Ellen M. Voorhees. Evaluation by highly relevant documents. In Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 74-82, 2001. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Using Manually-Built Web Directories for Automatic .. - Beitzel, Jensen.. (2003) (Correct)
....a valid ranking of engines according to general known item effectiveness, the set of query document pairs needs to be reasonable, unbiased, and large enough to satisfy both sampling and stability. It has been shown that even manual assessors rarely agree on which document is the best for a query [6]. The heuristic of selecting documents as best by exact title matches is a source of error in our method, but we hypothesize that we can control this error if our selected documents are reasonably good, and we use enough of them. Two other factors that must be controlled in this methodology are ....
Voorhees, E. Evaluation by highly relevant documents. SIGIR'01, 74-8.
The Importance of Morphological Normalization for XML .. - Kamps, Marx, de.. (2002) (Correct)
....scores are calculated by means of the function f g given above. The strict and generalized measures defined above differ from the standard mean average precision scores. When ignoring the coverage dimension, the strict measure is similar to the work on judging by highly relevant document [16]. This strict measure is still a dichotomous measure. When ignoring coverage, the generalized measure is similar to the graded measures of relevance [9] Run MAP Impr. P. at 0 Impr. Combined run 0.185 12 0.528 36 n Grammed run 0.183 11 0.544 40 Stemmed run 0.165 0 0.388 0 Strict ....
E. M. Voorhees. Evaluation by highly relevant documents. In D. H. Kraft, W. B. Croft, D. J. Harper, and J. Zobel, editors, Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 74--82. ACM Press, New York NY, USA, 2001.
Analysis of Lexical Signatures for Finding Lost or Related - Park (2002) (Correct)
....extract both desired and relevant documents is relatively stable over different search engines. 5. 2 Performance Evaluation Methods for Search Engines It is widely argued that search engines should be evaluated by their ability to retrieve highly relevant documents rather than all possible pages [8, 19]. Lexical signatures are good query terms that can extract relevant documents when the desired document cannot be retrieved. One limitation of lexical signatures mentioned by Phelps and Wilensky is that their performance can depend on particular search engines. However, this limitation can be ....
E. M. Voorhees. Evaluation by Highly Relevant Documents. In SIGIt 2001.
Overview of TREC 2001 - Ellen Voorhees Donna (2001) (38 citations) Self-citation (Voorhees) (Correct)
No context found.
Ellen M. Voorhees. Evaluation by highly relevant documents. In Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 74-82, 2001.
Overview of the TREC 2003 Question Answering Track - Ellen Voorhees National (1999) (8 citations) Self-citation (Voorhees) (Correct)
No context found.
Ellen M. Voorhees. Evaluation by highly relevant documents. In Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 74--82, 2001.
A study of the assessment of relevance for the INEX'02.. - Gabriella Kazai Sherezad (2004) (Correct)
No context found.
Voorhees, E. (2001): Evaluation by highly relevant documents. Proceedings of the 24th ACM-SIGIR conference on research and development in information retrieval, New York, pp. 74-82.
A study of the assessment of relevance for the INEX'02.. - Kazai, Masood, Lalmas (2004) (Correct)
No context found.
Voorhees, E. (2001): Evaluation by highly relevant documents. Proceedings of the 24th ACM-SIGIR conference on research and development in information retrieval, New York, pp. 74-82.
Using Titles and Category Names from Editor-driven .. - Beitzel, Jensen.. (2003) (Correct)
No context found.
Voorhees, E. Evaluation by highly relevant documents. In Proceedings of SIGIR'01 (New Orleans, LA, 2001), ACM Press, 74-82.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC