SlideShare ist ein Scribd-Unternehmen logo
1 von 40
Exploratory search on topics through different 
perspectives with DBpedia 
Nicolas Marie, Fabien Gandon, Alain Giboin, Émilie Palagi 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
CONTEXT 
PROPOSITION 
EVALUATION 
CONCLUSION 
2 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
CONTEXT 
PROPOSITION 
EVALUATION 
CONCLUSION 
3 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
Search is only a partially solved problem [White, 2009] 
Ambiguous queries, natural language queries, exploratory search tasks… 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub 
10 blue links paradigm, 
simple, fast 
Exploratory search 
bottleneck
Exploratory search systems are optimized to support 
exploratory search tasks, common functionalities: 
Overviews 
Faceted interfaces 
Results clustering 
Low-cost of browsing (going back-and-forth functionalities) 
Query-suggestions and refinement 
Serendipitous discoveries provocation 
In-session of account related memory features 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub 
Linked data are promising for 
supporting exploratory search: 
• new algorithms 
• new interaction models 
optimized for exploration.
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub
Discovery Hub Maturity 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
1 perspective
I want to discover Claude Monet (painter)... 
In American culture 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub 
Topics are complex, multifaceted, 
One entity => multiple perspectives & 
knowledge nuances 
Entourage Art. movement 
In French culture Curiosities…
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
MORE 
Aemoo
CONTEXT 
PROPOSITION 
EVALUATION 
CONCLUSION 
13 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub 
The models and algorithms we propose 
unveil topic knowledge nuances by allowing the 
exploration of topics through several perspectives. 
In the graph context of linked data these 
perspectives correspond to different non exclusive 
sets of objects and relations that are informative on 
a topic regarding specific aspects. 
Flexible querying and data processing
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
Building perspectives thanks to spreading activation 
…… 
Refer to the papers for the complete formalization 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
Discovery Hub 
3 perspective-operations to expose 
knowledge nuances : 
• Criteria of interest specification 
• Controlled randomness injection 
• Data source selection 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
Discovery Hub Criteria of interest specification 
, dcterms:category, ?x 
, dcterms:category, ?x 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Classic similarity measure 
, dcterms:category, ?a | ?b | ?c |... 
, dcterms:category, ?a | ?b | ?c |... 
Criteria spec. similarity
Discovery Hub Criteria of interest specification 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Classic – top 5 artists 
« French / not impressonist » criteria specification – top 5 artists 
« Not French / Impressonist » criteria specification – top 5 artists
* r + (1-r)* 
Chosen level of randomness 
Randomness injection 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
* r + (1-r)* 
* r + (1-r)* 
* r + (1-r)* 
* r + (1-* r +
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub 
Local Kgram instance 
Data source selection 
dbpedia.org/sparql 
de.dbpedia.org/sparql 
es.dbpedia.org/sparql 
fr.dbpedia.org/sparql 
it.dbpedia.org/sparql
Discovery Hub Data source selection 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
CONTEXT 
PROPOSITION 
EVALUATION 
CONCLUSION 
28 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
Evaluated algorithm versions 
•Basis algorithm of Discovery Hub 
•Personalized algorithm through criteria 
specification 
•Randomized algorithm, with 0.5 threshold 
•Highly randomized algorithm (Highly R.), with 
1.0 threshold 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub
• Hypothesis 1: 
Users who specify their criteria of interest about a topic find the results of 
the search more relevant. 
• Hypothesis 2: 
Users who specify their criteria of interest about a topic do not find the 
results of the search less novel. 
• Hypothesis 3: 
The stronger is the level of randomness the more surprising the results are 
for the users. 
• Hypothesis 4: 
Even if the level of surprise is high, the majority of the top results are still 
relevant to the users. 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub
Discovery Hub 
푃푒푟푠표푛푎푙푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > [퐵푎푠푖푠 ; 퐼푛푡푒푟푒푠푡] 
" ; 퐷푖푠푡푎푛푐푒 < [ " ; 퐷푖푠푡푎푛푐푒] 
푃푒푟푠표푛푎푙푖푧푒푑 ; 푆푢푝푟푖푠푖푛푔 푅푒푠푢푙푡 > [퐵푎푠푖푠 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡] 
[ " ; Surprising Relation] > [ " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛] 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
퐻3 
퐻1 
퐻2 
퐻푖푔ℎ푙푦 푅. ; 푆푢푝푟푖푠푖푛푔 푅푒푠푢푙푡 > 푅푎푛푑표푚푖푧푒푑 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡 > [퐵푎푠푖푠 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡] 
[ " ; Suprising Relation] > " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛 > [ " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛] 
(Highly R. : Highly Randomized) 
퐻4 
퐻푖푔ℎ푙푦 푅푎푛푑표푚푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > 퐴푣푒푟푎푔푒 (2,5) 
푅푎푛푑표푚푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > 퐴푣푒푟푎푔푒 (2,5)
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
A « good » 
result in 
ESS is… 
Our definitions Chosen metrics : Questions 
(Likert Scale) 
… A 
surprising 
result 
A result is surprising if : 
• You discovered an 
unknown resource or 
relation 
• You discovered 
something unexpected 
Surprising Result 
This result is suprising 
? 
Surprising 
Relation 
This relation between 
the topic searched and 
the result is surprising 
? 
… An 
intersting 
result 
A result is interesting if : 
• You think it is similar to 
the topic explored 
• You think you will 
remind or reuse it 
Interesting Result 
This result is interesting 
? 
Distance between 
the Result and the 
topic searched 
This result is too distant 
from the topic searched 
? 
Discovery Hub
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub 
• 16 participants 
• Phase 1 : Selection of 2 topics in a list of 20 queries randomly choose in the query log of 
Discovery Hub 
- Information Visualization 
- Serge Gainsbourg (french singer) 
• Phase 2 : Specification of the categories of interest 
• Phase 3 : User Test (~1h) 
- Before the test 
- Interview (name, age, do they know Discovery Hub ?,…) 
- Presentation of Discovery Hub and the objective of the test 
- Presentation of the questions and simulation
H1 : Users who specify their criteria of interest about a topic 
find the results of the search more relevant. 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
퐻1 
푃푒푟푠표푛푎푙푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > [퐵푎푠푖푠 ; 퐼푛푡푒푟푒푠푡] 
" ; 퐷푖푠푡푎푛푐푒 < [ " ; 퐷푖푠푡푎푛푐푒]
H2: Users who specify their criteria of interest about a topic do 
not find the results of the search less novel 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
퐻2 
푃푒푟푠표푛푎푙푖푧푒푑 ; 푆푢푝푟푖푠푖푛푔 푅푒푠푢푙푡 > [퐵푎푠푖푠 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡] 
[ " ; Surprising Relation] > [ " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛]
H3: The stronger is the level of randomness the more surprising the results are for the 
users 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
퐻3 
퐻푖푔ℎ푙푦 푅. ; 푆푢푝푟푖푠푖푛푔 푅푒푠푢푙푡 > 푅푎푛푑표푚푖푧푒푑 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡 > [퐵푎푠푖푠 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡] 
[ " ; Suprising Relation] > " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛 > [ " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛] 
(Highly R. : Highly Randomized)
H4: Even if the level of surprise is high, the majority of the 
top results are still relevant to the users 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
퐻4 
퐻푖푔ℎ푙푦 푅푎푛푑표푚푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > 퐴푣푒푟푎푔푒 (2,5) 
푅푎푛푑표푚푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > 퐴푣푒푟푎푔푒 (2,5)
CONTEXT 
PROPOSITION 
EVALUATION 
CONCLUSION 
38 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub 
•We proposed a framework to enable multi-perspective 
exploratory search: 
- Formalization 
- Implementation 
- Evaluation 
• 3 operators : criteria spec., randomization, data selection 
• Evaluations globally positive, slight adjustements needed 
• Interesting propositions from the reviewers, thank you
Thank you ! Questions ? 
http://semreco.inria.fr 
werarediscoveryhub@gmail.com 
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 
Discovery Hub

