The TREC 2002 Filtering Track Report
نویسندگان
چکیده
The TREC–11 filtering track measures the ability of systems to build persistent user profiles which successfully separate relevant and non-relevant documents in an incoming stream. It consists of three major subtasks: adaptive filtering, batch filtering, and routing. In adaptive filtering, the system begins with only a topic statement and a small number of positive examples, and must learn a better profile from on-line feedback. Batch filtering and routing are more traditional machine learning tasks where the system begins with a large sample of evaluated training documents. This report describes the track, presents some evaluation results, and provides a general commentary on lessons learned from this year’s track.
منابع مشابه
Microsoft Cambridge at TREC 2002: Filtering Track
Six runs were submitted for the Adaptive Filtering track, four on the adaptive filtering task (ok11af??), and two on the routing task (msPUM?). The adaptive filtering system has been somewhat modified from the one used for TREC–10, largely for efficiency and flexibility reasons; the basic filtering algorithms remain similar to those used in recent TRECs. For the routing task, a completely new s...
متن کاملInformation Filtering, Novelty Detection, and Named-Page Finding
In TREC 11, our group participated in the Novelty track, Filtering track, and the Named-Page Finding task of the Web track. This paper describes our approaches, experiments, and results. As the approach for each task is quite different, the paper contains a section for each of the tasks. The following section describes our experiments in adaptive filtering, Section 3 describes named-page findin...
متن کاملRutgers Filtering Work at TREC 2002: Adaptive and Batch
This year at TREC 2002 we participated in the adaptive filtering sub-task of the filtering track with some models for training a Rocchio classifier. Results were poorer than average on the utility type measures. Using simple feature selection produced better than average results on an F-type measure. The key to our approach was the use of pseudojudgments, and an approach to threshold updating. ...
متن کاملTREC 11 Experiments at CAS-ICT: Filtering and Web
CAS-ICT took part in the TREC conference for the second time this year and we undertook two tracks of TREC-11. For filtering track, we have submitted results of all three subtasks. In adaptive filtering, we paid more attention to undetermined documents processing, profile building and adaptation. In batch filtering and routing, a centroid-based classifier is used with preprocessed samples. For ...
متن کامل