完整後設資料紀錄
DC 欄位語言
dc.contributor.author葉鎮源en_US
dc.contributor.authorJen-Yuan Yehen_US
dc.contributor.author柯皓仁en_US
dc.contributor.author楊維邦en_US
dc.contributor.authorHao-Ren Keen_US
dc.contributor.authorWei-Pang Yangen_US
dc.date.accessioned2014-12-12T02:27:55Z-
dc.date.available2014-12-12T02:27:55Z-
dc.date.issued2001en_US
dc.identifier.urihttp://140.113.39.130/cdrfb3/record/nctu/#NT900394087en_US
dc.identifier.urihttp://hdl.handle.net/11536/68615-
dc.description.abstract本論文提出了兩種新的文件摘要方法來摘錄原始文件中的重要語句。第一個方法屬於以文件集為基礎的摘要技術(Corpus-based Approach),此方法基於統計模型,利用特徵的分析來計算語句重要性。我們提出三個新的想法:1) 利用語句位置重要性的分級以提高不同語句位置的重要性;2)利用詞彙相關程度(Word Co-occurrence)計算找出文件中的新詞,並將新詞加入關鍵詞重要性的計算,以得到更精確的關鍵詞權重特徵值;3) 利用基因演算法訓練計算語句權重的Score Function,以期了解訓練文件集的特性。第二個方法,我們結合潛在語意分析(Latent Semantic Analysis)與主題相關地圖(Text Relationship Map)的概念,用來擷取文件中的概念結構(Conceptual Structure)以期得到語意層面的分析。實驗中,我們收集100篇新台灣週刊中關於政治類的文章,並將上述的兩種方法應用於中文文件的摘要實驗上。效益評估結果顯示,我們所提的方法都有不錯的表現,在壓縮比為30%的情況下,平均來說,召回率分別為52.0%及45.6%。zh_TW
dc.description.abstractIn this thesis, two novel approaches are proposed to extract important sentences from a document to create its summary. The first is a corpus-based approach using feature analysis. It brings up three new ideas: 1) to employ ranked position to emphasize the significance of sentence position, 2) to reshape word unit to achieve higher accuracy of keyword importance, and 3) to train a score function by the genetic algorithm for obtaining a suitable combination of feature weights. The second approach combines the ideas of latent semantic analysis and text relationship maps to interpret conceptual structures of a document. Both approaches are applied to Chinese text summarization. The two approaches were evaluated by using a data corpus composed of 100 articles about politics from New Taiwan Weekly, and when the compression ratio was 30%, average recalls of 52.0% and 45.6% were achieved respectively.en_US
dc.language.isozh_TWen_US
dc.subject中文文件摘要zh_TW
dc.subject以文件集為基礎的摘要技術zh_TW
dc.subject潛在語意分析zh_TW
dc.subject主題關係地圖zh_TW
dc.subjectChinese Text Summarizationen_US
dc.subjectCorpus-based Approachen_US
dc.subjectLatent Semantic Analysisen_US
dc.subjectText Relationship Mapen_US
dc.title文件自動化摘要方法之研究及其在中文文件的應用zh_TW
dc.titleA Study on Automated Text Summarization and Its Application on Chinese Documentsen_US
dc.typeThesisen_US
dc.contributor.department資訊科學與工程研究所zh_TW
顯示於類別:畢業論文


文件中的檔案:

  1. 039408701.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。