Publications

You can find publications sorted by research area in the research pages

Table of Content

Conferences

2011

  • [PDF] A. Caputo, B. Piwowarski, and M. Lalmas, “A query algebra for quantum information retrieval,” in Proceedings of the 2nd italian information retrieval workshop, 2011.
    [Bibtex] 
     @inproceedings{Caputo2011QueryAlgebra, Author = {Annalina Caputo and Benjamin Piwowarski and Mounia Lalmas}, Booktitle = {Proceedings of the 2nd Italian Information Retrieval Workshop}, Date-Added = {2011-01-03 16:59:26 +0000}, Date-Modified = {2011-04-11 13:31:25 +0100}, Month = {January}, Title = {A Query Algebra for Quantum Information Retrieval}, Year = {2011}}
  • I. Frommholz, B. Piwowarski, M. Lalmas, and K. van Rijsbergen, “Processing queries in session in a quantum-inspired ir framework,” in Proceedings of ECIR 2011, 2011.
    [Bibtex] 
     @inproceedings{Frommholz2011Processing, Author = {Ingo Frommholz and Benjamin Piwowarski and Mounia Lalmas and Keith van Rijsbergen}, Booktitle = {Proceedings of {ECIR} 2011}, Date-Added = {2011-01-03 16:56:38 +0000}, Date-Modified = {2011-04-11 13:31:23 +0100}, Month = {March}, Note = {Poster}, Title = {Processing Queries in Session in a Quantum-inspired IR Framework}, Year = {2011}}
  • S. Attfield, G. Kazai, M. Lalmas, and B. Piwowarski, “Towards a science of user engagement (position paper),” in Wsdm workshop on user modelling for web applications, 2011.
    [Bibtex] 
     @inproceedings{Attfield2011Towards, Author = {S. Attfield and G. Kazai and M. Lalmas and B. Piwowarski}, Booktitle = {WSDM Workshop on User Modelling for Web Applications}, Date-Added = {2011-01-12 11:19:04 +0000}, Date-Modified = {2011-04-11 13:31:21 +0100}, Location = {Hong Kong, China}, Month = {February}, Title = {Towards a science of user engagement (Position Paper)}, Year = {2011}}

2010

  • S. Sushmita, B. Piwowarski, and M. Lalmas, “Dynamics of genre and domain intents,” in Proceedings of the sixth asia information retrieval society conference, 2010.
    [Bibtex] 
     @inproceedings{Sushmita2010Dynamics-of-Genre, Author = {Shanu Sushmita and Benjamin Piwowarski and Mounia Lalmas}, Booktitle = {Proceedings of The Sixth Asia Information Retrieval Society Conference}, Crossref = {AIRS2010}, Date-Added = {2010-08-12 17:33:48 +0100}, Date-Modified = {2011-04-11 13:31:24 +0100}, Title = {Dynamics of Genre and Domain Intents}, Type = {International Conference}, Year = {2010}}
  • I. Frommholz, B. Larsen, B. Piwowarski, M. Lalmas, P. Ingwersen, and K. van Rijsbergen, “Supporting polyrepresentation in a quantum-inspired geometrical retrieval framework,” in Proceedings of the 3rd iiiX symposium, 2010.
    [Bibtex] 
     @inproceedings{Frommholz2010Supporting-Polyrepresentation, Author = {Ingo Frommholz and Birger Larsen and Benjamin Piwowarski and Mounia Lalmas and Peter Ingwersen and Keith van Rijsbergen}, Booktitle = {Proceedings of the 3rd {iiiX} symposium}, Date-Added = {2010-05-30 10:46:21 +0100}, Date-Modified = {2011-04-11 13:31:24 +0100}, Month = {aug}, Title = {Supporting Polyrepresentation in a Quantum-inspired Geometrical Retrieval Framework}, Type = {International Conference}, Year = {2010}}
  • B. Piwowarski, I. Frommholz, M. Lalmas, and K. van Rijsbergen, “Exploring a multidimensional representation of documents and queries,” in Proceedings of riao, 2010.
    [Bibtex] 
     @inproceedings{Piwowarski2010Exploring-a-Multidimensional, Author = {Benjamin Piwowarski and Ingo Frommholz and Mounia Lalmas and Keith van Rijsbergen}, Booktitle = {Proceedings of RIAO}, Date-Added = {2010-01-12 12:39:52 +0000}, Date-Modified = {2011-04-11 13:31:24 +0100}, Title = {Exploring a Multidimensional Representation of Documents and Queries}, Type = {International Conference}, Year = {2010}}
  • B. Piwowarski, I. Frommholz, Y. Moshfeghi, M. Lalmas, and K. van Rijsbergen, “Filtering documents with subspaces,” in Advances in Information Retrieval, 2010.
    [Bibtex] 
     @inproceedings{Piwowarski2010Filtering-documents, Author = {Benjamin Piwowarski and Ingo Frommholz and Yashar Moshfeghi and Mounia Lalmas and Keith van Rijsbergen}, Booktitle = {{Advances in Information Retrieval}}, Crossref = {ECIR2010}, Date-Added = {2009-11-24 11:41:39 +0000}, Date-Modified = {2011-04-11 13:31:24 +0100}, Editor = {Cathal Gurrin and Yulan He and Gabriella Kazai and Udo Kruschwitz and Suzanne Little and Thomas Roelleke and Stefan R{\"u}ger and Keith van Rijsbergen}, Isbn = {978-3-642-12274-3}, Location = {Heidelberg}, Publisher = {Springer}, Series = {Lecture Notes in Computer Science}, Short-Series = {LNCS}, Title = {Filtering documents with subspaces}, Type = {International Conference}, Volume = {5993}, Year = {2010}}
  • G. Dupret and B. Piwowarski, “A user behavior model for average precision and its generalization to graded judgments,” in Proceedings of the 33rd annual international acm sigir conference on research and development in information retrieval, 2010.
    [Bibtex] 
     @inproceedings{Dupret2010A-User-Behavior, Author = {Georges Dupret and Benjamin Piwowarski}, Booktitle = {Proceedings of the 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval}, Crossref = {SIGIR2010}, Date-Added = {2010-07-14 10:37:25 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Editor = {Fabio Crestania and Marchand-Maillet St{\'e}phane and Hsin-Hsi Chen and Efthimiadis, Efthimis N. and Savoy, Jacques}, Publisher = {{ACM}}, Short-Booktitle = {SIGIR}, Short-Title = {SIGIR}, Title = {A User Behavior Model for Average Precision and its Generalization to Graded Judgments}, Type = {International Conference}, Year = {2010}}
  • [PDF] [DOI] B. Piwowarski, I. Frommholz, M. Lalmas, and K. van Rijsbergen, “What can quantum theory bring to IR?,” in Cikm’10: proceedings of the nineteenth acm conference on conference on information and knowledge management, 2010.
    [Bibtex] 
     @inproceedings{Piwowarski2010What-Quantum, Author = {Benjamin Piwowarski and Ingo Frommholz and Mounia Lalmas and Keith van Rijsbergen}, Booktitle = {CIKM'10: Proceedings of the nineteenth ACM conference on Conference on information and knowledge management}, Crossref = {CIKM2010}, Date-Added = {2010-07-19 09:20:38 +0200}, Date-Modified = {2011-04-11 13:31:22 +0100}, Doi = {10.1145/1871437.1871450}, Editor = {Huang, Jimmy and Koudas, Nick and Jones, Gareth and Wu, Xindong and Collins-Thompson, Kevyn and An, Aijun}, Location = {Toronto, Canada}, Publisher = {{ACM}}, Short-Booktitle = {{CIKM}}, Short-Title = {{CIKM}}, Title = {What can Quantum Theory bring to {IR}?}, Type = {International Conference}, Year = {2010}}

