8,775 Hits in 3.9 sec

Learning to shorten query sessions

Cristina Ioana Muntean, Franco Maria Nardini, Fabrizio Silvestri, Marcin Sydow
2013 Proceedings of the 22nd International Conference on World Wide Web - WWW '13 Companion  
We propose the use of learning to rank techniques to shorten query sessions by maximizing the probability that the query we predict is the "final" query of the current search session.  ...  Such a tool becomes advantageous when the number of queries in session is rather small. In conclusion, we used learning to rank for shortening query sessions.  ...  In this paper, we go a step beyond query recommendations, by proposing a way to shorten query sessions.  ... 
doi:10.1145/2487788.2487851 dblp:conf/www/MunteanNSS13 fatcat:byt5ptmfkreaffkwymutt3m5te

MUSETS: Diversity-Aware Web Query Suggestions for Shortening User Sessions [chapter]

Marcin Sydow, Cristina Ioana Muntean, Franco Maria Nardini, Stan Matwin, Fabrizio Silvestri
2015 Lecture Notes in Computer Science  
extracted from Wikipedia. • We apply a machine learning approach to learn the model on a set of user sessions to be subsequently used for queries that are under-represented in historical query logs Example  ...  interpretations of q0; • shortens maximally the subsequent possible sessions to lead the user faster to the satisfactory level of refinement of the query.  ... 
doi:10.1007/978-3-319-25252-0_26 fatcat:ucomo5pxfzexven42vjzhleb7y

University of Essex at LogCLEF 2011: Studying Query Refinement

M-Dyaa Albakour, Udo Kruschwitz
2011 Conference and Labs of the Evaluation Forum  
We first processed the logs to extract the actually submitted search queries together with user session information and the browsing information following the submission of a query.  ...  The focus of our work is to demonstrate that the given log files can be used to acquire structured knowledge that can assist users in searching the collections (and thus shortening the number of steps  ...  ACO is applied to query logs as an adaptive learning process.  ... 
dblp:conf/clef/AlbakourK11 fatcat:24dprwybcbac7dpxnfmjmtnkju

Task-Based User Profiling for Personalized Query Refinement

Chao Xu
2013 Bulletin of IEEE Technical Committee on Digital Libraries  
However, few studies examined the effect of utilizing search tasks to assist users to design effective queries through query refinement.  ...  search sessions.  ...  (c) Does the task-based user profiling method improve the performance of query refinement by shortening user search sessions?  ... 
dblp:journals/tcdl/000413 fatcat:sziflg2rgngeppo7y6riqgegbu

A reinforcement learning based distributed search algorithm for hierarchical peer-to-peer information retrieval systems

Haizheng Zhang, Victor Lesser
2007 Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems - AAMAS '07  
In these approaches, agents depend on the content similarity between incoming queries and their direct neighboring agents to direct the distributed search sessions.  ...  In this paper, an online reinforcement-learning based approach is developed to take advantage of the dynamic run-time characteristics of P2P IR systems as represented by information about past search sessions  ...  The goal of the learning algorithm, even though it consumes some network bandwidth, is to shorten the routing time so that more queries are processed per time unit while at the same time finding more relevant  ... 
doi:10.1145/1329125.1329182 dblp:conf/atal/ZhangL07a fatcat:45iltxy4rra3ffe3isrt73su3i

Applying language modeling to session identification from database trace logs

Xiangji Huang, Qingsong Yao, Aijun An
2006 Knowledge and Information Systems  
session identification result and how to learn a language model without well-labeled training data.  ...  The discovered patterns can be used to improve the performance of database systems by prefetching predicted queries, rewriting the current query or conducting effective cache replacement.  ...  We would also like to thank the anonymous reviewers for their valuable and constructive comments.  ... 
doi:10.1007/s10115-006-0015-9 fatcat:7yipi7kou5glthkgvmgjfe33ja

ICDE 2006 Ph.D. workshop report

Wai Gen Yee, Shamkant B. Navathe
2006 SIGMOD record  
Workshops may be improved by shortening each author's presentation time and having a poster session.  ...  This talk described a way of routing peer-to-peer queries in a random network by incrementally learning best paths by using a technique similar to pheromone trail blazing done by ants.  ... 
doi:10.1145/1228268.1228281 fatcat:b5zn4kfmybegrdvcwdc3mkyod4

Kernel-based distance metric learning for content-based image retrieval

Hong Chang, Dit-Yan Yeung
2007 Image and Vision Computing  
learning methods significantly due to its higher flexibility in metric learning.  ...  Unlike most existing metric learning methods which learn a Mahalanobis metric corresponding to performing linear transformation in the original image space, we define the transformation in * Corresponding  ...  Moreover, unlike most existing relevance feedback methods which only improve the retrieval results within a single query session, we propose a stepwise metric learning algorithm to boost the retrieval  ... 
doi:10.1016/j.imavis.2006.05.013 fatcat:6cd3utk6tjgqhomwh5cywvuhnq

Parameter Learning in Probabilistic Databases: A Least Squares Approach [chapter]

