Learning query intent from regularized click graphs Export

@inproceedings{citeulike:3032046, abstract = {This work presents the use of click graphs in improving query intent classifiers, which are critical if vertical search and general-purpose search services are to be offered in a unified user interface. Previous works on query classification have primarily focused on improving feature representation of queries, e.g. , by augmenting queries with search engine results. In this work, we investigate a completely orthogonal approach --- instead of enriching feature representation, we aim at drastically increasing the amounts of training data by semi-supervised learning with click graphs. Specifically, we infer class memberships of unlabeled queries from those of labeled ones according to their proximities in a click graph. Moreover, we regularize the learning with click graphs by content-based classification to avoid propagating erroneous labels. We demonstrate the effectiveness of our algorithms in two different applications, product intent and job intent classification. In both cases, we expand the training data with automatically labeled queries by over two orders of magnitude, leading to significant improvements in classification performance. An additional finding is that with a large amount of training data obtained in this fashion, classifiers using only query words/phrases as features can work remarkably well.}, address = {New York, NY, USA}, author = {Li, Xiao and Wang, Ye Y. and Acero, Alex}, booktitle = {SIGIR '08: Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval}, citeulike-article-id = {3032046}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1390334.1390393}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1390334.1390393}, doi = {10.1145/1390334.1390393}, isbn = {978-1-60558-164-4}, keywords = {click, graphs, intent, query}, location = {Singapore, Singapore}, pages = {339--346}, posted-at = {2008-12-10 09:27:58}, priority = {2}, publisher = {ACM}, title = {Learning query intent from regularized click graphs}, url = {http://dx.doi.org/10.1145/1390334.1390393}, year = {2008} }

TY - CONF ID - citeulike:3032046 L3 - citeulike-article-id:3032046 N2 - This work presents the use of click graphs in improving query intent classifiers, which are critical if vertical search and general-purpose search services are to be offered in a unified user interface. Previous works on query classification have primarily focused on improving feature representation of queries, e.g. , by augmenting queries with search engine results. In this work, we investigate a completely orthogonal approach --- instead of enriching feature representation, we aim at drastically increasing the amounts of training data by semi-supervised learning with click graphs. Specifically, we infer class memberships of unlabeled queries from those of labeled ones according to their proximities in a click graph. Moreover, we regularize the learning with click graphs by content-based classification to avoid propagating erroneous labels. We demonstrate the effectiveness of our algorithms in two different applications, product intent and job intent classification. In both cases, we expand the training data with automatically labeled queries by over two orders of magnitude, leading to significant improvements in classification performance. An additional finding is that with a large amount of training data obtained in this fashion, classifiers using only query words/phrases as features can work remarkably well. CY - Singapore, Singapore SN - 978-1-60558-164-4 AD - New York, NY, USA EP - 346 TI - Learning query intent from regularized click graphs PB - ACM T2 - SIGIR '08: Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval SP - 339 KW - click KW - graphs KW - intent KW - query AU - Li, Xiao AU - Wang, Ye AU - Acero, Alex PY - 2008/// UR - http://dx.doi.org/10.1145/1390334.1390393 ER -