2009

  • [PDF] [DOI] B. Piwowarski, G. Dupret, and R. Jones, “Mining user web search activity with layered bayesian networks or how to capture a click in its context,” in Proceedings of the second acm international conference on web search and data mining, Barcelona, Spain, 2009.
    [Bibtex] 
     @inproceedings{Piwowarski2009Mining-User, Abstract = {Mining user web search activity potentially has a broad range of applications including web result pre-fetching, automatic search query reformulation, click spam detection, estimation of document relevance and prediction of user satisfaction. This analysis is difficult because the data recorded by search engines while users interact with them, although abundant, is very noisy. In this work, we explore the utility of mining search behavior of users, represented by observed variables including the time the user spends on the page, and whether the user reformulated his or her query. As a case study, we examine the contribution this data makes to predicting the relevance of a document in the absence of document content models. To this end, we first propose a method for grouping the interactions of a particular user according to the different tasks he or she undertakes. With each task corresponding to a distinct infor- mation need, we then propose a Bayesian Network to holistically model these interactions. The aim is to identify distinct patterns of search behaviors. Finally, we join these patterns to a list of custom features and we use gradient boosted decision trees to predict the relevance of a set of query document pairs for which we have rele- vance assessments. The experimental results confirm the potential of our model, with significant improvements in precision for predicting the relevance of documents based on a model of the user's search and click behavior, over a baseline model using only click and query features, with no Bayesian Network input.}, Address = {Barcelona, Spain}, Author = {Benjamin Piwowarski and Georges Dupret and Rosie Jones}, Booktitle = {Proceedings of the Second ACM International Conference on Web Search and Data Mining}, Crossref = {WSDM2009}, Date-Added = {2008-10-23 13:06:25 +0100}, Date-Modified = {2011-04-11 13:31:25 +0100}, Doi = {10.1145/1498759.1498823}, Editor = {Ricardo A. Baeza-Yates and Paolo Boldi and Berthier A. Ribeiro-Neto and Berkant Barla Cambazoglu}, Keywords = {Web, Information Retrieval, Web Log Mining}, Month = {February}, Private = {0}, Publisher = {ACM}, Read = {Yes}, Title = {Mining User Web Search Activity with Layered Bayesian Networks or How to Capture a Click in its Context}, Type = {International Conference}, Year = {2009}}
  • [DOI] Y. Moshfeghi, D. Agarwal, B. Piwowarski, and J. M. Jose, “Movie recommender: semantically enriched unified relevance model for rating prediction in collaborative filtering,” in Ecir, Toulouse, France, 2009, pp. 54-65.
    [Bibtex] 
     @inproceedings{Moshfeghi2009Movie-Recommender:, Abstract = { Collaborative recommendation aims at suggesting new items based on past user interactions. In this paper, we investigate the role of semantic and emotion features in improving the performance of a model-based collaborative recommendation algorithm. In our approach, an item is represented as sets of features in different emotion and semantic spaces. In each space, we cluster features using the LDA algorithm in a novel way. When recommending an item, we use a two phase approach, where we first predict the probability that the item is liked in a given space, and then combine these probabilities using boosted trees into a single item rating. We apply our model to movie recommendation, in which semantic features are the movie actors, directors, and genre and emotion features are extracted from the movie plot summary and reviews. Experiments with the 100K and 1M MovieLens data sets show that including semantic and emotion information significantly improves the accuracy of prediction.}, Address = {Toulouse, France}, Author = {Yashar Moshfeghi and Deepak Agarwal and Benjamin Piwowarski and Joemon M. Jose}, Booktitle = {ECIR}, Crossref = {ECIR2009}, Date-Added = {2009-09-07 15:16:37 +0100}, Date-Modified = {2011-04-11 13:31:25 +0100}, Doi = {10.1007/978-3-642-00958-7_8}, Editor = {Mohand Boughanem and Catherine Berrut and Josiane Mothe and Chantal Soul{\'e}-Dupuy}, Isbn = {978-3-642-00957-0}, Month = {mar}, Pages = {54-65}, Private = {Yes}, Publisher = {Springer}, Series = {Lecture Notes in Computer Science}, Short-Title = {Proceedings of the 31th ECIR Conference}, Title = {Movie Recommender: Semantically Enriched Unified Relevance Model for Rating Prediction in Collaborative Filtering}, Type = {International Conference}, Volume = {5478}, Year = {2009}}
  • [PDF] B. Piwowarski and M. Lalmas, “Structured information retrieval and quantum theory,” in Proceedings of the third quantum interaction symposium, 2009.
    [Bibtex] 
     @inproceedings{Piwowarski2009Structured-Information, Abstract = {Information Retrieval (IR) systems try to identify documents relevant to user queries, which are representations of user information needs. Interaction, context, and document structure are three important and active themes in IR research. We present how we propose to model the task of Structured IR (SIR) based on a QT inspired framework, with a focus on how to exploit user contextual information and user interaction in the search process.}, Author = {Benjamin Piwowarski and Mounia Lalmas}, Booktitle = {Proceedings of the Third Quantum Interaction Symposium}, Crossref = {QI2009}, Date-Added = {2009-01-12 12:30:26 +0000}, Date-Modified = {2011-04-11 13:31:22 +0100}, Editor = {Bruza, Peter and Sofge, D. and Lawless, W. and van Rijsbergen, Cornelis J. and Klusch, M.}, Group = {Quantum Information}, Keywords = {quantum}, Location = {Saarbrucken, Germany}, Month = {March}, Publisher = {Springer}, Read = {Yes}, Series = {Lecture Notes in Artificial Intelligence}, Short-Series = {LNCS}, Short-Title = {Proceedings of the 3rd QI Symposium}, Title = {Structured Information Retrieval and Quantum Theory}, Type = {International Workshop}, Volume = {5494}, Year = {2009}}
  • B. Piwowarski and M. Lalmas, “A quantum-based model for interactive information retrieval,” in Proceeedings of the 2nd international conference on the theory of information retrieval, 2009.
    [Bibtex] 
     @inproceedings{Piwowarski2009B-A-Quantum-based-Model, Author = {Benjamin Piwowarski and Mounia Lalmas}, Booktitle = {Proceeedings of the 2nd International Conference on the Theory of Information Retrieval}, Crossref = {ICTIR2009}, Date-Added = {2009-06-17 12:47:18 +0100}, Date-Modified = {2011-04-11 13:31:22 +0100}, Editor = {Leif Azzopardi and Gabriella Kazai and Stephen E. Robertson and Stefan M. R{\"u}ger and Milad Shokouhi and Dawei Song and Emine Yilmaz}, Group = {Quantum Information; Information Retrieval}, Month = {Sep}, Publisher = {Springer}, Short-Title = {Proceedings of the 2nd ICTIR conference}, Title = {A Quantum-based Model for Interactive Information Retrieval}, Type = {International Conference}, Volume = {5766}, Year = {2009}}

