292 Hits in 2.2 sec

Clickthrough-based latent semantic models for web search

Jianfeng Gao, Kristina Toutanova, Wen-tau Yih
2011 Proceedings of the 34th international ACM SIGIR conference on Research and development in Information - SIGIR '11  
This paper presents two new document ranking models for Web search based upon the methods of semantic representation and the statistical translation-based approach to information retrieval (IR).  ...  Assuming that a query is parallel to the titles of the documents clicked on for that query, large amounts of query-title pairs are constructed from clickthrough data; two latent semantic models are learned  ...  Our evaluation on Web search shows that the proposed clickthrough-based latent semantic models significantly outperform both the standard IR models that do not use clickthrough data and those previous  ... 
doi:10.1145/2009916.2010007 dblp:conf/sigir/GaoTY11 fatcat:wcre2utsz5ekpiwu73wa3saq4e

Learning deep structured semantic models for web search using clickthrough data

Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, Larry Heck
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
Latent semantic models, such as LSA, intend to map a query to its relevant documents at the semantic level where keyword-based matching often fails.  ...  To make our models applicable to large-scale Web search applications, we also use a technique called word hashing, which is shown to effectively scale up our semantic models to handle large vocabularies  ...  essential for Web search.  ... 
doi:10.1145/2505515.2505665 dblp:conf/cikm/HuangHGDAH13 fatcat:6kuujlxihvfh7asjrbdfovgdkm

Learning semantic representations using convolutional neural networks for web search

Yelong Shen, Xiaodong He, Jianfeng Gao, Li Deng, Grégoire Mesnil
2014 Proceedings of the 23rd International Conference on World Wide Web - WWW '14 Companion  
This paper presents a series of new latent semantic models based on a convolutional neural network (CNN) to learn lowdimensional semantic vectors for search queries and Web documents.  ...  The new models are evaluated on a Web document ranking task using a large-scale, real-world data set.  ...  text, for Web search applications.  ... 
doi:10.1145/2567948.2577348 dblp:conf/www/ShenHGDM14 fatcat:owo6nxuqnvbqlm3o6ebwp65yla

A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval

Yelong Shen, Xiaodong He, Jianfeng Gao, Li Deng, Grégoire Mesnil
2014 Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management - CIKM '14  
In this paper, we propose a new latent semantic model that incorporates a convolutional-pooling structure over word sequences to learn low-dimensional, semantic vector representations for search queries  ...  The proposed convolutional latent semantic model (CLSM) is trained on clickthrough data and is evaluated on a Web document ranking task using a large-scale, real-world data set.  ...  A Deep Structured Semantic Model (DSSM) for Web search was proposed in [20] , which is reported to give very strong IR performance on a large-scale web search task when clickthrough data are exploited  ... 
doi:10.1145/2661829.2661935 dblp:conf/cikm/ShenHGDM14 fatcat:qzyuenvyh5dehafdkdi7xddwoq

Topic modelling of clickthrough data in image search

Donn Morrison, Theodora Tsikrika, Vera Hollink, Arjen P. de Vries, Éric Bruno, Stéphane Marchand-Maillet
2012 Multimedia tools and applications  
We use a subset of a clickthrough corpus from the image search portal of a news agency to evaluate several popular latent variable models in terms of their ability to model topics underlying queries.  ...  In this paper we explore the benefits of latent variable modelling of clickthrough data in the domain of image retrieval.  ...  The authors would also like to thank the Belga News Agency for the use of the query logs.  ... 
doi:10.1007/s11042-012-1038-8 fatcat:oaehqvunuzgkbozxfvfrkywiqi

Learning latent semantic relations from clickthrough data for query suggestion

Hao Ma, Haixuan Yang, Irwin King, Michael R. Lyu
2008 Proceeding of the 17th ACM conference on Information and knowledge mining - CIKM '08  
In this paper, aiming at providing semantically relevant queries for users, we develop a novel, effective and efficient two-level query suggestion model by mining clickthrough data, in the form of two  ...  Experimental analysis on the clickthrough data of a commercial search engine shows the effectiveness and the efficiency of our method.  ...  ACKNOWLEDGMENTS The authors appreciate the anonymous reviewers for their extensive and informative comments for the improvement of this paper.  ... 
doi:10.1145/1458082.1458177 dblp:conf/cikm/MaYKL08 fatcat:zyxafooy4zgtdbzhwdvm5uugam


Jian-Tao Sun, Hua-Jun Zeng, Huan Liu, Yuchang Lu, Zheng Chen
2005 Proceedings of the 14th international conference on World Wide Web - WWW '05  
As the competition of Web search market increases, there is a high demand for personalized Web search to conduct retrieval incorporating Web users' information needs.  ...  Therefore, Web search activities can be carried out based on CubeSVD analysis.  ...  However, it was not used for Web search application. The technique introduced in [14] uses clickthrough data in order to improve the quality of Web search.  ... 
doi:10.1145/1060745.1060803 dblp:conf/www/SunZLLC05 fatcat:wkfoq6bvfnhq5jrrcq7jek5wrm

