efficient diversification of web search results
play

Efficient Diversification of Web Search Results G. Capannini, F. M. - PowerPoint PPT Presentation

Jan 30, 2023 •318 likes •761 views

Efficient Diversification of Web Search Results G. Capannini, F. M. Nardini, R. Perego, and F. Silvestri ISTI-CNR, Pisa, Italy Laboratory Web Search Results Diversification Query: Vinci, what is the users intent? Information

  1. Efficient Diversification of Web Search Results G. Capannini, F. M. Nardini, R. Perego, and F. Silvestri ISTI-CNR, Pisa, Italy Laboratory

  2. Web Search Results Diversification • Query: “Vinci”, what is the user’s intent? • Information on Leonardo da Vinci? • Information on Vinci, the small village in Tuscany? • Information on Vinci, the company? • Others? F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 2

  3. Web Search Results Diversification • Query: “Vinci”, what is the user’s intent? • Information on Leonardo da Vinci? • Information on Vinci, the small village in Tuscany? • Information on Vinci, the company? • Others? F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 2

  4. Results Diversification as a Coverage Problem • Hypothesis: • For each user’s query I can tell what is the set of all possible intents • For each document in the collection I can tell what are all the possible user’s intents it represents • each intent for each document is, possibly, weighted by a value representing how much that intent is represented by that document (e.g., 1/2 of document D is related to the intent of “digital photography techniques”) • Goal: • Select the set of k documents in the collection covering the maximum amount of intent weight. i.e., maximize the number of satisfied users. F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 3

  5. State-of-the-Art Methods • IASelect: • Rakesh Agrawal, Sreenivas Gollapudi, Alan Halverson, and Samuel Ieong. 2009. Diversifying search results . In Proceedings of the Second ACM International Conference on Web Search and Data Mining (WSDM '09) , Ricardo Baeza- Yates, Paolo Boldi, Berthier Ribeiro-Neto, and B. Barla Cambazoglu (Eds.). ACM, New York, NY, USA, 5-14. • xQuAD: • Rodrygo L. T. Santos, Craig Macdonald, and Iadh Ounis. Exploiting query reformulations for Web search result diversification . In Proceedings of the 19th International Conference on World Wide Web , pages 881-890, Raleigh, NC, USA, 2010. ACM. F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 4

  6. Diversify( k ) F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 5

  7. Diversify( k ) intents F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 5

  8. Diversify( k ) the weight intents F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 5

  9. Diversify( k ) the weight intents is the probability of being relative to intent c F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 5

  10. Diversify( k ) the weight intents is the probability of being relative to intent c d is not pertinent to c F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 5

  11. Diversify( k ) the weight intents is the probability of being relative to intent c d is not pertinent to c no doc is pertinent to c F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 5

  12. Diversify( k ) the weight intents is the probability of being relative to intent c d is not pertinent to c no doc is at least one doc is pertinent to c pertinent to c F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 5

  13. Known Results • Diversify( k ) is NP-hard: • Reduction from max-weight coverage • Diversify( k )’s objective function is sub-modular: • Admits a (1-1/e) -approx. algorithm. • The algorithm works by inserting one result at a time, we insert the result with the max marginal utility. • Quadratic complexity in the number of results to consider: • at each iteration scan the complete list of not-yet-inserted results. F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 6

  14. Known Results • Diversify( k ) is NP-hard: • Reduction from max-weight coverage • Diversify( k )’s objective function is sub-modular: • Admits a (1-1/e) -approx. algorithm. • The algorithm works by inserting one result at a time, we insert the result with the max marginal utility. • Quadratic complexity in the number of results to consider: • at each iteration scan the complete list of not-yet-inserted results. F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 6

  15. It looks reasonable, but... • ... it may not diversify! • The objective function is NOT about including as many categories as possible in the final results set. • It is possible that even if there are less than k categories, NOT all categories will be covered: • the formulation explicitly considers how well a document satisfies a given category. • If a category c is dominant and not well satisfied, more documents from c will be added: • possible at the expense of not showing certain categories altogether. F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 7

  16. xQuAD_Diversify( k ) F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 8

  17. xQuAD_Diversify( k ) F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 8

  18. xQuAD_Diversify( k ) Same problem as before... It may not diversify! F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 8