2008

  • [PDF] G. Dupret and B. Piwowarski, “A user browsing model to predict search engine click data from past observations,” in Sigir 2008, Singapore, 2008.
    [Bibtex] 
     @inproceedings{Dupret2008A-user-browsing, Address = {Singapore}, Author = {Dupret, Georges and Benjamin Piwowarski}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {SIGIR 2008}, Crossref = {SIGIR2008}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:22 +0100}, Editor = {Sung-Hyon Myaeng and Douglas W. Oard and Fabrizio Sebastiani and Tat-Seng Chua and Mun-Kew Leong}, Isbn = {978-1-60558-164-4}, Location = {Singapore, Singapore}, Month = {July}, Publisher = {ACM}, Short-Booktitle = {Proceedings of the 31st {ACM SIGIR}}, Short-Title = {Proceedings of the 31st {ACM SIGIR}}, Title = {A user browsing model to predict search engine click data from past observations}, Type = {International Conference}, Year = {2008}}

2007

  • [PDF] O. Motelet, B. Piwowarski, G. Dupret, J. A. Pino, and N. Baloian, “Enhancing educational-material retrieval using authored-lesson metadata,” in Fourteenth string processing and information retrieval symposium (spire 2007), Santiago, Chile, 2007.
    [Bibtex] 
     @inproceedings{Motelet2007Enhancing-Educational-Material, Address = {Santiago, Chile}, Author = {Olivier Motelet and Benjamin Piwowarski and Dupret, Georges and Jose A. Pino and Nelson Baloian}, Booktitle = {Fourteenth String Processing and Information Retrieval Symposium (SPIRE 2007)}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:25 +0100}, Month = {October}, Owner = {bpiwowar}, Timestamp = {2007.07.20}, Title = {Enhancing Educational-Material Retrieval using Authored-Lesson Metadata}, Type = {International Conference}, Year = {2007}}
  • [PDF] G. Dupret, V. Murdock, and B. Piwowarski, “Web search engine evaluation using clickthrough data and a user model,” in Query log analysis: social and technological challenges, 2007.
    [Bibtex] 
     @inproceedings{Dupret2007Web-Search-Engine, Abstract = {Traditional search engine evaluation relies on a list of query document pairs along with a score reflecting the document relevance to the query. The score is generally a human assessment, but nothing is said explicitly about the actual user behavior. In this paper we illustrate with a toy model that once the user behavior is agreed upon, the human assessment can be eliminated and the engine performance can be evaluated based on the clickthrough data of past users.}, Author = {Dupret, Georges and Vanessa Murdock and Benjamin Piwowarski}, Booktitle = {Query Log Analysis: Social and Technological Challenges}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:24 +0100}, Title = {Web Search Engine Evaluation using Clickthrough Data and a User Model}, Type = {International Workshop}, Year = {2007}}
  • O. Motelet, N. Baloian, B. Piwowarski, and J. A. Pino, “Taking advantage of the semantics of a lesson graph based on learning objects,” in The 13th international conference on artificial intelligence in education (aied 2007), 2007.
    [Bibtex] 
     @inproceedings{Motelet2007Taking-advantage, Author = {Olivier Motelet and Nelson Baloian and Benjamin Piwowarski and Jose A. Pino}, Booktitle = {The 13th International Conference on Artificial Intelligence in Education (AIED 2007)}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Month = {July}, Owner = {bpiwowar}, Publisher = {IOS Press}, Timestamp = {2007.05.28}, Title = {Taking advantage of the semantics of a lesson graph based on learning objects}, Type = {International Conference}, Year = {2007}}
  • [PDF] G. Kazai, B. Piwowarski, and S. E. Robertson, “Effort precision and gain-recall based on a probabilistic navigation model,” in 1st international conference on the theory of information retrieval, 2007.
    [Bibtex] 
     @inproceedings{Kazai2007Effort-Precision, Abstract = {Traditional evaluation of retrieval systems is based on implicit assumptions about the users' interaction with the system. It is assumed that the user is presented with the ranked results and examines the documents one after the other in the order they are listed. In this paper we argue that such a model is obsolete in the case of the Web and structured document retrieval, where navigation is an integral part of the user's search strategy. We advocate that post-query navigation needs to be reflected in the evaluation framework. We substantiate our proposal with the evidence of post-query navigation from user studies and discuss examples of systems that have been developed with the consideration of the user's browsing behaviour. In order to capture retrieval effectiveness for query and navigation based search, we introduce a measure of retrieval effectiveness that comprises a probabilistic model of the users' post-query navigation.}, Author = {Gabriella Kazai and Benjamin Piwowarski and Robertson, Stephen E.}, Booktitle = {1st International Conference on the Theory of Information Retrieval}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Month = {October}, Owner = {bpiwowar}, Private = {0}, Timestamp = {2007.10.01}, Title = {Effort Precision and Gain-recall based on a probabilistic navigation model}, Type = {International Conference}, Year = {2007}}
  • [PDF] B. Piwowarski and H. Zaragoza, “Predictive user click models based on click-through history,” in Proceedings of the sixteenth conference on information and knowledge management (cikm 2007), Lisbon, Portugal, 2007, pp. 175-182.
    [Bibtex] 
     @inproceedings{Piwowarski2007Predictive-User, Abstract = {Web search engines consistently collect information about users interaction with the system: they record the query they issued, the URL of presented and selected documents along with their ranking. This information is very valuable: It is a poll over millions of users on the most various topics and it has been used in many ways to mine users interests and preferences. Query logs have the potential to partially alleviate the search engines from thousand of searches by providing a way to predict answers for a subset of queries and users without knowing the content of a document. Even if the predicted result is at rank one, this analysis might be of interest: If there is enough confidence on a user's click, we might redirect the user directly to the page whose link would be clicked. In this paper, we present three different models for predicting user clicks, ranging from most specific ones (using only past user history for the query) to very general ones (aggregating data over all users for a given query). The former model has a very high precision at low recall values, while the latter can achieve high recalls. We show that it is possible to combine the different models to predict with high accuracy (over 90%) a high subset of query sessions (24% of all the sessions).}, Address = {Lisbon, Portugal}, Author = {Benjamin Piwowarski and Hugo Zaragoza}, Booktitle = {Proceedings of the Sixteenth Conference on Information and Knowledge Management (CIKM 2007)}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:22 +0100}, Month = {November}, Owner = {bpiwowar}, Pages = {175--182}, Publisher = {ACM}, Timestamp = {2007.07.20}, Title = {Predictive User Click Models Based on Click-through History}, Type = {International Conference}, Year = {2007}}

