Filters








52 Hits in 5.2 sec

Joint relevance and freshness learning from clickthroughs for news search

Hongning Wang, Anlei Dong, Lihong Li, Yi Chang, Evgeniy Gabrilovich
2012 Proceedings of the 21st international conference on World Wide Web - WWW '12  
In contrast to traditional Web search, where topical relevance is often the main selection criterion, news search is characterized by the increased importance of freshness.  ...  We use click statistics and content analysis techniques to define a set of temporal features, which predict the right mix of freshness and relevance for a given query.  ...  these two aspects based on the clickthroughs for the news search task.  ... 
doi:10.1145/2187836.2187915 dblp:conf/www/WangDLCG12 fatcat:cv2zdvwycfd7xc3ylihrfcefxe

User modeling in search logs via a nonparametric bayesian approach

Hongning Wang, ChengXiang Zhai, Feng Liang, Anlei Dong, Yi Chang
2014 Proceedings of the 7th ACM international conference on Web search and data mining - WSDM '14  
Searchers' information needs are diverse and cover a broad range of topics; hence, it is important for search engines to accurately understand each individual user's search intents in order to provide  ...  By postulating generative assumptions about a user's search behaviors, dpRank identifies each individual user's latent search interests and his/her distinct result preferences in a joint manner.  ...  Probabilistic click models [5, 7, 28] have been proposed for modeling user click behaviors and extracting intrinsic relevance information from the clickthroughs.  ... 
doi:10.1145/2556195.2556262 dblp:conf/wsdm/WangZLDC14 fatcat:xd2smlycrnf3tj5zpi6b2vnfsq

Web dynamics and their ramifications for the development of Web search engines

Yiping Ke, Lin Deng, Wilfred Ng, Dik-Lun Lee
2006 Computer Networks  
As the most popular and important tools for finding information on the Web, Web search engines have to face many challenges arising from the Web dynamics.  ...  ., the growing number of Web sites and pages), Web pages (page content and page existence), hyperlink structures and users' searching needs.  ...  We would like to express our sincere thanks to the editors and the reviewers, who gave very insightful and encouraging comments.  ... 
doi:10.1016/j.comnet.2005.10.012 fatcat:4e3ibhyycnhwbpnx2bq32pw4ua

Click-boosting multi-modality graph-based reranking for image search

Xiaopeng Yang, Yongdong Zhang, Ting Yao, Chong-Wah Ngo, Tao Mei
2014 Multimedia Systems  
Encouraging results are reported for image reranking on a real-world image dataset collected from a commercial search engine with click-through data.  ...  The algorithm leverages clicked images to locate similar images that are not clicked, and reranks them in a multi-modality graph-based learning scheme.  ...  They further use the document relevance as a feature for a ''learning to rank'' machine learning algorithm [4] . Chapelle et al.  ... 
doi:10.1007/s00530-014-0379-8 fatcat:thyd5lxa5zbl7jygne26ke3wam

Machine learning for query-document matching in search

Hang Li, Jun Xu
2012 Proceedings of the fifth ACM international conference on Web search and data mining - WSDM '12  
A Good Web Search Engine • Must be good at -Relevance -Freshness -Comprehensiveness -User interface • Relevance is particularly important 6 Query Document Mismatch is Biggest Challenge  ...  document transformation No transformation Machine Learning for Query Document Matching in Web Search 17 Learning for Matching between Query and Document • Learning matching function • Using  ...  ., 2003) • Generation process -Word distribution given topic ~Dir -For each document:  ... 
doi:10.1145/2124295.2124393 dblp:conf/wsdm/LiX12 fatcat:ie2hyzulwvd6tayifniys5ih4y

Neural Networks in Big Data and Web Search

Will Serrano
2018 Data  
On the other hand, web search engine and recommender system revenue is obtained from advertisements and pay-per-click.  ...  The use of artificial intelligence (AI) based on neural networks and deep learning in learning relevance and ranking is also analyzed, including its utilization in Big Data analysis and semantic applications  ...  The RankSVM learning to rank algorithm learns retrieval functions using clickthrough data for training based on a support vector machine (SVM) approach [99] .  ... 
doi:10.3390/data4010007 fatcat:2irxpdvtfrclrbndkrubl5jvqq

A Survey of Query Auto Completion in Information Retrieval

Fei Cai, Maarten de Rijke
2016 Foundations and Trends in Information Retrieval  
We describe the datasets and metrics that are used to evaluate algorithms for query auto completion.  ...  search intents.  ...  We are also grateful to the editors of the journal, Doug Oard and Mark Sanderson, for their advice and support throughout the writing process.  ... 
doi:10.1561/1500000055 fatcat:cwnopwelhnbdbn4s3joiarmymq

Related Pins at Pinterest: The Evolution of a Real-World Recommender System [article]