Mining Web Graphs for Recommendations

Hao Ma, Irwin King, Michael R. Lyu
2012 IEEE Transactions on Knowledge and Data Engineering  
No matter what types of data sources are used for the recommendations, essentially these data sources can be modeled in the form of various types of graphs.  ...  In this paper, aiming at providing a general framework on mining Web graphs for recommendations, (1) we first propose a novel diffusion method which propagates similarities between different nodes and  ...  Clickthrough data record the activities of Web users, which reflect their interests and the latent semantic relationships between users and queries, as well as queries and clicked Web documents.  ... 
doi:10.1109/tkde.2011.18 fatcat:wv56jllhzbhrtb3gxkbnxdt4ze

Exploring Session Context using Distributed Representations of Queries and Reformulations

Bhaskar Mitra
2015 Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '15  
In this paper, we study the distributed representation of queries learnt by deep neural network models, such as the Convolutional Latent Semantic Model, and show that they can be used to represent query  ...  Furthermore, we show that the distributed representations of queries and reformulations are both useful for modelling session context for query prediction tasks, such as for query auto-completion (QAC)  ...  RELATED WORK Latent semantic models for Web search. Latent semantic models have received significant attention in IR.  ... 
doi:10.1145/2766462.2767702 dblp:conf/sigir/Mitra15 fatcat:y2uk4posqfbybilea5u7qw7a4q

Clickthrough-based translation models for web search

Jianfeng Gao, Xiaodong He, Jian-Yun Nie
2010 Proceedings of the 19th ACM international conference on Information and knowledge management - CIKM '10  
Web search is challenging partly due to the fact that search queries and Web documents use different language styles and vocabularies.  ...  Two translation models are trained and integrated into retrieval models: A word-based translation model that learns the translation probability between single words, and a phrase-based translation model  ...  ACKNOWLEDGMENTS The authors would like to thank Chris Quirk, Xiaolong Li, Kuansan Wang and Guihong Cao for the very helpful discussions and collaboration.  ... 
doi:10.1145/1871437.1871582 dblp:conf/cikm/GaoHN10 fatcat:orrfszivqnavfbjpxhpgswwyxe


Bin Cao, Jian-Tao Sun, Evan Wei Xiang, Derek Hao Hu, Qiang Yang, Zheng Chen
2009 Proceeding of the 18th ACM conference on Information and knowledge management - CIKM '09  
Users' preferences that are hidden in clickthrough logs are quite helpful for search engines to improve their understandings of users' queries.  ...  To tackle the sparseness problem in clickthrough logs, we propose a collaborative ranking model to leverage similar users' information.  ...  For example, PLSA [10] models how documents are generated from latent semantic topics.  ... 
doi:10.1145/1645953.1646108 dblp:conf/cikm/CaoSXHYC09 fatcat:2d4jgxxphfbb3e4p6hbpthw2wu

Beyond Click Graph: Topic Modeling for Search Engine Query Log Analysis [chapter]

Di Jiang, Kenneth Wai-Ting Leung, Wilfred Ng, Hao Li
2013 Lecture Notes in Computer Science  
The third model, the Clickthrough Model (CTM), captures the clicking behavior explicitly and models the ternary relation between search queries, query terms and URLs.  ...  However, click graph is usually plagued by low information coverage, failure of capturing the diverse types of co-occurrence and the incapability of discovering the latent semantics in data.  ...  We also wish to thank the anonymous reviewers for their comments.  ... 
doi:10.1007/978-3-642-37487-6_18 fatcat:43alhnx4azf45fa4daw27m6ubu

Learning Concept Embeddings for Query Expansion by Quantum Entropy Minimization

Alessandro Sordoni, Yoshua Bengio, Jian-Yun Nie
In this paper, we propose a novel method for learning, in a supervised way, semantic representations for words and phrases.  ...  In web search, users queries are formulated using only few terms and term-matching retrieval functions could fail at retrieving relevant documents.  ...  Acknowledgments We would like to thank NSERC, Compute Canada, and Calcul Québec for providing computational resources.  ... 
doi:10.1609/aaai.v28i1.8933 fatcat:pgrgixh6p5fl3h2n5ablqvlha4

Application of Convolution Neural Networks in Web Search Log Mining for Effective Web Document Clustering

Suruchi Chawla
2022 International Journal of Information Retrieval Research  
Experiment was done on the data set of web search query and associated clicked URLs to measure the quality of clusters based on document semantic representation using Deep learning model CNN.  ...  In this paper Deep Learning Model Convolution Neural Network(CNN) is used in big web search log data mining to learn the semantic representation of a document.  ...  Training of CNN Based on Clickthrough Web Query Session Data For The Generation of Semantic Document Concept Vector The data set of clickthrough data is partitioned to validation and training set.  ... 
doi:10.4018/ijirr.300367 fatcat:p37htwoyovcmvnsjb4bhnuhsge

Annotation for free

Ting Yao, Tao Mei, Chong-Wah Ngo, Shipeng Li
2013 Proceedings of the 21st ACM international conference on Multimedia - MM '13  
Furthermore, considering the long tail effect that few videos dominate most clicks, a new method based on polynomial semantic indexing is proposed to learn a latent space for alleviating the sparsity problem  ...  This paper studies the exploration of user searching behavior through click-through data, which is largely available and freely accessible by search engines, for learning video relationship and applying  ...  Different from model-based methods, data driven approaches construct video similarity for annotation.  ... 
doi:10.1145/2502081.2502085 dblp:conf/mm/YaoMNL13 fatcat:hh72fhpsjfalla7fywzfkdeqla
« Previous Showing results 1 — 15 out of 292 results