2006

  • H. Bast, G. Dupret, D. Majumdar, and B. Piwowarski, “Discovering a term taxonomy from term similarities using principal component analysis,” in Semantics, web and mining, joint international workshops, ewmf 2005 and kdo 2005, Porto, Portugal, 2006, pp. 103-120.
    [Bibtex] 
     @inproceedings{Bast2006Discovering-a-Term, Address = {Porto, Portugal}, Author = {Holger Bast and Dupret, Georges and Debapriyo Majumdar and Benjamin Piwowarski}, Booktitle = {Semantics, Web and Mining, Joint International Workshops, EWMF 2005 and KDO 2005}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:25 +0100}, Editor = {Markus Ackermann and Bettina Berendt and Marko Grobelnik and Andreas Hotho and Dunja Mladenic and Giovanni Semeraro and Myra Spiliopoulou and Gerd Stumme and Vojtech Sv{\'a}tek and Maarten van Someren}, Pages = {103-120}, Publisher = {Springer}, Series = {Lecture Notes in Computer Science}, Title = {Discovering a Term Taxonomy from Term Similarities Using Principal Component Analysis}, Type = {International Workshop}, Volume = {4289}, Year = {2006}}
  • G. Dupret and B. Piwowarski, “Principal components for automatic term hierarchy building,” in Proceedings of the 13th international symposium on string processing and information retrieval (spire 2006), 2006, pp. 37-48.
    [Bibtex] 
     @inproceedings{Dupret2006Principal-Components, Author = {Dupret, Georges and Benjamin Piwowarski}, Booktitle = {Proceedings of the 13th International Symposium on String Processing and Information Retrieval (SPIRE 2006)}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:24 +0100}, Pages = {37--48}, Private = {Yes}, Publisher = {Springer}, Series = {LNCS 4209}, Title = {Principal Components for Automatic Term Hierarchy Building}, Type = {International Conference}, Year = {2006}}
  • [PDF] [DOI] B. Piwowarski and G. Dupret, “Evaluation in (XML) information retrieval: expected precision-recall with user modelling (EPRUM),” in Proceedings of the 29th annual international acm sigir conference on research and development in information retrieval, Seattle, Washington, USA, 2006, pp. 260-267.
    [Bibtex] 
     @inproceedings{Piwowarski2006Evaluation-in-XML-Information, Abstract = {Standard Information Retrieval (IR) metrics assume a simple model where documents are understood as independent units. Such an assumption is not adapted to new paradigms like XML or Web IR where retrievable informations are parts of documents or sets of related documents. Moreover, classical hypotheses assumes that the user ignores the structural or logical context of document elements and hence the possibility of navigation between units. EPRUM is a generalisation of Precision-Recall (PR) that aims at allowing the user to navigate or browse in the corpus structure. Like the Cumulated Gain metrics, it is able to handle continuous valued relevance. We apply and compare EPRUM in the context of XML Retrieval -- a very active field for evaluation metrics. We also explain how EPRUM can be used in other IR paradigms.}, Address = {Seattle, Washington, USA}, Author = {Benjamin Piwowarski and Dupret, Georges}, Booktitle = {Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval}, Crossref = {SIGIR2006}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Doi = {10.1145/1148170.1148218}, Editor = {Efthimis N. Efthimiadis and Susan T. Dumais and David Hawking and Kalervo J{\"a}rvelin}, Isbn = {1-59593-369-7}, Month = {aug}, Pages = {260--267}, Publisher = {ACM}, Short-Booktitle = {Proceedings of the 29th {ACM SIGIR}}, Short-Title = {Proceedings of the 29th {ACM SIGIR}}, Title = {Evaluation in ({XML}) Information Retrieval: Expected Precision-Recall with User Modelling ({EPRUM})}, Type = {International Conference}, Year = {2006}}
  • G. Dupret, B. Piwowarski, C. Hurtado, and M. Mendoza, “A statistical model of query log generation,” in Proceedings of the 13th international symposium on string processing and information retrieval (spire 2006), 2006, pp. 217-228.
    [Bibtex] 
     @inproceedings{Dupret2006A-Statistical-Model, Author = {Dupret, Georges and Benjamin Piwowarski and Hurtado, C. and Mendoza, M.}, Booktitle = {Proceedings of the 13th International Symposium on String Processing and Information Retrieval (SPIRE 2006)}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Pages = {217--228}, Publisher = {Springer}, Series = {LNCS 4209}, Title = {A Statistical Model of Query Log Generation}, Type = {International Conference}, Year = {2006}}

2004

  • H. Vu, B. Piwowarski, and P. Gallinari, “Filtering in XML retrieval: a prospective analysis,” in Xml and information retrieval workshop of sigir 2004, University of Sheffield, UK, 2004.
    [Bibtex] 
     @inproceedings{Vu2004Filtering-in-XML-Retrieval:, Abstract = {In XML retrieval paradigm, elements inside a document can be returned as answers to a user request. Since the information in an element is more specific than in a whole document, this might reduce the user effort in finding relevant information. However, as XML documents are composed of nested elements, many of which being possibly relevant to the user information need, retrieval systems must take care of the overlap issue before showing answers to the user. In this paper, we investigate how to disallow overlapping results by considering it as a filtering problem.}, Address = {University of Sheffield, UK}, Author = {Vu, Huyen-Trang and Benjamin Piwowarski and Gallinari, Patrick}, Booktitle = {XML and Information Retrieval workshop of SIGIR 2004}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:24 +0100}, Month = {July}, Title = {Filtering in {XML} Retrieval: a Prospective Analysis}, Type = {International Workshop}, Year = {2004}}
  • [PDF] B. Piwowarski and M. Lalmas, “Interface pour l’évaluation de systèmes de recherche sur des documents xml,” in Premiere conference en recherche d’information et applications (coria’04), Toulouse, France, 2004.
    [Bibtex] 
     @inproceedings{Piwowarski2004Interface-pour, Abstract = {L'{\'e}valuation des syst{\`e}mes de Recherche d'Information est depuis le d{\'e}but un des piliers de l'{\'e}volution de ce domaine. La qualit{\'e} de l'{\'e}valuation est d'une importance capitale puisqu'elle permet de discriminer les diff{\'e}rents mod{\`e}les entre eux. Il est donc primordial de pouvoir constituer des corpus o{\`u} les questions et leurs jugements de pertinence associ{\'e}s sont de qualit{\'e}. Alors qu'avec des documents plats les m{\'e}thodes sont bien {\'e}tablies, ce n'est plus le cas avec des documents structur{\'e}s de type XML. Il est donc n{\'e}cessaire de d{\'e}velopper de nouvelle fa{\c c}on d'{\'e}valuer. Nous pr{\'e}sentons dans cet article l'interface utilis{\'e}e lors de la campagne INEX 2003 qui permet d'{\'e}valuer de fa{\c c}on la plus consistante et la plus exhaustive possible les documents XML.}, Address = {Toulouse, France}, Author = {Benjamin Piwowarski and Lalmas, Mounia}, Booktitle = {Premiere COnference en Recherche d'Information et Applications (CORIA'04)}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:24 +0100}, Month = {March}, Title = {Interface pour l'{\'e}valuation de syst{\`e}mes de recherche sur des documents XML}, Type = {National conference}, Year = {2004}}
  • [PDF] B. Piwowarski and P. Gallinari, “An algebra for probabilistic XML retrieval,” in The first twente data management workshop, Enschede, The Netherlands, 2004.
    [Bibtex] 
     @inproceedings{Piwowarski2004An-algebra-for-probabilistic, Abstract = {In this paper, we describe a new algebra for XML retrieval. We first describe how to transform an XPath-like query in our algebra. The latter contains a vague predicate, about, which defines a set of document parts within an XML document that fullfill a query expressed as in ``flat'' Information Retrieval - a query that contains only constraints on content but not on structure. This predicate is evaluated in a probabilistic way: we thus need a probabilistic interpretation of our algebra. Answers to query needs expressed with vague content and vague structure constraints can then be evaluated.}, Address = {Enschede, The Netherlands}, Author = {Benjamin Piwowarski and Gallinari, Patrick}, Booktitle = {The First Twente Data Management Workshop}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:24 +0100}, Month = {June}, Organization = {SIKS}, Title = {An algebra for probabilistic {XML} Retrieval}, Type = {International Workshop}, Year = {2004}}
  • [PDF] [DOI] B. Piwowarski and M. Lalmas, “Providing consistent and exhaustive relevance assessments for XML retrieval evaluation,” in Proceedings of the thirteenth conference on information and knowledge management (cikm 2004), Washington D.C., U.S.A., 2004.
    [Bibtex] 
     @inproceedings{Piwowarski2004Providing-Consistent, Abstract = {Comparing retrieval approaches requires test collections, which consist of documents, queries and relevance assessments. Obtaining consistent and exhaustive relevance assessments is crucial for the appropriate comparison of retrieval approaches. Whereas the evaluation methodology for flat text retrieval approaches is well established, the evaluation of XML retrieval approaches is a research issue. This is because XML documents are composed of nested components, which cannot be considered as independent in terms of relevance. This paper describes the methodology adopted in INEX (the INitiative for the Evaluation of XML Retrieval) to ensure consistent and exhaustive relevance assessments.}, Address = {Washington D.C., U.S.A.}, Author = {Benjamin Piwowarski and Lalmas, Mounia}, Booktitle = {Proceedings of the Thirteenth Conference on Information and Knowledge Management (CIKM 2004)}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Doi = {10.1145/1031171.1031246}, Month = {November}, Read = {Yes}, Title = {Providing Consistent and Exhaustive Relevance Assessments for {XML} Retrieval Evaluation}, Type = {International Conference}, Year = {2004}}

2003

  • B. Piwowarski and P. Gallinari, “Structure, recherche d’information et apprentissage,” , Lyon, France, 2003.
    [Bibtex] 
     @inproceedings{Piwowarski2003Structure-recherche, Address = {Lyon, France}, Author = {Benjamin Piwowarski and Gallinari, Patrick}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:25 +0100}, Month = {January}, Title = {Structure, recherche d'information et apprentissage}, Type = {National conference}, Year = {2003}}
  • [PDF] B. Piwowarski and P. Gallinari, “A machine learning model for information retrieval with structured documents,” in Machine learning and data mining in pattern recognition, Leipzig, Germany, 2003, pp. 425-438.
    [Bibtex] 
     @inproceedings{Piwowarski2003A-Machine-Learning, Abstract = {Most recent document standards rely on structured representations. On the other hand, current information retrieval systems have been developed for flat document representations and cannot be easily extended to cope with more complex document types. Only a few models have been proposed for handling structured documents, and the design of such systems is still an open problem. We present here a new model for structured document retrieval which allows to compute and to combine the scores of document parts. It is based on bayesian networks and allows for learning the model parameters in the presence of incomplete data. We present an application of this model for ad-hoc retrieval and evaluate its performances on a small structured collection. The model can also be extended to cope with other tasks such as interactive navigation in structured documents or corpus}, Address = {Leipzig, Germany}, Author = {Benjamin Piwowarski and Gallinari, Patrick}, Booktitle = {Machine Learning and Data Mining in Pattern Recognition}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Editor = {Petra Perner}, Month = {July}, Pages = {425--438}, Publisher = {Springer Verlag}, Title = {A Machine Learning Model for Information Retrieval with Structured Documents}, Type = {International Conference}, Year = {2003}}
  • [PDF] B. Piwowarski, “Working group report: the assessment tool,” in Initiative for the evaluation of xml retrieval (inex). proceedings of the second inex workshop, Dagstuhl, Germany, 2003.
    [Bibtex] 
     @inproceedings{Piwowarski2003Working-group, Abstract = {This paper is the report of the working group on the evaluation assessment interface that was used in INEX'03. This paper describes the changes that are planned for INEX'04 and the different issues that were raised during the working group session.}, Address = {Dagstuhl, Germany}, Author = {Benjamin Piwowarski}, Booktitle = {INitiative for the Evaluation of XML Retrieval (INEX). Proceedings of the Second INEX Workshop}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Editor = {Fuhr, Norbert and Lalmas, Mounia and Malik, Saadia}, Month = {December}, Title = {Working group report: the Assessment Tool}, Type = {International Workshop}, Year = {2003}}
  • [PDF] B. Piwowarski, H. Vu, and P. Gallinari, “Bayesian networks and INEX’03,” in Initiative for the evaluation of xml retrieval (inex). proceedings of the second inex workshop, Dagstuhl, Germany, 2003.
    [Bibtex] 
     @inproceedings{Piwowarski2003Bayesian-Networks, Abstract = {We present a Bayesian framework for XML document retrieval. This framework allows us to consider content-only (CO) queries. We perform the retrieval task using inference in our network. The proposed model can adapt to a specific corpus through parameter learning and it uses a grammar to speed up the retrieval process in large or distributed databases. We also experimented list filtering to avoid overlap in the retrieved element list.}, Address = {Dagstuhl, Germany}, Author = {Benjamin Piwowarski and Vu, Huyen-Trang and Gallinari, Patrick}, Booktitle = {INitiative for the Evaluation of XML Retrieval (INEX). Proceedings of the Second INEX Workshop}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Editor = {Fuhr, Norbert and Lalmas, Mounia and Malik, Saadia}, Month = {December}, Title = {Bayesian Networks and {INEX}'03}, Type = {International Workshop}, Year = {2003}}
  • G. Kazai, M. Lalmas, and B. Piwowarski, “Inex guidelines for topic development,” in Proceedings of inex 2003, 2003.
    [Bibtex] 
     @inproceedings{Kazai2003INEX-Guidelines, Author = {Kazai, Gabriella and Lalmas, Mounia and Benjamin Piwowarski}, Booktitle = {Proceedings of INEX 2003}, Crossref = {INEX2003}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:22 +0100}, Editor = {Fuhr, Norbert and Lalmas, Mounia and Malik, Saadia}, Keywords = {Evaluation}, Owner = {bpiwowar}, Read = {Yes}, Title = {INEX Guidelines for Topic Development}, Type = {International Workshop}, Year = {2003}}
  • [PDF] B. Piwowarski and P. Gallinari, “Expected ratio of relevant units: a measure for structured information retrieval,” in Initiative for the evaluation of xml retrieval (inex). proceedings of the second inex workshop, Dagstuhl, France, 2003.
    [Bibtex] 
     @inproceedings{Piwowarski2003Expected-Ratio, Abstract = {Since the 60's, evaluation has been a key problem for Information Retrieval (IR) systems and has been extensively discussed in the IR community. New IR paradigms, like Structured Information Retrieval (SIR), make classical evaluation measures inappropriate. A few tentative extensions to these measures has been proposed but are also inadequate. We do propose in this paper a new measure which is a generalisation of recall. This measure takes into account the specificity of SIR, when elements to be retrieved are linked by structural relationships. We show an instantiation of this measure on the INEX database and present experiments to show how well it is adapted to SIR evaluation.}, Address = {Dagstuhl, France}, Author = {Benjamin Piwowarski and Gallinari, Patrick}, Booktitle = {INitiative for the Evaluation of XML Retrieval (INEX). Proceedings of the Second INEX Workshop}, Crossref = {INEX2003}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:22 +0100}, Editor = {Fuhr, Norbert and Lalmas, Mounia and Malik, Saadia}, Keywords = {Evaluation}, Month = {December}, Owner = {bpiwowar}, Title = {Expected Ratio of Relevant Units: A Measure for Structured Information Retrieval}, Type = {International Workshop}, Year = {2003}}

2002

  • B. Piwowarski and P. Gallinari, “A bayesian network model for page retrieval in a hierarchically structured collection,” in Xml workshop of the 25th acm sigir conference, Tampere, Finland, 2002.
    [Bibtex] 
     @inproceedings{Piwowarski2002A-Bayesian-Network, Abstract = {Most recent document standards rely on structured representations. Nevertheless, current information retrieval systems have been developed for flat document representations and cannot be easily extended to cope with more complex document types. Only a few models have been proposed for handling structured documents, and the design of such systems is still an open problem. We present here a new model for structured document retrieval which allows to compute and to combine the scores of document parts. It is based on bayesian networks and makes use of machine learning algorithms for learning the model parameters in the presence of incomplete data. We present an application of this model for ad-hoc retrieval and evaluate its performances on a small structured collection.}, Address = {Tampere, Finland}, Author = {Benjamin Piwowarski and Gallinari, Patrick}, Booktitle = {XML Workshop of the 25th ACM SIGIR Conference}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:25 +0100}, Month = {August}, Title = {A Bayesian Network Model for Page Retrieval in a Hierarchically Structured Collection}, Type = {International Workshop}, Year = {2002}}
  • B. Piwowarski, G. Faure, and P. Gallinari, “Bayesian networks and INEX,” in Proceedings of the first annual workshop of the initiative for the evaluation of xml retrieval (inex), Dagstuhl, Germany, 2002.
    [Bibtex] 
     @inproceedings{Piwowarski2002Bayesian-networks, Abstract = {We present a bayesian framework for XML document retrieval. This framework allows us to consider content only and content and structure queries. We perform the retrieval task using inference in our network. Our model can adapt to a specific corpora through parameter learning.}, Address = {Dagstuhl, Germany}, Author = {Benjamin Piwowarski and Faure, Georges-Etienne and Gallinari, Patrick}, Booktitle = {Proceedings of the First Annual Workshop of the Initiative for the Evaluation of XML retrieval (INEX)}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:24 +0100}, Month = {December}, Publisher = {ERCIM}, Series = {DELOS workshop}, Title = {Bayesian networks and {INEX}}, Type = {International Workshop}, Year = {2002}}
  • [PDF] B. Piwowarski, L. Denoyer, and P. Gallinari, “Un modèle pour la recherche d’information sur des documents structurés,” in Jadt, Saint-Malo, France, 2002.
    [Bibtex] 
     @inproceedings{Piwowarski2002Un-modele-pour, Abstract = {Avec l'{\'e}mergence de nouveaux standards comme le XHTML ou le DocBook o{\`u} la structure des documents est apparente, la communaut{\'e} de recherche d'information a commenc{\'e} {\`a} s'int{\'e}resser {\`a} l'utilisation de cette nouvelle source d'information. La t{\^a}che est ardue, car il s'agit de concilier de sources d'informations de natures diff{\'e}rentes, {\`a} savoir le texte et la structure. Quelques mod{\`e}les ont fait leur apparition ; mais ces travaux manquent encore de maturit{\'e} et n'utilisent la structure que d'une mani{\`e}re simple. Le cadre th{\'e}orique que nous pr{\'e}sentons dans ce papier a pour vocation de permettre une prise en compte de la structure dans les t{\^a}ches de recherche documentaire et de cat{\'e}gorisation. Ce mod{\`e}le bas{\'e} sur l'utilisation de r{\'e}seaux bay{\'e}siens est capable de s'adapter {\`a} de nouvelles bases de donn{\'e}es gr{\^a}ce {\`a} des techniques d'apprentissage num{\'e}rique. Il offre {\'e}galement des perspectives de d{\'e}veloppement int{\'e}ressantes comme par exemple la navigation interactive dans une base de donn{\'e}es.}, Address = {Saint-Malo, France}, Author = {Benjamin Piwowarski and Denoyer, Ludovic and Gallinari, Patrick}, Booktitle = {JADT}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Month = {March}, Title = {Un mod{\`e}le pour la recherche d'information sur des documents structur{\'e}s}, Type = {National conference}, Year = {2002}}

2000

  • [PDF] B. Piwowarski, “Learning in information retrieval: a probabilistic differential approach,” in Proceedings of the bcs-irsg, 22nd annual colloquium on information retrieval research, Sidney Sussex College, Cambridge, England, 2000.
    [Bibtex] 
     @inproceedings{Piwowarski2000Learning-in-Information, Abstract = {Since user's relevance judgments are a source of evidence for information retrieval, learning from this feedback is an appealing idea. Many different learning techniques have successfully been used for relevance feedback. In most models, learning is either performed off line or is based on simple heuristics. The approach we propose is based on a classical probabilistic model in which learning from feedback is simple and incremental. In this paper, we extend this model, presenting a new similarity function that takes into account feedback on the entire database while computing the score between a query and a single document. As a result, when a user judges a document it modifies the whole retrieval process.}, Address = {Sidney Sussex College, Cambridge, England}, Author = {Benjamin Piwowarski}, Booktitle = {Proceedings of the BCS-IRSG, 22nd Annual Colloquium on Information Retrieval Research}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Keywords = {Information Retrieval, learning}, Month = {April}, Rating = {0}, Title = {Learning in Information Retrieval: a Probabilistic Differential Approach}, Toread = {No}, Type = {International Conference}, Year = {2000}}
  • [PDF] B. Piwowarski, “Apprentissage et recherche documentaire : une approche probabiliste différentielle,” in Colloque francophone sur l’apprentissage automatique (cap’2000), Saint-Etienne, France, 2000.
    [Bibtex] 
     @inproceedings{Piwowarski2000Apprentissage-et-Recherche, Abstract = {Le but de la recherche documentaire (RD) consiste {\`a} trouver, parmi une base de documents, ceux qui r{\'e}pondent le mieux {\`a} une demande formul{\'e}e par un utilisateur. Les exp{\'e}riences r{\'e}alis{\'e}es ont montr{\'e} qu'il {\'e}tait impossible d'obtenir des r{\'e}sultats satisfaisants avec des syst{\`e}mes o{\`u} la repr{\'e}sentation des documents ainsi que les param{\`e}tres utilis{\'e}s lors de la recherche {\'e}taient fig{\'e}s. C'est pourquoi on emploie l'apprentissage pour modifier les param{\`e}tres du syst{\`e}me de recherche, en se basant sur les jugements (feedback) que les utilisateurs peuvent porter sur la qualit{\'e} des documents trouv{\'e}s. Pourtant, l'application de telles techniques reste probl{\'e}matique. En effet, celles-ci sont soit complexes {\`a} mettre en oeuvre (traitement off-line), soit difficiles {\`a} contr{\^o}ler. Nous proposons une approche est bas{\'e}e sur un mod{\`e}le probabiliste de recherche documentaire qui permet d'utiliser le feedback de mani{\`e}re rapide et incr{\'e}mentale. Dans cet article, nous {\'e}tendons ce mod{\`e}le pour ne plus regarder si un document r{\'e}pond {\`a} une requ{\^e}te dans l'absolu mais plut{\^o}t relativement {\`a} une base documentaire donn{\'e}e. Ainsi, un jugement portant sur un seul document modifie l'ensemble du processus de recherche am{\'e}liorant ainsi la rapidit{\'e} de l'apprentissage. De plus, cette extension facilite notablement l'initialisation de la repr{\'e}sentation des documents.}, Address = {Saint-Etienne, France}, Author = {Benjamin Piwowarski}, Booktitle = {Colloque Francophone sur l'Apprentissage Automatique (CAP'2000)}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:21 +0100}, Keywords = {national conference}, Month = {June}, Title = {Apprentissage et Recherche Documentaire : une Approche Probabiliste Diff{\'e}rentielle}, Type = {National conference}, Year = {2000}}

Journals

2009

  • B. Piwowarski, A. Trotman, and M. Lalmas, “Sound and complete relevance assessments for XML retrieval,” ACM Transactions On Information Systems, vol. 27, iss. 1, 2009.
    [Bibtex] 
     @article{Piwowarski2009Sound-and-Complete, Abstract = {In information retrieval research, comparing retrieval approaches requires test collections consisting of documents, user requests and relevance assessments. Obtaining relevance assessments that are as sound and complete as possible is crucial for the comparison of retrieval approaches. In XML retrieval, the problem of obtaining sound and complete relevance assessments is further complicated by the structural relationships between retrieval results. A major difference between XML retrieval and flat document retrieval is that the relevance of elements (the retrievable units) is not independent of that of related elements. This has major consequences for the gathering of relevance assessments. This paper describes investigations into the creation of sound and complete relevance assessments for the evaluation of content-oriented XML retrieval as carried out at INEX, the evaluation campaign for XML retrieval. The campaign, now in its seventh year, has had three substantially different approaches to gather assessments and has finally settled on a highlighting method for marking relevant passages within documents - even though the objective is to collect assessments at element level. The different methods of gathering assessments at INEX are discussed and contrasted. The highlighting method is shown to be the most reliable of the methods.}, Author = {Benjamin Piwowarski and Trotman, Andrew and Lalmas, Mounia}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:24 +0100}, Journal = {ACM Transactions On Information Systems}, Month = {jan}, Number = {1}, Private = {Yes}, Read = {Yes}, Short-Journal = {ACM TOIS}, Title = {Sound and Complete Relevance Assessments for {XML} Retrieval}, Type = {Journal}, Volume = {27}, Year = {2009}}
  • J. M. Fernández-Luna, J. F. Huete, and B. Piwowarski, “Introduction to the special issue on Graphical Models and Information Retrieval,” International Journal of Approximate Reasoning, vol. 50, iss. 7, pp. 929-931, 2009.
    [Bibtex] 
     @article{Fernandez-Luna2009Introduction-to-the-special, Author = {Juan M. {Fern{\'a}ndez-Luna} and Juan F. Huete and Benjamin Piwowarski}, Date-Added = {2009-12-14 11:20:13 +0000}, Date-Modified = {2011-04-11 13:31:22 +0100}, Issn = {{0888-613X}}, Journal = {International Journal of Approximate Reasoning}, Month = {July}, Number = {7}, Pages = {929--931}, Title = {{Introduction to the special issue on Graphical Models and Information Retrieval}}, Volume = {50}, Year = {2009}}

2007

  • [PDF] [DOI] B. Piwowarski, P. Gallinari, and G. Dupret, “An extension of precision-recall with user modelling (PRUM): application to XML retrieval,” ACM Transactions On Information Systems, vol. 25, iss. 1, 2007.
    [Bibtex] 
     @article{Piwowarski2007An-Extension-of-Precision-Recall, Abstract = {Standard Information Retrieval (IR) metrics are not well suited for new paradigms like XML or Web IR in which retrievable information units are document elements and/or sets of related documents. Part of the problem stems from the classical hypotheses on the user models: They do not take into account the structural or logical context of document elements or the possibility of navigation between units. This article proposes an explicit and formal user model that encompasses a large variety of user behaviors. Based on this model, we extend the probabilistic precision-recall metric to deal with the new IR paradigms.}, Author = {Benjamin Piwowarski and Gallinari, Patrick and Dupret, Georges}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:22 +0100}, Doi = {10.1145/1198296.1198297}, Journal = {ACM Transactions On Information Systems}, Keywords = {XML, Information Retrieval, Evaluation}, Number = {1}, Owner = {bpiwowar}, Read = {Yes}, Timestamp = {2005.11.16}, Title = {An Extension of Precision-Recall with User Modelling ({PRUM}): Application to {XML} Retrieval}, Type = {Journal}, Volume = {25}, Year = {2007}}

2005

  • [PDF] [DOI] B. Piwowarski and P. Gallinari, “A bayesian network for XML information retrieval: searching and learning with the INEX collection,” Information Retrieval, vol. 8, iss. 4, pp. 655-681, 2005.
    [Bibtex] 
     @article{Piwowarski2005A-Bayesian-Network, Abstract = {Most recent document standards like XML rely on structured representations. On the other hand, current information retrieval systems have been developed for flat document representations and cannot be easily extended to cope with more complex document types. The design of such systems is still an open problem. We present a new model for structured document retrieval which allows computing scores of document parts. This model is based on Bayesian networks whose conditional probabilities are learnt from a labelled collection of structured documents -- which is composed of documents, queries and their associated assessments. Training these models is a complex machine learning task and is not standard. This is the focus of the paper: we propose here to train the structured Bayesian Network model using a cross-entropy training criterion. Results are presented on the INEX corpus of XML documents.}, Author = {Benjamin Piwowarski and Gallinari, Patrick}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:22 +0100}, Doi = {10.1007/s10791-005-0751-6}, Journal = {Information Retrieval}, Month = {December}, Number = {4}, Pages = {655-681}, Title = {A Bayesian Network for {XML} Information Retrieval: Searching and Learning with the {INEX} Collection}, Type = {Journal}, Volume = {8}, Year = {2005}}

Other

2011

  • B. Piwowarski and R. Blanco, “Recuperación de información: un enfoque práctico y multidisciplinar,” , pp. 33-60, 2011.
    [Bibtex] 
     @InBook{Piwowarski2011Introduccion, author = {Benjamin Piwowarski and Roi Blanco}, editor = {Cacheda Seijo, Fidel and Fernandez Luna, Juan Manuel and Huete Guadix, Juan Francisco}, title = {Recuperación de Información: Un Enfoque Práctico y Multidisciplinar}, chapter = {Introducci\'on a la recuperaci\'on de informaci\'on}, publisher = {Ra-Ma Editorial}, year = 2011, month = sep, pages = {33--60}, note = {English title: Introduction to Information Retrieval}}
  • Y. Moshfeghi, B. Piwowarski, and J. M. Jose, “Handling data sparsity in collaborative filtering using emotion and semantic based features,” , 2011.
    [Bibtex] 
     @inproceedings{Moshfeghi2011Handling, Author = {Yashar Moshfeghi and Benjamin Piwowarski and Joemon M. Jose}, Booktitle = {Proceedings of the 34th {Annual International ACM SIGIR Conference on Research and Development in Information Retrieval}}, Crossref = {SIGIR2011}, Date-Added = {2011-04-11 13:26:54 +0100}, Date-Modified = {2011-04-11 13:31:25 +0100}, Month = {June}, Publisher = {{ACM}}, Short-Booktitle = {SIGIR}, Short-Title = {SIGIR}, Title = {Handling Data Sparsity in Collaborative Filtering using Emotion and Semantic Based Features}, Year = {2011}}

