查詢結果分析
相關文獻
- 中文全文文件群集索引理論研究與實證
- 中文全文資訊檢索之效能評量初探
- 網路文件自動分類
- 利用相關回饋建立概念化的使用者興趣檔以協助使用者進行網頁查詢
- WWW資訊檢索的新趨勢--欄位檢索
- Social Dimensions of the Digital Revolution
- Searching for Information on the Internet Using Medical World Search
- Information Extraction: Beyond Document Retrieval
- An Assessment of Character-based Chinese News Filtering Using Latent Semantic Indexing
- 架構在WWW與Z39.50上的近似自然語言OPAC檢索系統
頁籤選單縮合
題 名 | 中文全文文件群集索引理論研究與實證=A Theoretic and Empirical Research of Cluster Indexing for Mandarin Chinese Full Text Document |
---|---|
作 者 | 黃雲龍; | 書刊名 | 圖書與資訊學刊 |
卷 期 | 24 1998.02[民87.02] |
頁 次 | 頁44-68 |
分類號 | 028.7 |
關鍵詞 | 自動索引; 群集索引; 資訊檢索; 向量空間模型; 群集索引模型; 奇異值分解; Automatic indexing; Cluster indexing; Information retrieval; Vector space model; VSM; Cluster index model; CIM; Singular value decomposition; SVD; |
語 文 | 中文(Chinese) |
中文摘要 | 當前商業應用的全文檢索系統仍以字串比對的全文檢視法,配合布林查詢介面為 主流,這種系統過於簡化電子文件檢索系統環境的形式與內容關係。本研究根據向量空間模 型 (VSM),探討索引詞彙的形式與文件內容關係,運用奇異值分析技術 (SVD),建構中文全 文文件的群集索引模型 (CIM)。 本文從兒童日報全文語料庫中選取醫藥新聞 502 篇文件, 經由各項實驗設計初步獲致以下結論:CIM 索引的效果優於傳統 VSM,而且可以提昇其效能 ,達到具有權威控制機制下的索引效果。 |
英文摘要 | Since most popular commercialized systems for full text document retrieval are designed with full text scanning and Boolean logic query mode. These systems use an oversimplified relationship between the indexing form and the content of document. We use Singular Value Decomposition (SVD) try to develop a Cluster Indexing Model (CIM) based on Vector Space Model (VSM) in order to explore the index theory of cluster indexing for Chinese full test document. Test corpus was selected from Children's Daily News: the medicine news( MED) with 502 documents. Under a seriesx of experiments, the following conclusions are discovered: we find the indexing performance of CIM is better than traditional VSM, and has almost equivalent effectiveness of the authority control of index terms. |
本系統中英文摘要資訊取自各篇刊載內容。