|
|
|
                                          
|
Return to Posters
We describe an evaluation of result set filtering techniques for providing ultra-high precision in the task of presenting related news for general web queries. In this task, the negative user experience generated by retrieving non-relevant documents has a much worse impact than not retrieving relevant ones. We adapt cost-based metrics from the document filtering domain to this result filtering problem in order to explicitly examine the tradeoff between missing relevant documents and retrieving non-relevant ones. A large manual evaluation of three simple threshold filters shows that the basic approach of counting matching title terms outperforms also incorporating selected abstract terms based on part-of-speech or higher-level linguistic structures. Simultaneously, leveraging these cost-based metrics allows us to explicitly determine what other tasks would benefit from these alternative techniques.
@inproceedings{1009087, author = {Steven M. Beitzel and Eric C. Jensen and Abdur Chowdhury and David Grossman and Ophir Frieder}, title = {Evaluation of filtering current news search results}, booktitle = {SIGIR '04: Proceedings of the 27th annual international conference on Research and development in information retrieval}, year = {2004}, isbn = {1-58113-881-4}, pages = {494--495}, location = {Sheffield, United Kingdom}, doi = {http://doi.acm.org/10.1145/1008992.1009087}, publisher = {ACM Press}, }  ©2005 Association for Computing Machinery |