  19. Our Proposal: MaxUtility F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 9

  20. Our Proposal: Vinci MaxUtility F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 9

  21. Leonardo da Vinci Our Proposal: Vinci Vinci Town MaxUtility Vinci Group F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 9

  22. Leonardo da Vinci Our Proposal: 5/12 Vinci Vinci Town 1/3 MaxUtility Vinci Group 1/4 F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 9

  23. Leonardo da Vinci Our Proposal: 5/12 Vinci Vinci Town 1/3 MaxUtility Vinci Group 1/4 R q S F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 9

  24. Leonardo da Vinci Our Proposal: 5/12 Vinci Vinci Town 1/3 MaxUtility Vinci Group 1/4 R q S F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 9

  25. MaxUtility_Diversify( k ) F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 10

  26. Why it is Efficient? • By using a simple arithmetic argument we can show that: • Therefore we can find the optimal set S of diversified documents by using a sort-based approach. F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 11

  27. OptSelect F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 12

  28. OptSelect F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 12

  29. The Specialization Set S q • It is crucial for OptSelect to have the set of specialization available for each query. • Our method is, thus, query log- based . • we use a query recommender system to obtain a set of queries from which S q is built by including the most popular (i.e., freq. in query log > f(q) / s ) D. Broccolo, L. Marcon, F.M. Nardini, R. Perego, F. Silvestri recommendations: Generating Suggestions for Queries in the Long Tail with an Inverted Index Information Processing & Management, August 2011 F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 13

  30. Probability Estimation F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 14

  31. Usefulness of a Result F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 15

  32. Usefulness of a Result F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 15

  33. Experiments: Settings • TREC 2009 Web track's Diversity Task framework: • ClueWeb-B, the subset of the TREC ClueWeb09 dataset • The 50 topics (i.e., queries) provided by TREC • We evaluate α -NDCG and IA-P • All the tests were conducted on a Intel Core 2 Quad PC with 8Gb of RAM and Ubuntu Linux 9.10 (kernel 2.6.31-22). F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 16

  34. Experiments: Quality F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 17

  35. Experiments: Quality F. M. Nardini - Efficient Diversification of Web Search Results - VLDB 2011 - Aug/Sept 2011, Seattle, US 17

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Efficient visual search of local features Efficient visual search of local features Cordelia

Efficient visual search of local features Efficient visual search of local features Cordelia

Efficient visual search of local features Efficient visual search of local features Cordelia Schmid Cordelia Schmid Visual search Visual search change in viewing angle Matches Matches 22 correct matches Image search system for large

1.05k views • 74 slides
Efficient Local Search Application Examples Graph Coloring Traveling Salesman Problem Single

Efficient Local Search Application Examples Graph Coloring Traveling Salesman Problem Single

Outline DM811 HEURISTICS AND LOCAL SEARCH ALGORITHMS FOR COMBINATORIAL OPTIMZATION Lecture 8 1. Efficient Local Search Efficiency vs Effectiveness Efficient Local Search Application Examples Graph Coloring Traveling Salesman Problem

555 views • 7 slides
An Efficient Algorithm for Feature-based 3D Point Cloud Correspondence Search Outline

An Efficient Algorithm for Feature-based 3D Point Cloud Correspondence Search Outline

Zili Yi Co-authors: Yang Li, Minglun Gong Memorial University of Newfoundland 2016-12-12 An Efficient Algorithm for Feature-based 3D Point Cloud Correspondence Search Outline Introduction Background Method Results

223 views • 18 slides
Permutation Search Methods are Efficient, Yet Faster Search is Possible Bileg (Bilegsaikhan)

Permutation Search Methods are Efficient, Yet Faster Search is Possible Bileg (Bilegsaikhan)

Permutation Search Methods are Efficient, Yet Faster Search is Possible Bileg (Bilegsaikhan) Naidan 1 Leo (Leonid) Boytsov 2 Eric Nyberg 2 1 Norwegian University of Science and Technology (NTNU) 2 Carnegie Mellon University (CMU)

577 views • 54 slides
IDWalk : a local search algorithm combining intensification and diversification Bertrand Neveu 1 ,

IDWalk : a local search algorithm combining intensification and diversification Bertrand Neveu 1 ,

