Mining broad latent query aspects from search sessions Export

@inproceedings{citeulike:5044001, abstract = {Search queries are typically very short, which means they are often underspecified or have senses that the user did not think of. A broad latent query aspect is a set of keywords that succinctly represents one particular sense, or one particular information need, that can aid users in reformulating such queries. We extract such broad latent aspects from query reformulations found in historical search session logs. We propose a framework under which the problem of extracting such broad latent aspects reduces to that of optimizing a formal objective function under constraints on the total number of aspects the system can store, and the number of aspects that can be shown in response to any given query. We present algorithms to find a good set of aspects, and also to pick the best k aspects matching any query. Empirical results on real-world search engine logs show significant gains over a strong baseline that uses single-keyword reformulations: a gain of 14\% and 23\% in terms of human-judged accuracy and click-through data respectively, and around 20\% in terms of consistency among aspects predicted for "similar" queries. This demonstrates both the importance of broad query aspects, and the efficacy of our algorithms for extracting them.}, address = {New York, NY, USA}, author = {Wang, Xuanhui and Chakrabarti, Deepayan and Punera, Kunal}, booktitle = {KDD '09: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining}, citeulike-article-id = {5044001}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1557019.1557114}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1557019.1557114}, doi = {10.1145/1557019.1557114}, isbn = {978-1-60558-495-9}, keywords = {clustering, queries}, location = {Paris, France}, pages = {867--876}, posted-at = {2009-07-03 09:27:21}, priority = {2}, publisher = {ACM}, title = {Mining broad latent query aspects from search sessions}, url = {http://dx.doi.org/10.1145/1557019.1557114}, year = {2009} }

TY - CONF ID - citeulike:5044001 L3 - citeulike-article-id:5044001 N2 - Search queries are typically very short, which means they are often underspecified or have senses that the user did not think of. A broad latent query aspect is a set of keywords that succinctly represents one particular sense, or one particular information need, that can aid users in reformulating such queries. We extract such broad latent aspects from query reformulations found in historical search session logs. We propose a framework under which the problem of extracting such broad latent aspects reduces to that of optimizing a formal objective function under constraints on the total number of aspects the system can store, and the number of aspects that can be shown in response to any given query. We present algorithms to find a good set of aspects, and also to pick the best k aspects matching any query. Empirical results on real-world search engine logs show significant gains over a strong baseline that uses single-keyword reformulations: a gain of 14% and 23% in terms of human-judged accuracy and click-through data respectively, and around 20% in terms of consistency among aspects predicted for "similar" queries. This demonstrates both the importance of broad query aspects, and the efficacy of our algorithms for extracting them. CY - Paris, France SN - 978-1-60558-495-9 AD - New York, NY, USA EP - 876 TI - Mining broad latent query aspects from search sessions PB - ACM T2 - KDD '09: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining SP - 867 KW - clustering KW - queries AU - Wang, Xuanhui AU - Chakrabarti, Deepayan AU - Punera, Kunal PY - 2009/// UR - http://dx.doi.org/10.1145/1557019.1557114 ER -