David C. Liu, Stephanie Rogers, Raymond Shiau, Dmitry Kislyuk, Kevin C. Ma, Zhigang Zhong, Jenny Liu, Yushi Jing
2017 arXiv   pre-print
This paper is a longitudinal study of three years of its development, exploring the evolution of the system and its components from prototypes to present state.  ...  Finally, we offer suggestions for tackling these challenges when engineering Web-scale recommender systems.  ...  ; Vanja Josifovski, Xin Liu, and Mukund Narasimhan for sharing machine learning insight and expertise; Jure Leskovec, Pong Eksombatchai, and Mark Ulrich for the Pixie service; Sarah Tavel, Maura Lynch,  ... 
arXiv:1702.07969v1 fatcat:i6a7dszhtjdjrik3ifztithkqu

Behavioral dynamics on the web

Kira Radinsky, Krysta M. Svore, Susan T. Dumais, Milad Shokouhi, Jaime Teevan, Alex Bocharov, Eric Horvitz
2013 ACM Transactions on Information Systems  
We also develop a novel methodology that learns to select the best prediction model from a family of predictive models for a given query or a class of queries.  ...  We develop a temporal modeling framework adapted from physics and signal processing and harness it to predict temporal patterns in search behavior using smoothing, trends, periodicities and surprises.  ...  Diaz [2009] and Dong et al. [2010b] developed algorithms for identifying queries that are related to breaking news and for blending relevant news results into core search results.  ... 
doi:10.1145/2493175.2493181 fatcat:uuchmtxa5zcd5aw2tyrihrq2li

User Response Prediction in Online Advertising [article]

Zhabiz Gharibshah, Xingquan Zhu
2021 arXiv   pre-print
Online advertising, as the vast market, has gained significant attention in various platforms ranging from search engines, third-party websites, social media, and mobile apps.  ...  Recent years have witnessed a significant increase in the number of studies using computational approaches, including machine learning methods, for user response prediction.  ...  large number of features, and learn to create new features, for accurate user response prediction.  ... 
arXiv:2101.02342v2 fatcat:clgefamcd5fmbeg5ephizy3zqu

Semantic Matching in Search

Hang Li, Jun Xu
2014 Foundations and Trends in Information Retrieval  
Relevance is the most important factor to assure users' satisfaction in search and the success of a search engine heavily depends on its performance on relevance.  ...  "New York Times"), because term matching, i.e., the bag-of-words approach, still functions as the main mechanism of modern search engines.  ...  of semantic matching in search and in general learning to match.  ... 
doi:10.1561/1500000035 fatcat:ici6lm2fgjfwznnydro5u2s3va

Learning to Match Using Local and Distributed Representations of Text for Web Search [article]

Bhaskar Mitra, Fernando Diaz, Nick Craswell
2016 arXiv   pre-print
Models such as latent semantic analysis and those based on neural embeddings learn distributed representations of text, and match the query against the document in the latent semantic space.  ...  the document using learned distributed representations.  ...  of this work, and to Frank Seide and Dong Yu for their incredible support with CNTK.  ... 
arXiv:1610.08136v1 fatcat:pynz4kpa7jddzgrukeo24zwh4y

Personalized recommendation on dynamic content using predictive bilinear models

Wei Chu, Seung-Taek Park
2009 Proceedings of the 18th international conference on World wide web - WWW '09  
In Web-based services of dynamic content (such as news articles), recommender systems face the difficulty of timely identifying new items of high-quality and providing recommendations for new users.  ...  Based on all features in user and content profiles, we develop predictive bilinear regression models to provide accurate personalized recommendations of new items for both existing and new users.  ...  ACKNOWLEDGMENTS We thank Raghu Ramakrishnan, Scott Roy, Deepak Agarwal, Bee-Chung Chen, Pradheep Elango, and Ajoy Sojan for many discussions and helps on data collection.  ... 
doi:10.1145/1526709.1526802 dblp:conf/www/ChuP09 fatcat:jf3lp5e46zhynpzgppvng3gfam

Leveraging context in user-centric entity detection systems

Vadim von Brzeski, Utku Irmak, Reiner Kraft
2007 Proceedings of the sixteenth ACM conference on Conference on information and knowledge management - CIKM '07  
We show that leveraging surrounding context can greatly improve the performance of such systems in all three dimensions by employing novel algorithms for generating a concept vector and for finding concept  ...  Therefore, we propose to measure the quality and utility of user-centric entity detection systems in three core dimensions: the accuracy, the interestingness, and the relevance of the entities it presents  ...  ACKNOWLEDGMENTS We are grateful to Farzin Maghoul for his helpful comments and suggestions.  ... 
doi:10.1145/1321440.1321537 dblp:conf/cikm/BrzeskiIK07 fatcat:rzc34jvau5e4tdowwgmgmyhd4y

Finding trending local topics in search queries for personalization of a recommendation system

Ziad Al Bawab, George H. Mills, Jean-Francois Crespo
2012 Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '12  
For a set of queries we compute their counts and what we call buzz scores, which is a metric for detecting trending behavior.  ...  We do this by mining the search query logs to detect trending local topics.  ...  The language models are trained from search queries, queries triggering news displays, and from news feeds.  ... 
doi:10.1145/2339530.2339594 dblp:conf/kdd/BawabMC12 fatcat:viwmkxqxvbbmdarrr66jntmnx4
« Previous Showing results 1 — 15 out of 52 results