Query-oriented automatic summarization is a hot research topic in the field of text mining in recent years. It aims to automatically generate personalized concise summaries that are biased towards user query needs. From the perspective of optimization problems, this paper proposes a sentence extraction type summary selection strategy and method based on genetic algorithm. The random summary consisting of different sentence sets that can meet the summary length limit is used as the initial population, and the comprehensive characteristic evaluation function of the summary is used as the fitness function. Through the global optimization ability of the genetic algorithm, a sentence set with nearly optimal overall characteristics is searched as the summary. This method seamlessly integrates the query preference and redundancy of the summary into the fitness function of the genetic algorithm, so that the generated summary has better comprehensive quality. 100 news texts of different topics were randomly selected from Sina.com as summary test texts. Through experiments, the effectiveness of this strategy and method was verified.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore