1989
DOI: 10.1145/74697.74703
|View full text |Cite
|
Sign up to set email alerts
|

A very fast prototype retrieval system using statistical ranking

Abstract: The most striking result in working with Professor Gerald Salton over 20 years ago on the comparison between the SMART system and the MEDLARS system [Salton69] was the fact that whereas Boolean retrieval (MEDLARS) did very well or very poorly, the SMART system always seemed to find some of the relevant records. All of us working at Cornell University during that time wanted to run a full-scale comparison between these systems to demonstrate what was to us the clear superiority of a ranking retrieval system, bu… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

1990
1990
2005
2005

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 8 publications
(2 citation statements)
references
References 9 publications
0
2
0
Order By: Relevance
“…All of us working at Cornell University during that time wanted to run a full-scale comparison between these systems to demonstrate what was to us the clear superiority of a ranking retrieval system [italics added]. (Harman & Candela, 1989) This quote illustrates very well the atmosphere of the experiment and the eagerness of all the participants "to demonstrate what was to us the clear superiority of a ranking retrieval system." But what would have happened if the experiments were conducted by the creators of a new Boolean system who were convinced of its "clear superiority" and tried to demonstrate this superiority?…”
Section: Analysis Of the Existing Criticism Of A Boolean Systemmentioning
confidence: 99%
“…All of us working at Cornell University during that time wanted to run a full-scale comparison between these systems to demonstrate what was to us the clear superiority of a ranking retrieval system [italics added]. (Harman & Candela, 1989) This quote illustrates very well the atmosphere of the experiment and the eagerness of all the participants "to demonstrate what was to us the clear superiority of a ranking retrieval system." But what would have happened if the experiments were conducted by the creators of a new Boolean system who were convinced of its "clear superiority" and tried to demonstrate this superiority?…”
Section: Analysis Of the Existing Criticism Of A Boolean Systemmentioning
confidence: 99%
“…Experiments were run to test various efficiency algorithms, with the result s always being tested using the standard test collection t o ensure that improvements in response time had no t sacrificed effective performance . A detailed descriptio n of the prototype data structures, the algorithms selected , and the experiments themselves is given in an earlie r paper (Harman & Candela 1989) . A brief overview o f the system internals is presented below .…”
Section: Prototype Descriptio Nmentioning
confidence: 99%