1 IDWalk : a local search algorithm combining intensification and diversification Bertrand Neveu 1 , Gilles Trombettoni 1 , Fred Glover 2 1 Equipe COPRIN CERTIS-I3S-INRIA, Sophia Antipolis, France neveu@sophia.inria.fr trombe@sophia.inria.fr 2

259 views • 21 slides
Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label

Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label

Introduction Methodology Results Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label Active Learning Weishi Shi and Qi Yu B. Thomas Golisano College of Computing and Information Sciences Rochester

332 views • 12 slides
Entity-oriented Entity-oriented Search Result Diversification A d Andrey Plakhov Pl kh Yandex

Entity-oriented Entity-oriented Search Result Diversification A d Andrey Plakhov Pl kh Yandex

Entity-oriented Entity-oriented Search Result Diversification A d Andrey Plakhov Pl kh Yandex Outline Outline Introduction Brief overview Brief overview Optimization target: pFound-IA Implementation details

429 views • 30 slides
How efficient are binary search trees? Balanced search trees Balancing a tree means to keep the

How efficient are binary search trees? Balanced search trees Balancing a tree means to keep the

CS206 CS206 How efficient are binary search trees? Balanced search trees Balancing a tree means to keep the left and right subtree of Binary search tree operations take time O ( h ) , where h is the every node of roughly equal size.

200 views • 3 slides
Binary Search Trees ! A data structures with efficient support for many dynamic set operations:

Binary Search Trees ! A data structures with efficient support for many dynamic set operations:

Binary Search Trees ! A data structures with efficient support for many dynamic set operations: Search/Find Minimum/findMin Maximum/findMax Binary Search Trees Predecessor Successor Insert Delete/Remove ! All

83 views • 4 slides
Diversification, Efficiency, and Diversification, Efficiency, and Diversification, Efficiency,

Diversification, Efficiency, and Diversification, Efficiency, and Diversification, Efficiency,

Diversification, Efficiency, and Diversification, Efficiency, and Diversification, Efficiency, and Diversification, Efficiency, and Economic Growth Economic Growth Economic Growth Economic Growth Seminar presentation at Research Colloquium

406 views • 28 slides
Efficient visual search of local features Cordelia Schmid Visual search change in viewing

Efficient visual search of local features Cordelia Schmid Visual search change in viewing

Efficient visual search of local features Cordelia Schmid Visual search change in viewing angle Matches 22 correct matches Image search system for large datasets Large image dataset (one million images or more) query ranked image list

1.2k views • 43 slides
Efficient query processing Efficient scoring, distributed query processing Web Search 1 Ranking

Efficient query processing Efficient scoring, distributed query processing Web Search 1 Ranking

Efficient query processing Efficient scoring, distributed query processing Web Search 1 Ranking functions In general, document scoring functions are of the form The BM25 function, is one of the best performing: The term frequency is

648 views • 31 slides
Exposing iClass Key Diversification Contents Introduction RFID iClass and Picopass

Exposing iClass Key Diversification Contents Introduction RFID iClass and Picopass

Usenix WOOT 2011 Flavio D. Garcia Gerhard de Koning Gans Roel Verdult Exposing iClass Key Diversification Contents Introduction RFID iClass and Picopass Key Diversification iClass Key Diversification DES and

619 views • 42 slides
Search Result Diversification Rodrygo L. T. Santos Craig Macdonald Iadh Ounis Department of

Search Result Diversification Rodrygo L. T. Santos Craig Macdonald Iadh Ounis Department of

Exploiting Query Reformulations for Web Search Result Diversification Rodrygo L. T. Santos Craig Macdonald Iadh Ounis Department of Computer Science Department of Computer Science Department of Computer Science University of Glasgow, UK

351 views • 20 slides
Efficient Top-k Algorithms for Fuzzy Search in String Collections Rares Vernica Chen Li

Efficient Top-k Algorithms for Fuzzy Search in String Collections Rares Vernica Chen Li

Efficient Top-k Algorithms for Fuzzy Search in String Collections Rares Vernica Chen Li Department of Computer Science University of California, Irvine First International Workshop on Keyword Search on Structured Data, 2009 Rares Vernica (UC

960 views • 56 slides
EFFICIENT NONMYOPIC ACTIVE SEARCH Shali Jiang, Gustavo Malkomes, Geoff Converse, Alyssa Shofner,

