Okapi at TREC-2
نویسندگان
چکیده
This paper reports on City University's work on the TREC{2 project from its commencement up to November 1993. It includes many results which were obtained after the August 1993 deadline for submission of o cial results. For TREC{2, as for TREC{1, City University used versions of the Okapi text retrieval system much as described in [2] (see also [3, 4]). Okapi is a simple and robust set-oriented system based on a generalised probabilistic model with facilities for relevance feedback, but also supporting a full range of deterministic Boolean and quasi-Boolean operations. For TREC{1 [1] the \standard" Robertson{Sparck Jones weighting function was used for all runs (equation 1, see also [5]). City's performance was not outstandingly good among comparable systems, and the intention for TREC{2 was to develop and investigate a number of alternative probabilistic term-weighting functions. Other possibilities included varieties of query expansion, database models enabling paragraph retrieval and the use of phrases obtained by query parsing. Unfortunately, a prolonged disk failure prevented realistic test runs until almost the deadline for submission of results. A full inversion of the disks 1 and 2 database was only achieved a few hours before the nal automatic runs. None of the new weighting functions (Section 1.1) was properly evaluated until after the results had been submitted to NIST; we have since discovered that several of these models perform much better than the weighting functions used for the o cial runs, and most of the results reported herein are from these later runs.
منابع مشابه
UCLA-Okapi at TREC-2: Query Expansion Experiments
This is the rst participation of the Graduate School of Library and Information Science, University of California at Los Angeles in the TREC Conference. For TREC{2, Category B, UCLA used a version of the Okapi text retrieval system that was made available to UCLA by City University, London, UK. OKAPI has been described in TREC1 (Robertson, Walker, Hancock-Beaulieu, Gull & Lau, 1993a) as well as...
متن کاملOkapi at TREC-5
City submitted two runs each for the automatic ad hoc, very large collection track, automatic routing and Chinese track; and took part in the interactive and ltering tracks. There were no very signi cant new developments; the same Okapi-style weighting as in TREC{3 and TREC{4 was used this time round, although there were attempts, in the ad hoc and more notably in the Chinese experiments, to ex...
متن کاملMultiText Legal Experiments at TREC 2008
Our TREC 2008 e ort used fusion IR methods identical to those used for our TREC 2007 e ort; in addition we used logistic regression to attempt to learn the optimal K value for the primary F1@K measure introduced at TREC 2008. We used the Wumpus search engine combining several methods that have proven successful, including cover density ranking and Okapi BM25 ranking, and combination methods. St...
متن کاملTREC 14 Enterprise Track at CSIRO and ANU
By the time of submission deadline, we completed two tasks: known-item search and discussion search. For both tasks, we used the PADRE retrieval system [1], in which the Okapi BM25 relevance function was implemented. Each message in the collection was treated as an independent document, so both topic distillation scoring and same site suppression mechanism were turned off (i.e. -nocool and –SSS...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1993