Bernd Gutmann, Angelika Kimmig, Kristian Kersting, Luc De Raedt
2008 Lecture Notes in Computer Science  
Probabilistic databases compute the success probabilities of queries. We introduce the problem of learning the parameters of the probabilistic database ProbLog.  ...  Given the observed success probabilities of a set of queries, we use a least squares approach to compute the probabilities attached to facts that have a low approximation error on the training data as  ...  ProbLog has been designed to support life scientists that mine a large network of biological entities in interactive querying sessions..  ... 
doi:10.1007/978-3-540-87479-9_49 fatcat:pma4lnj2r5hd3kcqyaodl4ya6y

A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion

Alessandro Sordoni, Yoshua Bengio, Hossein Vahabi, Christina Lioma, Jakob Grue Simonsen, Jian-Yun Nie
2015 Proceedings of the 24th ACM International on Conference on Information and Knowledge Management - CIKM '15  
This is in contrast to current synthetic suggestion models relying upon machine learning pipelines and hand-engineered feature sets.  ...  In addition to query suggestion, our model is general enough to be used in a variety of other applications.  ...  Acknowledgments We would like to thank Jianfeng Gao,Çaglar Gülçehre and Bhaskar Mitra for their precious advice, enlightening discussions and invaluable moral support.  ... 
doi:10.1145/2806416.2806493 dblp:conf/cikm/SordoniBVLSN15 fatcat:po3ha3heofgazgwzfeglg5z4h4

Boosting cross-media retrieval via visual-auditory feature analysis and relevance feedback

Hong Zhang, Junsong Yuan, Xingyu Gao, Zhenyu Chen
2014 Proceedings of the ACM International Conference on Multimedia - MM '14  
There are abundant correlations among heterogeneous low-level media content, which makes it challenging to query cross-media data effectively.  ...  How to learn comprehensive high-level semantics from different types of data and enable efficient crossmedia retrieval becomes an emerging hot issue.  ...  Furthermore, we propose short-term learning within a single query session and long-term learning over the course of many query sessions for performance optimization.  ... 
doi:10.1145/2647868.2654975 dblp:conf/mm/ZhangYGC14 fatcat:adpf47i5lbgdxkpespkzgbzhnq

WebFrame: In Pursuit of Computationally and Cognitively Efficient Web Mining [chapter]

Tong Zheng, Yonghe Niu, Randy Goebel
2002 Lecture Notes in Computer Science  
Not dissimilar to conventional data mining, the general idea is that good use of web data first requires the careful selection of data (both usage and content data), the deployment of appropriate learning  ...  methods, and the evaluation of the results of applying the results of learning in a web application.  ...  Apply the NCMs to the sessions in the test set, and generate a new set of shortened navigation paths.  ... 
doi:10.1007/3-540-47887-6_26 fatcat:ikpudl2tkvg2nnhoyxwixf3bci

Page 259 of Friends' Intelligencer Vol. 41, Issue 17 [page]

1884 Friends' Intelligencer  
The answers to the Fifth Query showed that proper care is taken to aid those who need assistance, and that all the children of Friends are instructed in useful learning, to fit them for the business of  ...  Then adjourned. n the Men’s Meeting, on the afternoon session, the remaining Queries were read and answered. The report of the Committee to Visit Sub- ordinate Meetings was read and approved.  ... 

Supporting children's web search in school environments

Carsten Eickhoff, Pieter Dekker, Arjen P. de Vries
2012 Proceedings of the 4th Information Interaction in Context Symposium on - IIIX '12  
Already in early grades, children are encouraged to search for information on-line.  ...  Building on the findings of this survey, we propose an automatic method of identifying struggling searchers in order to enable teaching personnel to provide appropriate and targeted guidance where needed  ...  Acknowledgements We would like to thank Allison Druin and Elizabeth Foss for their support and for sharing their original search role coding scheme. This research is part of the PuppyIR project 1 .  ... 
doi:10.1145/2362724.2362748 dblp:conf/iiix/EickhoffDV12 fatcat:omisiu3t4vck3ogqp7r3hvwoya

Simulation training program for vacuum application to improve technical skills in vacuum-assisted vaginal delivery

Paolo Mannella, Mario Giordano, Maria Magdalena Montt Guevara, Andrea Giannini, Eleonora Russo, Federica Pancetti, Marta Caretto, Tommaso Simoncini
2021 BMC Pregnancy and Childbirth  
After 8 weeks, simulation training was repeated and trainees were re-evaluated by the same tutor. after 8 weeks from the first simulation session, trainees have been shown to increase technical skills  ...  (46.27 ± 4.6 with p-value < 0.0001), the successful application rate (85.71% with p-value 0.0161).) and to reduce the time to complete the procedure (86.2 ± 29.9 s with p-value < 0.0001). simulation training  ...  The evaluation in session 2 was 8 weeks later of session 1. Graph characterize the evaluation of selfassessment (a), self-evaluation queries (b), and self-management queries (C).  ... 
doi:10.1186/s12884-021-03829-y pmid:33910520 fatcat:o54um3qxpvbmjamnfyosvjadm4
« Previous Showing results 1 — 15 out of 8,775 results