This report constitutes the proceedings of the seventh Text REtrieval Conference (TREC-7) held in Gaithersburg, Maryland, November 9-11, 1998. The conference was co-sponsored by the National Institute of Standards and Technology (NIST) and the Defense Advanced Research Projects Agency (DARPA), and was attended by 150 people. Fifty-six groups including participants from 13 different countries and 19 companies were represented.The goal of the conference was to bring research groups together to discuss their work on a large test collection. The diversity of the participants meant that a wide variety of retrieval techniques were represented, including new models for retrieval and refined machine learning techniques. Results were scored using a common evaluation package, so groups were able to compare the effectiveness of different techniques, and to discuss how differences between systems affected performance. In addition to the main evaluation, seven additional evaluations, called tracks, allowed participants to focus on particular common subproblems.The conference included paper sessions and discussion groups. This proceedings includes papers from most of the participants (some groups did not submit papers), track reports that define the problem addressed by the track plus summarize the main track results, and tables of individual group results. The TREC-7 proceedings web site also contains system descriptions that detail the timing and storage requirements of the different runs.
information retrieval, search engines, text retrieval, TREC
and Harman, D.
The Seventh Text REtrieval Conference (TREC-7), Special Publication (NIST SP), National Institute of Standards and Technology, Gaithersburg, MD
(Accessed February 27, 2024)