EFFICIENT NONMYOPIC ACTIVE SEARCH Shali Jiang, Gustavo Malkomes, Geoff Converse, Alyssa Shofner,

EFFICIENT NONMYOPIC ACTIVE SEARCH Shali Jiang, Gustavo Malkomes, Geoff Converse, Alyssa Shofner, Roman Garnett, Benjamin Moseley Washington University in St. Louis 12.10.16 1. ACTIVE SEARCH Finding interesting points Active search 1 In

615 views • 22 slides
Ms Aliah (Form Teacher) Ms Koh (Co-Form Teacher) Introduction of teachers Name Subject DID

Ms Aliah (Form Teacher) Ms Koh (Co-Form Teacher) Introduction of teachers Name Subject DID

07/03/2016 P1 Da Vinci Class Briefing By Ms Aliah (Form Teacher) Ms Koh (Co-Form Teacher) Introduction of teachers Name Subject DID Email Ms Aliah (FT) EL, Math, SS 65067646 sharifah_aliah_syed@moe.edu.sg Ms Koh Seok Hui (CO-FT) Art

552 views • 6 slides
By Ms May Lim (FT) Ms Josephine Teow (Co-FT) Introduction of teachers

By Ms May Lim (FT) Ms Josephine Teow (Co-FT) Introduction of teachers

07/03/2016 P2 Da Vinci Briefing By Ms May Lim (FT) Ms Josephine Teow (Co-FT) Introduction of teachers http://www.palmviewpri.moe.edu.sg/about-us/2016-form-and-co-form-teachers Mrs Tan Boon Yen Mr Ernest Tan Mathematics Physical Education

519 views • 4 slides
Intelligent Systems for Scientific Discovery Yolanda Gil Information Sciences

Intelligent Systems for Scientific Discovery Yolanda Gil Information Sciences

Intelligent Systems for Scientific Discovery Yolanda Gil Information Sciences Institute and Department of Computer Science University of Southern California http://www.isi.edu/~gil @yolandagil gil@isi.edu USC Information

733 views • 50 slides
Correlation between Stick - Slip events and contact charging in the dynamic friction at

Correlation between Stick - Slip events and contact charging in the dynamic friction at

Correlation between Stick - Slip events and contact charging in the dynamic friction at nano-scales G. Ananthakrishna Materials Research Centre Indian Institute Science Bangalore - 560012 Collaborator Jagadish Kumar G.A & J. Kumar,

700 views • 34 slides
Tap or Shower Or Can be Used Communally Made From UV stable food and water grade silicone it

Tap or Shower Or Can be Used Communally Made From UV stable food and water grade silicone it

A Low Cost Portable, Personal Tap & Shower System That Fits in Your Pocket = Tap or Shower Or Can be Used Communally Made From UV stable food and water grade silicone it dispenses a flow controllable stream of water in 3 different ways.

416 views • 10 slides
Mainstreaming Green Chemistry Webinar Series March 26, 2014 Perceptions and Experiences of

Mainstreaming Green Chemistry Webinar Series March 26, 2014 Perceptions and Experiences of

Mainstreaming Green Chemistry Webinar Series March 26, 2014 Perceptions and Experiences of Green Chemistry Practitioners With Lynn Leger ALCERECO What is the GC3? A cross sectoral, B-2-B network of more than 70 companies and other

396 views • 38 slides
Creative AI Combining Knowledge, Learning and Control for Expressive Modeling & Animation

Creative AI Combining Knowledge, Learning and Control for Expressive Modeling & Animation

Creative AI Combining Knowledge, Learning and Control for Expressive Modeling & Animation Marie-Paule Cani Ecole Polytechnique Paris, France Visual representations Mandatory to understand and create! @ Renaud Chabrier Leonardo da Vinci

639 views • 33 slides
Dr Abubakr Muhammad Assistant Professor Electrical

Dr Abubakr Muhammad Assistant Professor Electrical

EE-562 : Robot Motion Planning Lecture 1 Dr Abubakr Muhammad Assistant Professor Electrical Engineering, LUMS Director, CYPHYNETS Lab http://cyphynets.lums.edu.pk Resources Course material from

801 views • 62 slides

More recommend