Code description text-based technical feature keyword extraction method and system
The invention discloses a technical feature keyword extraction method and system based on a code description text, and belongs to the technical field of natural language processing. According to the method, code technical feature related information such as semantics, syntactic and vocabulary specif...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
16.08.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a technical feature keyword extraction method and system based on a code description text, and belongs to the technical field of natural language processing. According to the method, code technical feature related information such as semantics, syntactic and vocabulary specificity is comprehensively considered, a fusion analysis method of vocabulary knowledge and sentence syntactic knowledge is adopted, and co-occurrence vocabularies and dependency relationships are combined to construct a semantic association graph; a pre-training model BERT is adopted as a text encoder, and text abstract semantic information is extracted; vocabulary weights are calculated by adopting a random walk algorithm so as to capture a long-distance semantic dependency relationship between vocabularies, and the importance and specificity of keywords are considered.
一种基于代码描述文本的技术特征关键词抽取方法与系统,属于自然语言处理的技术领域。本发明综合考虑语义、句法和词汇特异性等代码技术特征相关信息,采用词汇知识和句子句法知识的融合分析方法,将共现词汇和依存关系相结合构建语义关联图;采用预训练模型BERT作为文本编码器,提取文本抽象语义信息;采用随机游 |
---|---|
Bibliography: | Application Number: CN202210838242 |