%0 Conference Paper %1 L3S_af7207a39993b703470e8e9ed120f025b9997d27 %A Demidova, Elena %A Fankhauser, Peter %A Zhou, Xuan %A Nejdl, Wolfgang %B Proc. of 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2010, Geneva, Switzerland, July 19-23, 2010. %D 2010 %K Nejdl publication %T DivQ: Diversification for Keyword Search over Structured Databases %X Keyword queries over structured databases are notoriously ambiguous. No single interpretation of a keyword query can satisfy all users, and multiple interpretations may yield overlapping results. This paper proposes a scheme to balance the relevance and novelty of keyword search results over structured databases. Firstly, we present a probabilistic model which effectively ranks the possible interpretations of a keyword query over structured data. Then, we introduce a scheme to diversify the search results by re-ranking query interpretations, taking into account redundancy of query results. Finally, we propose a-nDCG-W and WS-recall, an adaptation of a-nDCG and S-recall metrics, taking into account graded relevance of subtopics. Our evaluation on two real-world datasets demonstrates that search results obtained using the proposed diversification algorithms better characterize possible answers available in the database than the results of the initial relevance ranking.

@inproceedings{L3S_af7207a39993b703470e8e9ed120f025b9997d27, abstract = {Keyword queries over structured databases are notoriously ambiguous. No single interpretation of a keyword query can satisfy all users, and multiple interpretations may yield overlapping results. This paper proposes a scheme to balance the relevance and novelty of keyword search results over structured databases. Firstly, we present a probabilistic model which effectively ranks the possible interpretations of a keyword query over structured data. Then, we introduce a scheme to diversify the search results by re-ranking query interpretations, taking into account redundancy of query results. Finally, we propose a-nDCG-W and WS-recall, an adaptation of a-nDCG and S-recall metrics, taking into account graded relevance of subtopics. Our evaluation on two real-world datasets demonstrates that search results obtained using the proposed diversification algorithms better characterize possible answers available in the database than the results of the initial relevance ranking.}, added-at = {2012-06-15T15:46:30.000+0200}, author = {Demidova, Elena and Fankhauser, Peter and Zhou, Xuan and Nejdl, Wolfgang}, biburl = {https://www.bibsonomy.org/bibtex/27df25ded889b6724c65fa7e29c6e8ef2/l3s}, booktitle = {Proc. of 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2010, Geneva, Switzerland, July 19-23, 2010.}, interhash = {c71c60d70c303e00214657495ac568d7}, intrahash = {7df25ded889b6724c65fa7e29c6e8ef2}, keywords = {Nejdl publication}, timestamp = {2012-06-15T15:46:34.000+0200}, title = {DivQ: Diversification for Keyword Search over Structured Databases}, year = 2010 }