基于句法分析及主题分布的关键词抽取模型

iming at the problem that TextRank ignores syntactic information and topic information when extracting chapter keywords, propose a chapter keyword extraction model based on syntactic analysis and topic distribution. Model includes two stages of chapter keyword extraction: paragraph and chapter. Firstly, use paragraphs as a unit to extract paragraph keywords by combining word co-occurrence, grammatical and semantic information. Then cluster the paragraphs according to the paragraph topics to form the paragraph topic set. Finally, extract chapter keywords based on the distribution characteristics of paragraph topics. On the open news dataset, the model's extraction effect improves by about 10% compared with the original TextRank. Results show that the method has significantly improved the extraction effect, and prove the importance of grammatical information and topic information.