随着富媒体展现形式被越来越多地引入搜索交互界面,搜索引擎的结果页面呈异质化和二维模块展现形式,这对传统的点击预测模型提出了巨大的挑战。针对这一情况,我们对实际搜索引擎结果页面的多模态结果进行了分析,构建了一个结合深度神经网络和点击模型的框架,该框架既包含了神经网络的特性,又利用了点击模型的预测能力。我们希望利用这个框架挖掘出多模态信息与文本信息之间的相关性,使之具有描述异质化结果和二维模块展示形式的能力。实验表明,我们的框架相较于传统的点击模型在点击预测性能上有显著提升,但由于搜索引擎的多模态结果内容复杂,仅利用多模态结果的底层特征,即使使用深度神经网络,从中能够挖据出的语义相关性较弱。
Abstract
With the rich media introduced into searching interface, the result pages of the search engine appear to be heterogeneous and in a form of two-dimensional distribution. To deal with this new challenge to traditional click model, we analyze the result pages of a popular commercial search engine and build a click model based on deep neural network, trying to reveal correlations between multimedia information and text information. This framework contains both the characteristics of neural network and prediction ability of click model. The experiment demonstrates that our framework is well improved compared to original click model. However, due to the complexity of multimedia contents, even deep neural network would produce quite weak semantic correlations if we rely merely on basic characteristics of multimedia results.
关键词
异质化结果 /
深度神经网络 /
点击模型
{{custom_keyword}} /
Key words
heterogeneous results /
deep neural network /
click model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Sparck J K. A statistical interpretation of term specificity and its application in retrieval[J]. Journal of documentation, 1972, 28(1):11-21.
[2] Agichtein E, Brill E, Dumais S, et al. Learning user interaction models for predicting web search result preferences[C]//Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2006:3-10.
[3] Chuklin A, Markov I, Rijke M. Click models for web search[J]. Synthesis Lectures on Information Concepts, Retrieval, and Services, 2015, 7(3):1-115.
[4] Severyn A, Moschitti A. Learning to rank short text pairs with convolutional deep neural networks[C]//Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2015.
[5] Craswell N, Zoeter O, Taylor M, et al. An experimental comparison of click position-bias models[C]//Proceedings of the 2008 International Conference on Web Search and Data Mining, ACM, 2008:87-94.
[6] Guo F, Liu C, Wang Y M. Efficient multiple-click models in web search[C]//Proceedings of the Second ACM International Conference on Web Search and Data Mining, ACM, 2009:124-131.
[7] Dupret G E, Piwowarski B. A user browsing model to predict search engine click data from past observations[C]//Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, 2008:331-338.
[8] Chapelle O, Zhang Y. A dynamic bayesian network click model for web search ranking[C]//Proceedings of the 18th International Conference on World Wide Web, ACM, 2009:1-10.
[9] Wang H, Zhai C, Dong A, et al. Content-aware click modeling//The 23rd International World Wide Web Conference (WWW’2013), 2013.
[10] Wang C, Liu Y, Wang M, et al. Incorporating non-sequential behavior into click models[C]//Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, 2013:283-292.
[11] Salakhutdinov R, Hinton G. Semantic hashing. International Journal of Approximate Reasoning, 2009, 50(7):969-978.
[12] Huang P S, He X, Gao J, et al. Learning deep structured semantic models for web search using click through data[C]//Proceedings of the 22nd ACM International Conference on Conference on Information and Knowledge Management, ACM, 2013:2333-2338.
[13] Shen Y, He X, Gao J, et al. Learning semantic representations using convolutional neural networks for web search[C]//Proceedings of the Companion Publication of the 23rd International Conference on World Wide Web Companion, International World Wide Web Conferences Steering Committee, 2014:373-374.
[14] Liu Q, Yu F, Wu S, et al. A convolutional click prediction model[C]//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, ACM, 2015:1743-1746.
[15] Zhang Y, Dai H, Xu C, et al. Sequential click prediction for sponsored search with recurrent neural networks. arXiv preprint arXiv:1404. 5772, 2014.
[16] Severyn A, Moschitti A. Learning to rank short text pairs with convolutional deep neural networks[C]//Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, 2015:373-382.
[17] Bengio Y, Lecun Y. Convolutional networks for images, speech, and time-series[J]. The Handbook of Brain Theory & Neural, 1995(10):3361.
[18] Krizhevsky A, Sutskever I, Hinton G E. Image net classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 25(2):2012.
[19] Lin M, Lu Z, Li H. Learning to answer questions from image using convolutional neural network[C]//Proceedings of the AAAI, 2016, 3(7):16.
[20] Wan J, Wang D, Hoi S C H, et al. Deep learning for content-based image retrieval:A comprehensive study[C]//Proceedings of the 22nd ACM International Conference on Multimedia. ACM, 2014:157-166.
[21] Mikolov T, Sutskever I, Chen K, et al. Distributed representations of words and phrases and their compositionality[C]//Proceedings of Advances in neural information processing systems, 2013:3111-3119.
[22] Nair V, Hinton G E. Rectified linear units improve restricted Boltzmann machines[C]//Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010:807-814.
[23] A Bordes, J Weston, N Usunier. Open question answering with weakly superised embedding models[M]. In Machine Learning and Knowledge Discovery in Databases. Springer, 2014:165-180.
[24] Echihabi A, Marcu D. A noisy-channel approach to question answering[C]//Proceedings of the 41st Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 2003(1):16-23.
[25] 刘龙飞. 基于卷积神经网络的微博情感倾向性分析[J]. 中文信息学报, 2015, 29(6):159-165.
[26] 孙晓, 何家劲, 任福继. 基于多特征融合的混合神经网络模型讽刺语用判别[J]. 中文信息学报, 2016, 30(6):215-223.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61622208, 61532011, 61472206);国家973计划(2015CB358700)
{{custom_fund}}
PDF(4186 KB)
