查詢結果分析
相關文獻
- 資訊檢索查詢之自然語言處理
- 文件內容之分析--語料庫為本的模型
- 資訊擷取技術之初探
- 以Ontology為基礎的資訊抽取系統之研究--以旅遊網站為例
- WWW資訊檢索的新趨勢--欄位檢索
- Social Dimensions of the Digital Revolution
- 網路文件自動分類
- 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
頁籤選單縮合
| 題 名 | 資訊檢索查詢之自然語言處理=Natural Language Processing of Information Retrieval& Searching |
|---|---|
| 作 者 | 陳光華; | 書刊名 | 中國圖書館學會會報 |
| 卷 期 | 57 1996.12[民85.12] |
| 頁 次 | 頁141-153 |
| 分類號 | 028.7 |
| 關鍵詞 | 資訊檢索; 自然語言處理; 剖析技術; Information retrieval; Natural language processing; Parsing technology; |
| 語 文 | 中文(Chinese) |
| 中文摘要 | 在資訊檢索系統的發展已行之有年,然而使用者查詢的方式仍是以關鍵詞為基礎 ,並且結合布林邏輯運算。對於使用者而言,最自然的查詢方式是使用自然語查詢所需要的 資訊。尤其當語音輸入技術達到實用階段時,自然語言查詢的需求,將益形重要。少數具 有自然語言查詢方式的系統,使用的僅是樣式比對(Pattern Matching)的技術,無法知 道各詞彙之間的關係,當然也就無法知道各詞彙扮演的角色。本文提出一種自然語言剖析 的技術,可以快速並且穩定地剖析自然語言,分析各詞彙的關係與彼此的角色,而建構這種 剖析技術所需的資源僅僅是具有詞類標記的語料庫。在分析大規模的實驗結果之後,根據 Crossing準則,平均準確率為81%;根據PARSEVAL準則,平均的召回率與精確率皆為33%。 |
| 英文摘要 | Many researchers have devoted themselves to developing information retrieval systems for a long time. However, the form which users use to retrieve information is still keyword-based queries with Boolean operators. From user's point of view, the most natural way to issue queries is using their mother tongue. That is, user are more likely to apply natural language queries to retrieve useful information. some system accept natural language queries, but the technique they use is simple pattern-matching. Such kind of technique does not discover the relatonship among the keywords. and then does not understand the roles which these keywords play in natural language sentences. This paper proposes a new parsing technique, which can quickly and stably parse natural language sentences. Moreover, this parsing technique can find out the relationship among keywords and the roles of each grammatical constitutents. The resource needed to construct a parser based on the proposed parsing technique is tagged text corpora. After a large-scale experiment, the recall and the precision are 33% based on the PARSEVAL criterion. They accuracy is 81% based on the Crossing criterion. |
本系統中英文摘要資訊取自各篇刊載內容。