本研究主要在探詩建置一個中文檢索評估系統的可行性。數位化成為必要的趨勢 之後，世界上各重要語言都受到其使用國家的重視與贊助而開始進行研究。1992年起美國國 家標準暨技術局（NIST）和美國國防部尖端研究企畫署的資訊科技室（DARPA）開始組織一 系列的文獻獻檢索會議（Text REtrieval Conference, TREC），每年舉辦一次評比研討會 議，至今已有TREC 9的召開。日本在籌畫五年之後，亦在今年（1999）開始推展日文的檢索 評比研討活動。本文提出建置一個中文檢索評估系統可行性研究，並期望政府重視支持而能 建設一個良好的中文檢索研究環境，以便鼓勵更多的研究者參與中文資訊檢索的研究。

　　　　　Chinese language retrieval evaluation has caught the attention of researchers studying cross-language retrieval techniques internationally. The importance of Chinese language in information retrieval (IR) has been recognized, however, the evaluation tool and research environment is limited. Given the importance of Networked Information Retrieval (NIR) and the accelerating development of Digital Library (DL), a Chinese corpus test collection and a set of evaluation criteria for IR evaluation is desperately needed for the IR research and development community. The purpose of this study is to propose a prototype of CTREC. Main tasks and tracks, test collections, topics, measurement procedures and evaluation criteria are proposed. Some solutions for implementing CTREC are also suggested.