The Specific Research Of The Part-of-speech Tagging In The “Boya Chinese” Edited By Li Xiaoqi

Based on the editor of Li Xiaoqi about the part-of-speech tagging of the words in a "Boya Chinese" as the research object, the part of speech judgment in "Modern Chinese dictionary"(fifth edition) standard. Finding out the part-of-speech tagging inaccurate words in the book. It is concluded that the part-of-speech tagging of Chinese as a foreign language textbooks should be only on the part of speech of the words in this text annotation, rather than like a dictionary as the conclusion of all listed in reference books. Analyzing in part-of-speech tagging inaccurate reason mainly is the diversity of Chinese word part of speech, teaching Chinese as a foreign language development is not mature and authors of grammar knowledge is limited, etc. Giving some suggestions to solve these problems. The teaching materials should pay attention to the part of speech and text example between cooperate, don’t want to be part of speech tagging, and choose a symbol to indicate the part of speech of science.The article is divided into five parts.The first part is introduction.Introducing the content and significance of this study.The methods and steps of the study, review of relevant literature and language.The second part mainly introduces the teaching material lack of pertinence, do not match the case of part of speech tagging and the text, a word with multiple parts of speech, no labelling part of speech, targeted clutch word part-of-speech tagging, and some other problems in teaching material. This is the focus of the paper.The third part discusses part-of-speech tagging problem. Specific cause of the part-of-speech tagging inaccurate factors. And according to the analysis of the reasons put forward some relevant to the specific vocabulary of countermeasures, in the teaching material for the text to word of part-of-speech tagging cases targeted for labeling.The fourth part is epilogue. Teaching Chinese part-of-speech tagging should be according to the text in the specific case to annotate, rather than a list of all the parts of speech.