Filters








7,240 Hits in 6.1 sec

Win-win search

Jiyun Luo, Sicong Zhang, Hui Yang
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
The framework, which we term "win-win search", is based on Partially Observable Markov Decision Process.  ...  We observe a Markov chain in session search: user's judgment of retrieved documents in the previous search iteration affects user's actions in the next iteration.  ...  We therefore model session search as a Partially Observable Markov Decision Process (POMDP) [18] . Session 2: Information Need Session 2: Queries You want to buy a scooter.  ... 
doi:10.1145/2600428.2609629 dblp:conf/sigir/LuoZY14 fatcat:7glme7mbubgkrj7pmf4moukqli

Reinforcement Learning for Online Information Seeking [article]

Xiangyu Zhao and Long Xia and Jiliang Tang and Dawei Yin
2019 arXiv   pre-print
Search, recommendation, and online advertising are the three most important information-providing mechanisms on the web.  ...  These information seeking techniques, satisfying users' information needs by suggesting users personalized objects (information or services) at the appropriate time and place, play a crucial role in mitigating  ...  Session search is modeled as a dual-agent stochastic game based on Partially Observable Markov Decision Process (POMDP) in .  ... 
arXiv:1812.07127v4 fatcat:pyc75g5hufcs5b3f75gonbkp24

Modeling User Feedback in Dynamic Search and Browsing

Jiyun Luo
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
In our previous work [3] , we argue that it is suitable to model session searches as a Dual-Agent Stochastic Game, which essentially is a Partially Observable Markov Decision Process (POMDP) [2] with  ...  Our model treats session search as a "trial-and-error" process and uses user feedback as learning signals to adjust its search strategies, such as exploration and exploitation.  ... 
doi:10.1145/2911451.2911483 dblp:conf/sigir/Luo16 fatcat:jxey3bx4frbsxkcewbpaaydk5m

Enhanced Model of Web Page Prediction using Page Rank and Markov Model

Soumen Swarnakar, A. Thakur, D. Misra, D. Paul, M. Pakira, S. Roy
2016 International Journal of Computer Applications  
There are four common Markov models such as Markov Chain, Hidden Markov Model, Markov Decision Process, and Partially Observable Markov Decision Process.  ...  is performed by using 2nd order of markov model taking two pages.  ... 
doi:10.5120/ijca2016909410 fatcat:tl6ex6jjbfdpxivj224dgomqty

Artificial intelligence framework for simulating clinical decision-making: A Markov decision process approach

Casey C. Bennett, Kris Hauser
2013 Artificial Intelligence in Medicine  
It can operate in partially observable environments (in the case of missing observations or data) by maintaining belief states about patient health status and functions as an online agent that plans and  ...  This approach combines Markov decision processes and dynamic decision networks to learn from clinical data and develop complex plans via simulation of alternative sequential decision paths while capturing  ...  Partially observable Markov decision processes (POMDPs) extend MDPs by maintaining internal belief states about patient status, treatment effect, etc., similar to the cognitive planning aspects in a human  ... 
doi:10.1016/j.artmed.2012.12.003 pmid:23287490 fatcat:knrpod5hi5gobgntem62ogkwmu

Personalised Search Time Prediction using Markov Chains

Vu Tran, David Maxwell, Norbert Fuhr, Leif Azzopardi
2017 Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval - ICTIR '17  
In this paper, we show how Markov models derived from search logs can be used for predicting search times, and describe a method for evaluating these predictions.  ...  Our experimental results show that by observing users for only 100 seconds, the personalised predictions are already signicantly better than global predictions.  ...  Acknowledgements This work was supported by ESF ELIAS grant nos. 7109 (Tran) and 7271 (Maxwell), GSF grant no. FU 205/26-1 (Tran), and EPSRC grant no. 1367507 (Maxwell).  ... 
doi:10.1145/3121050.3121085 dblp:conf/ictir/TranMFA17 fatcat:ciwstegqwfgynke3lfpded4o54

User Activity Patterns During Information Search

Michael J. Cole, Chathra Hendahewa, Nicholas J. Belkin, Chirag Shah
2015 ACM Transactions on Information Systems  
User activity patterns can be at least partially observed in server-side search logs.  ...  To investigate these questions we model sequences of user behaviors in two independent user studies of information search sessions (N=32 users, 128 sessions, and N=40 users, 160 sessions).  ...  ACKNOWLEDGMENTS This research was supported by a Google Faculty Research Award to N.J. Belkin and C. Shah and by IMLS grants LM-06-07-0105-07and RE-04-12-0105-12.  ... 
doi:10.1145/2699656 fatcat:ckwkijq35fhufdlf5exp4pvnvy

Dynamic information retrieval modeling

Hui Yang, Marc Sloan, Jun Wang
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
It will cover techniques ranging from classic relevance feedback to the latest applications of partially observable Markov decision processes (POMDPs) and a handful of useful algorithms and tools for solving  ...  The objective of this tutorial is to provide a comprehensive and up-to-date introduction to Dynamic Information Retrieval Modeling, the statistical modeling of IR systems that can adapt to change.  ...  , such as in the areas of session search [4] and online advertising [6] .  ... 
doi:10.1145/2600428.2602297 dblp:conf/sigir/YangS014 fatcat:nunvudsogrgl7m7zj4kaqu3t6a

