Beyond independent relevance: methods and evaluation metrics for subtopic retrieval Export

@inproceedings{citeulike:3795990, abstract = {We present a non-traditional retrieval problem we call subtopic retrieval . The subtopic retrieval problem is concerned with finding documents that cover many different subtopics of a query topic. In such a problem, the utility of a document in a ranking is dependent on other documents in the ranking, violating the assumption of independent relevance which is assumed in most traditional retrieval methods. Subtopic retrieval poses challenges for evaluating performance, as well as for developing effective algorithms. We propose a framework for evaluating subtopic retrieval which generalizes the traditional precision and recall metrics by accounting for intrinsic topic difficulty as well as redundancy in documents. We propose and systematically evaluate several methods for performing subtopic retrieval using statistical language models and a maximal marginal relevance (MMR) ranking strategy. A mixture model combined with query likelihood relevance ranking is shown to modestly outperform a baseline relevance ranking on a data set used in the TREC interactive track.}, address = {New York, NY, USA}, author = {Zhai, Cheng X. and Cohen, William W. and Lafferty, John}, booktitle = {SIGIR '03: Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval}, citeulike-article-id = {3795990}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=860435.860440}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/860435.860440}, doi = {10.1145/860435.860440}, isbn = {1-58113-646-3}, keywords = {diversity, recommender}, location = {Toronto, Canada}, pages = {10--17}, posted-at = {2008-12-16 10:14:40}, priority = {2}, publisher = {ACM}, title = {Beyond independent relevance: methods and evaluation metrics for subtopic retrieval}, url = {http://dx.doi.org/10.1145/860435.860440}, year = {2003} }

TY - CONF ID - citeulike:3795990 L3 - citeulike-article-id:3795990 N2 - We present a non-traditional retrieval problem we call subtopic retrieval . The subtopic retrieval problem is concerned with finding documents that cover many different subtopics of a query topic. In such a problem, the utility of a document in a ranking is dependent on other documents in the ranking, violating the assumption of independent relevance which is assumed in most traditional retrieval methods. Subtopic retrieval poses challenges for evaluating performance, as well as for developing effective algorithms. We propose a framework for evaluating subtopic retrieval which generalizes the traditional precision and recall metrics by accounting for intrinsic topic difficulty as well as redundancy in documents. We propose and systematically evaluate several methods for performing subtopic retrieval using statistical language models and a maximal marginal relevance (MMR) ranking strategy. A mixture model combined with query likelihood relevance ranking is shown to modestly outperform a baseline relevance ranking on a data set used in the TREC interactive track. CY - Toronto, Canada SN - 1-58113-646-3 AD - New York, NY, USA EP - 17 TI - Beyond independent relevance: methods and evaluation metrics for subtopic retrieval PB - ACM T2 - SIGIR '03: Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval SP - 10 KW - diversity KW - recommender AU - Zhai, Cheng AU - Cohen, William AU - Lafferty, John PY - 2003/// UR - http://dx.doi.org/10.1145/860435.860440 ER -