%0 Conference Paper %1 citeulike:14139126 %A Mitsui, Matthew %A Shah, Chirag %B Proceedings of the 10th ACM Conference on Recommender Systems %C New York, NY, USA %D 2016 %I ACM %K query-recommendation recsys2016 social-search topic-modeling %P 27--30 %R 10.1145/2959100.2959154 %T Multi-Word Generative Query Recommendation Using Topic Modeling %U http://dx.doi.org/10.1145/2959100.2959154 %X Query recommendation predominantly relies on search logs to use existing queries for recommendation, typically calculating query similarity metrics or transition probabilities from the log. While effective, such recommendations are limited to the queries, words, and phrases in the log. They hence do not recommend potentially useful, entirely novel queries. Recent query recommendation methods have proposed generating queries on a topical or thematic level, though current approaches are limited to generating single words. We propose a hybrid method for constructing multi-word queries in this generative sense. It uses Latent Dirichlet Allocation to generate a topic for exploration and skip-gram modeling to generate queries from the topic. According to additional evaluation metrics we present, our model improves diversity and has some room for improving relevance, yet offers an interesting avenue for query recommendation. %@ 978-1-4503-4035-9

@inproceedings{citeulike:14139126, abstract = {{Query recommendation predominantly relies on search logs to use existing queries for recommendation, typically calculating query similarity metrics or transition probabilities from the log. While effective, such recommendations are limited to the queries, words, and phrases in the log. They hence do not recommend potentially useful, entirely novel queries. Recent query recommendation methods have proposed generating queries on a topical or thematic level, though current approaches are limited to generating single words. We propose a hybrid method for constructing multi-word queries in this generative sense. It uses Latent Dirichlet Allocation to generate a topic for exploration and skip-gram modeling to generate queries from the topic. According to additional evaluation metrics we present, our model improves diversity and has some room for improving relevance, yet offers an interesting avenue for query recommendation.}}, added-at = {2018-03-19T12:24:51.000+0100}, address = {New York, NY, USA}, author = {Mitsui, Matthew and Shah, Chirag}, biburl = {https://www.bibsonomy.org/bibtex/2a860368d52122e10aefe4d67e31f6d7a/aho}, booktitle = {Proceedings of the 10th ACM Conference on Recommender Systems}, citeulike-article-id = {14139126}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=2959154}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/2959100.2959154}, doi = {10.1145/2959100.2959154}, interhash = {232534cf726ee0cdaa2c4580ac895893}, intrahash = {a860368d52122e10aefe4d67e31f6d7a}, isbn = {978-1-4503-4035-9}, keywords = {query-recommendation recsys2016 social-search topic-modeling}, location = {Boston, Massachusetts, USA}, pages = {27--30}, posted-at = {2016-09-17 16:41:44}, priority = {2}, publisher = {ACM}, series = {RecSys '16}, timestamp = {2018-03-19T12:24:51.000+0100}, title = {{Multi-Word Generative Query Recommendation Using Topic Modeling}}, url = {http://dx.doi.org/10.1145/2959100.2959154}, year = 2016 }