Learning to Reinforce Search Effectiveness

Jiyun Luo, Xuchu Dong, Hui Yang
2015 Proceedings of the 2015 International Conference on Theory of Information Retrieval - ICTIR '15  
The algorithm infers user feedback models by an EM algorithm from the query logs.  ...  Session search is an Information Retrieval (IR) task which handles a series of queries issued for a search task.  ...  The research is supported by DARPA FA8750-14-2-0226, NSF IIS-1453721, and NSF CNS-1223825.  ... 
doi:10.1145/2808194.2809468 dblp:conf/ictir/LuoDY15a fatcat:7ui67ulsojhmpo6v4ipfotunwq

Discovering temporal hidden contexts in web sessions for user trail prediction

Julia Kiseleva, Hoang Thanh Lam, Mykola Pechenizkiy, Toon Calders
2013 Proceedings of the 22nd International Conference on World Wide Web - WWW '13 Companion  
A web session can be represented as a sequence of user's actions where actions are ordered by time. The generation of a web session might be influenced by several hidden temporal contexts.  ...  We define the problem of discovering temporal hidden contexts in such way that we optimize directly the accuracy of predictive models (e.g. users' trails prediction) during the process of context acquisition  ...  Acknowledgements This research has been partly supported by STW and it is a part of CAPA project.  ... 
doi:10.1145/2487788.2488120 dblp:conf/www/KiselevaLPC13 fatcat:nkp5wgykoffifkbgfv4gbq4clq

Toward the attribution of Web behavior

Myriam Abramson
2012 2012 IEEE Symposium on Computational Intelligence for Security and Defence Applications  
Unlike discrete Markov processes, the page type observation O t is decoupled from the state S t in an HMM.  ...  Structured prediction methods, like maximum entropy Markov models, turn HMMs on their head by conditioning the probability of Y on the observations X making it possible to leverage from modern discriminative  ... 
doi:10.1109/cisda.2012.6291524 dblp:conf/cisda/Abramson12 fatcat:7zxkjpblnnaspivwpxqcqhogtu

Using Markov Models to Define Proactive Action Plans for Users at Multi-viewpoint Websites [chapter]

Ernestina Menasalvas, Socorro Millán, P. Gonzalez
2004 Lecture Notes in Computer Science  
The key idea to do this is based on detecting users behaviour changes by means of Behaviour Evolution Models (a combination of Discrete Markov Models).  ...  Research is partially supported by Universidad Politécnica de Madrid (project Web-RT) and MCYT under project DAWIS  ...  Acknowledgments The research has been partially supported by Universidad Politécnica de Madrid under Project WEB-RT Doctorado con Cali.  ... 
doi:10.1007/978-3-540-25929-9_95 fatcat:wwroeywsbnggdcmc6fkzykpsde

Designing States, Actions, and Rewards for Using POMDP in Session Search [chapter]

Jiyun Luo, Sicong Zhang, Xuchu Dong, Hui Yang
2015 Lecture Notes in Computer Science  
Recent efforts have been made in modeling session search using the Partially Observable Markov Decision Process (POMDP).  ...  Session search is an information retrieval task that involves a sequence of queries for a complex information need.  ...  Among various models in the RL family, Partially Observable Markov Decision Processes (POMDP) [19] has been applied recently on IR problems including session search [14] , document reranking [8, 22  ... 
doi:10.1007/978-3-319-16354-3_58 fatcat:lnzkykgq4re3rndgaoka36ggn4

Session Search by Direct Policy Learning

Jiyun Luo, Xuchu Dong, Hui Yang
2015 Proceedings of the 2015 International Conference on Theory of Information Retrieval - ICTIR '15  
This paper proposes a novel retrieval model for session search.  ...  Through gradient descent, the model finds optimal policies for the best search engine actions from what is observed in the user and search engine interactions.  ...  The research is supported by DARPA FA8750-14-2-0226, NSF IIS-1453721, and NSF CNS-1223825.  ... 
doi:10.1145/2808194.2809461 dblp:conf/ictir/LuoDY15 fatcat:3hl2u7lfbnd57lh62bn5vda24y

A POMDP model for content-free document re-ranking

Sicong Zhang, Jiyun Luo, Hui Yang
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
In this paper, we propose to model log-based document re-ranking as a Partially Observable Markov Decision Process (POMDP).  ...  Log-based document re-ranking is a special form of session search.  ...  In this paper we propose to model document re-ranking in sessions as a Partially Observable Markov Decision Process (POMDP) [12] .  ... 
doi:10.1145/2600428.2609529 dblp:conf/sigir/ZhangLY14 fatcat:25aup3jshfgjnnfpa66azybfhi
« Previous Showing results 1 — 15 out of 7,240 results