CAJ | 학술논문

聚焦查询的函数计算句子重要度,以体现问题与预期答案中的词密度特性.通过窗口从头到尾滑动来计算句子的权值选择出权值高的作为文摘.实验结果表明该方法形成的文摘优于Google文摘.
취초사순적함수계산구자중요도,이체현문제여예기답안중적사밀도특성.통과창구종두도미활동래계산구자적권치선택출권치고적작위문적.실험결과표명해방법형성적문적우우Google문적.
Query-focused summarization laid emphasis on user's concern in the document.An approach to query-focused automatic summarization is presented.It utilizes search engine as tool for seeking answer.The importance of each sentence is computed by the Hanning window to take the density of words contained in the question and prospective answering acceunt.Summarize a document by selecting the sentences with high weights as computed by moving a window from the beginning to the end of the document.Experimental results show that the summarization is better than Google's.