of speech in the dictionaries...