陳光華2006-07-262018-05-302006-07-262018-05-301999-07-31http://ntur.lib.ntu.edu.tw//handle/246246/20395在國內資訊檢索研究已日趨受到重視，合適的測試 評估機制卻十分缺乏的背景下，本研究實際進行測 試集的規劃與建置工作。測試集建構工作主要包括 蒐集整理文件、建立查詢主題、以及進行相關判斷 三個部分。本研究建立的文件集來源為新聞網站中 的五種電子報，共有132,207 篇文件。查詢主題是 透過網路問卷實際徵集查詢需求，並進行三次的篩 選之後，修正建構而成，共完成50 個查詢主題。相 關判斷的部分則是先對每個查詢主題建立一相關文 件候選集，再針對候選集中的每篇文件以人工進行 相關判斷，每一查詢主題由三位次判斷者同時進 行，最後，則依據判斷結果計算並定義文件的相關 程度。經由研究結果的分析顯示，本測試集有完整 的架構及一定的規模，未來的研究應可以此為基 礎，作進一步的擴展與改進The research and development of information retrieval (IR) has made much progress recently. However, there’s not any applicable mechanism for system evaluation in the Chinese research society. This project aims at the design and the implementation for Chinese information retrieval benchmark. Generally speaking, a benchmark consists of a set of documents, a set of topics, and a set of relevance between documents and topics. Accordingly, our task is also separated into three parts. The document set is downloaded from various electronic news sites, and totally 132,207 documents are collected. To build the topics, we investigate the real user information needs by using a questionnaire, and then modify them to be the formal topics. As to relevance judgment, we first set up a pool of candidate documents for each topic, and then invite three persons to judge the relevance. Finally, we combine the judgments and offer a relevance measure for each document in the pool. The result of our research shows that the benchmark possesses a complete structure and medium scale, and we may further expand and improve it based on existing framework in the future.application/pdf96206 bytesapplication/pdfzh-TW國立臺灣大學圖書資訊學系暨研究所標竿測試集資訊檢索相關判斷查詢主題BenchmarkInformation RetrievalRelevance JudgmentTopicreporthttp://ntur.lib.ntu.edu.tw/bitstream/246246/20395/1/882213E002035.pdf