Learning to rank: from pairwise approach to listwise approach Export

@inproceedings{citeulike:2898739, abstract = {The paper is concerned with learning to rank, which is to construct a model or a function for ranking objects. Learning to rank is useful for document retrieval, collaborative filtering, and many other applications. Several methods for learning to rank have been proposed, which take object pairs as 'instances' in learning. We refer to them as the pairwise approach in this paper. Although the pairwise approach offers advantages, it ignores the fact that ranking is a prediction task on list of objects. The paper postulates that learning to rank should adopt the listwise approach in which lists of objects are used as 'instances' in learning. The paper proposes a new probabilistic method for the approach. Specifically it introduces two probability models, respectively referred to as permutation probability and top k probability, to define a listwise loss function for learning. Neural Network and Gradient Descent are then employed as model and algorithm in the learning method. Experimental results on information retrieval show that the proposed listwise approach performs better than the pairwise approach.}, address = {New York, NY, USA}, author = {Cao, Zhe and Qin, Tao and Liu, Tie Y. and Tsai, Ming F. and Li, Hang}, booktitle = {ICML '07: Proceedings of the 24th international conference on Machine learning}, citeulike-article-id = {2898739}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1273513}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1273496.1273513}, doi = {10.1145/1273496.1273513}, isbn = {978-1-59593-793-3}, keywords = {c-learn-to-rank, s-collected, t-retrieval}, location = {Corvalis, Oregon}, pages = {129--136}, posted-at = {2009-07-05 14:12:07}, priority = {2}, publisher = {ACM}, title = {Learning to rank: from pairwise approach to listwise approach}, url = {http://dx.doi.org/10.1145/1273496.1273513}, year = {2007} }

TY - CONF ID - citeulike:2898739 L3 - citeulike-article-id:2898739 N2 - The paper is concerned with learning to rank, which is to construct a model or a function for ranking objects. Learning to rank is useful for document retrieval, collaborative filtering, and many other applications. Several methods for learning to rank have been proposed, which take object pairs as 'instances' in learning. We refer to them as the pairwise approach in this paper. Although the pairwise approach offers advantages, it ignores the fact that ranking is a prediction task on list of objects. The paper postulates that learning to rank should adopt the listwise approach in which lists of objects are used as 'instances' in learning. The paper proposes a new probabilistic method for the approach. Specifically it introduces two probability models, respectively referred to as permutation probability and top k probability, to define a listwise loss function for learning. Neural Network and Gradient Descent are then employed as model and algorithm in the learning method. Experimental results on information retrieval show that the proposed listwise approach performs better than the pairwise approach. CY - Corvalis, Oregon SN - 978-1-59593-793-3 AD - New York, NY, USA EP - 136 TI - Learning to rank: from pairwise approach to listwise approach PB - ACM T2 - ICML '07: Proceedings of the 24th international conference on Machine learning SP - 129 KW - c-learn-to-rank KW - s-collected KW - t-retrieval AU - Cao, Zhe AU - Qin, Tao AU - Liu, Tie AU - Tsai, Ming AU - Li, Hang PY - 2007/// UR - http://dx.doi.org/10.1145/1273496.1273513 ER -