跨語言資訊檢索中查詢問題特性於檢索效益之影響

Influences of Query Characteristics to Retrieval Performance in Cross-Language Information Retrieval

10.6120/JoEMLS.200812_46(2).0258.RS.CM

陳光華(Kuang-Hua Chen)；吳恬安(Tien-An Wu)

資訊需求 ； 查詢問句 ； 查詢問題 ； 檢索效益 ； 查詢主題 ； Information need ； Query ； Question ； Retrieval performance ； Topic

教育資料與圖書館學

46卷2期（2008 / 12 / 01）

183 - 210

繁體中文

本研究分別由查詢主題(Topic)的文本特性、語言特性，及欄位特性等三個面向，檢視第六屆NTCIR資訊檢索評估會議之跨語言檢索評估項目的資料，試圖找出查詢主題特性對檢索效益之影響。研究結果發現查詢主題的文本特性僅有「主題類別」對檢索效益具影響力，涵蓋地域、時間空間明確性，條件敘述明確性及數量等對檢索效益沒有顯著差異；語言特性方面，以韓文表現最佳，表示在CLIR機制中，選用不同語言的問題集與文件集對於檢索效益的確會造成影響；欄位特性方面，本研究發現不論選用標題(Title)、簡短資訊需求(Description)、詳細資訊需求(Narrative)、相關概念(Concepts)為索引來源，不會造成明顯檢索效益的差異，但部分欄位的檢索效益確實比較好；在研究團隊與欄位特性及語言特性的交互作用的檢定，本研究發現研究團隊與檢索欄位在檢索效益上有交互作用，也就是說研究團隊的不同與檢索欄位的不同對檢索效益會造成影響，而在語言組合的選擇上則無明顯的交互作用。

This study investigated the influences of structured query on retrieval performance from textual, linguistic, and fielded characteristics. The search runs of NCTIR-6 CLIR Task have been used as the targeted data for this study. The results concluded that only subject out of other textual characteristics demonstrated significant effects on retrieval performance; linguistic characteristics showed great impacts on retrieval performance; fielded information did not show significant effects on retrieval performance but some fielded information performed better than others. This study also made clear that there existed interactions between fielded information in queries and participating teams (consequently the retrieval techniques used by these teams) but no significant interactions between linguistic characteristics and participating teams.

1. The TREC-9 query track
2. Derr, R. L.(1982).A classification of questions in information retrieval by conceptual presupposition.Proceedings of the 45th Annual Meeting of the American Society for Information Science
3. Fidel, R.,Soergel, D.(1983).Factors affecting online bibliographic retrieval: A conceptual framework for research.Journal of the American Society for Information Science,34(3),163-180.
4. Keyes, J. G.(1996).Using conceptual categories of questions to measure differences in retrieval performance.Proceedings of the 59th Annual Meeting of the American Society for Information Science
5. Kishida, K.,Chen, K. H.,Lee, S.,Kuriyama, K.,Kando, N.,Chen, H. H.(2007).Procedings of NTCIR-6 Workshop Meeting.Japan:Symposium held at the Tokyo.
6. Lancaster, F. W.(1968).Evaluation of the MEDLARS demand search service.Bethesda, Md.:National Library of Medicine.
7. Lehnert, W. G.(1978).The process of question answering: A computer simulation of cognition.Hillsdale, NJ:Lawrence Erlbaum Associates.
8. Murachver, T.,A.C. Graesser,J. B. Black (Eds.)(1985).The psychology of questions.Lawrence Hillsdale, NJ:Erlbaum Associates.
9. Nelson, M. J.(1995).The effect of query characteristics on retrieval results in the TREC retrieval tests.Proceedings of the 23rd annual conference of the canadian association for information science (CAIS 95),Canada:
10. Saracevic, T.,Baxter, M. A.(1983).On a method for studying the structure and nature of requests in information retrieval.Proceedings of the 46th Annual Meeting of the American Society for Information Science
11. Saracevic, T.,Kantor, P.(1988).A study of information seeking and retrieving II: Users, questions, and effectiveness.Journal of the American Society for Information Science,39(3),177-196.
12. 王怡人(2004)。碩士論文(碩士論文)。台北市，國立臺灣大學圖書資訊學研究所。
13. 江玉婷(1999)。碩士論文(碩士論文)。台北市，國立臺灣大學圖書資訊學研究所。
14. 陳光華、江玉婷(2000)。中文資訊檢索測試集之設計與製作。資訊傳播與圖書館學，6(3)，61-80。
15. 陳明君(1999)。碩士論文(碩士論文)。台北市，國立臺灣大學圖書資訊學研究所。
16. 黃怡如(1999)。碩士論文(碩士論文)。台北市，國立臺灣大學圖書資訊學研究所。