2010

  • [PDF] B. Piwowarski, I. Frommholz, M. Lalmas, and K. van Rijsbergen, “Exploring a multidimensional representation of documents and queries (extended version),” , iss. 1002.3238, 2010.
    [Bibtex] 
     @techreport{Piwowarski2010Exploring-a-Multidimensional-Full, Abstract = {In Information Retrieval (IR), whether implicitly or explicitly, queries and documents are often represented as vectors. However, it may be more beneficial to consider documents and/or queries as multidimensional objects. Our belief is this would allow building ``truly'' interactive IR systems, i.e., where interaction is fully incorporated in the IR framework. The probabilistic formalism of quantum physics represents events and densities as multidimensional objects. This paper presents our first step towards building an interactive IR framework upon this formalism, by stating how the first interaction of the retrieval process, when the user types a query, can be formalised. Our framework depends on a number of parameters affecting the final document ranking. In this paper we ex- perimentally investigate the effect of these parameters, showing that the proposed representation of documents and queries as multidimensional ob- jects can compete with standard approaches, with the additional prospect to be applied to interactive retrieval.}, Author = {Benjamin Piwowarski and Ingo Frommholz and Mounia Lalmas and Keith van Rijsbergen}, Date-Added = {2010-02-15 14:20:10 +0000}, Date-Modified = {2011-04-11 13:31:24 +0100}, Institution = {arXiv}, Number = {1002.3238}, Title = {Exploring a Multidimensional Representation of Documents and Queries (extended version)}, Year = {2010}}
  • B. Piwowarski and G. Dupret, System and method for deducing user interaction patterns based on limited activities, 2010.
    [Bibtex] 
     @misc{Piwowarski2010System, Author = {B. Piwowarski and G. Dupret}, Date-Added = {2010-11-10 17:51:34 +0000}, Date-Modified = {2011-04-11 13:31:24 +0100}, Howpublished = {United States Patent Application 20100082605}, Month = {August}, Title = {System and method for deducing user interaction patterns based on limited activities}, Year = {2010}}

2009

  • [PDF] [DOI] J. Pehcevski and B. Piwowarski, “Evaluation metrics for structured text retrieval,” , pp. 1015-1024, 2009.
    [Bibtex] 
     @incollection{Pehcevski2009Evaluation-Metrics, Author = {Jovan Pehcevski and Benjamin Piwowarski}, Booktitle = {Encyclopedia of Database Systems}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:25 +0100}, Doi = {10.1007/978-0-387-39940-9}, Editor = {{\"O}zsu, M. Tamer and Liu, Ling}, Month = {May}, Pages = {1015--1024}, Publisher = {Springer}, Read = {Yes}, Series = {Encyclopedia of Database Systems}, Title = {Evaluation Metrics for Structured Text Retrieval}, Year = {2009}}
  • B. Piwowarski and H. Zaragoza, “System and method for creating and applying predictive user click models to predict a target page associated with a search query,” , 2009.
    [Bibtex] 
     @misc{Piwowarski2009System, Author = {B. Piwowarski and Hugo Zaragoza}, Date-Added = {2010-11-10 17:53:20 +0000}, Date-Modified = {2011-04-11 13:31:24 +0100}, Howpublished = {United States Patent Application 20090094196}, Month = {July}, Title = {System and Method for Creating and Applying Predictive User Click Models to Predict a Target Page Associated with a Search Query}, Year = {2009}}
  • [PDF] B. Piwowarski and M. Lalmas, “A Quantum-based Model for Interactive Information Retrieval (extended version),” arXiv, 0906.4026, , 2009.
    [Bibtex] 
     @techreport{Piwowarski2009A-Quantum-based-Model, Abstract = {Even the best information retrieval model cannot always identify the most useful answers to a user query. This is in particular the case with web search systems, where it is known that users tend to minimise their effort to access relevant information. It is, however, believed that the interac- tion between users and a retrieval system, such as a web search engine, can be exploited to provide better answers to users. Interactive Informa- tion Retrieval (IR) systems, in which users access information through a series of interactions with the search system, are concerned with building models for IR, where interaction plays a central role. There are many pos- sible interactions between a user and a search system, ranging from query (re)formulation to relevance feedback. However, capturing them within a single framework is difficult and previously proposed approaches have mostly focused on relevance feedback. In this paper, we propose a general framework for interactive IR that is able to capture the full interaction process in a principled way. Our approach relies upon a generalisation of the probability framework of quantum physics, whose strong geometric component can be a key towards a successful interactive IR model.}, Author = {Benjamin Piwowarski and Mounia Lalmas}, Date-Added = {2009-06-22 17:29:45 +0100}, Date-Modified = {2011-04-11 13:31:21 +0100}, Group = {Quantum Information; Information Retrieval}, Institution = {arXiv}, Month = {September}, Number = {0906.4026}, Title = {{A Quantum-based Model for Interactive Information Retrieval (extended version)}}, Year = {2009}}

2003

  • [PDF] B. Piwowarski, “Techniques d’apprentissage pour le traitement d’informations structurées : application à la recherche d’information,” , 2003.
    [Bibtex] 
     @phdthesis{Piwowarski2003Techniques-dapprentissage, Abstract = {Dans le contexte de l'Acc{\`e}s {\`a} l'Information, la notion de document {\'e}lectronique a consid{\'e}rablement {\'e}volu{\'e}e. En peu de temps, nous sommes pass{\'e}s d'un monde o{\`u} la repr{\'e}sentation dominante d'un document {\'e}tait constitu{\'e}e de la suite de ses mots ou de ses phrases {\`a} une repr{\'e}sentation bien plus riche et structur{\'e}e~(multim{\'e}dia). Cette {\'e}volution touche les communaut{\'e}s de la Recherche d'Information~(RI), des Bases de Donn{\'e}es et de l'Apprentissage Automatique qui sont celles qui sont au coeur de notre travail. Dans ce manuscrit, nous pr{\'e}sentons un mod{\`e}le complet de RI structur{\'e}e bas{\'e} sur les R{\'e}seaux Bay{\'e}siens~(RB). Notre mod{\`e}le est capable de r{\'e}pondre {\`a} des questions portant {\`a} la fois sur la structure et le contenu. Notre mod{\`e}le peut {\'e}galement apprendre de mani{\`e}re automatique ses param{\`e}tres. Nous nous int{\'e}ressons {\'e}galement {\`a} la d{\'e}finition d'une nouvelle mesure d'{\'e}valuation des syst{\`e}mes de RI structur{\'e}s. }, Address = {Paris, France}, Author = {Benjamin Piwowarski}, Date-Added = {2008-09-02 13:52:16 +0100}, Date-Modified = {2011-04-11 13:31:23 +0100}, Month = {July}, School = {University Paris 6}, Title = {Techniques d'apprentissage pour le traitement d'informations structur{\'e}es : application {\`a} la recherche d'information}, Year = {2003}}
  • B. Piwowarski, M. Amini, and M. Lalmas, “On using a Quantum Physics formalism for Multi-document Summarisation,” {Journal of the American Society for Information Science and Technology}.
    [Bibtex] 
     @Article{Piwowarski2011OnUsing, author = {Piwowarski, Benjamin and Amini, Massih-Reza and Lalmas, Mounia}, title = {{On using a Quantum Physics formalism for Multi-document Summarisation}}, journal = {{Journal of the American Society for Information Science and Technology}}, note = {accepted for publication} }