Weitere ähnliche Inhalte

Andere mochten auch

Andere mochten auch (19)

Grupos mediáticos
Grupos mediáticosGrupos mediáticos
Grupos mediáticos
 
Luis Ragno En Prospectiva lo Humano es Capital
Luis  Ragno En Prospectiva lo Humano es CapitalLuis  Ragno En Prospectiva lo Humano es Capital
Luis Ragno En Prospectiva lo Humano es Capital
 
Webs interesantes cómo crear un cv impactante
Webs interesantes cómo crear un cv impactanteWebs interesantes cómo crear un cv impactante
Webs interesantes cómo crear un cv impactante
 
Base de datos en sql
Base de datos en sql  Base de datos en sql
Base de datos en sql
 
Maleta samsonite del futuro con gps
Maleta samsonite del futuro con gpsMaleta samsonite del futuro con gps
Maleta samsonite del futuro con gps
 
Memòria 2015
Memòria 2015Memòria 2015
Memòria 2015
 
Mystery Shopping Report for UniKassel Bibliothek
Mystery Shopping Report for UniKassel BibliothekMystery Shopping Report for UniKassel Bibliothek
Mystery Shopping Report for UniKassel Bibliothek
 
Social Media - KPI & ROI
Social Media - KPI & ROI Social Media - KPI & ROI
Social Media - KPI & ROI
 
Running lean jci national congress 2015
Running lean jci national congress 2015Running lean jci national congress 2015
Running lean jci national congress 2015
 
Miau
MiauMiau
Miau
 
Progetto scuola digitale
Progetto scuola digitaleProgetto scuola digitale
Progetto scuola digitale
 
Kits Detoxificación Dr. Reckeweg
Kits Detoxificación Dr. ReckewegKits Detoxificación Dr. Reckeweg
Kits Detoxificación Dr. Reckeweg
 
717
717717
717
 
Revista Deusto nº 106 (primavera - udaberria. 2010)
Revista Deusto nº 106 (primavera - udaberria. 2010)Revista Deusto nº 106 (primavera - udaberria. 2010)
Revista Deusto nº 106 (primavera - udaberria. 2010)
 
5 valencia ensanche
5 valencia ensanche5 valencia ensanche
5 valencia ensanche
 
Eventos más importantes de los festejos del 5 de Mayo
Eventos más importantes de los festejos del 5 de MayoEventos más importantes de los festejos del 5 de Mayo
Eventos más importantes de los festejos del 5 de Mayo
 
Palíndromo.ppt
 Palíndromo.ppt  Palíndromo.ppt
Palíndromo.ppt
 
La República Romana: consolidación y expansión.
La República Romana: consolidación y expansión.La República Romana: consolidación y expansión.
La República Romana: consolidación y expansión.
 
Orangutan
OrangutanOrangutan
Orangutan
 

Kürzlich hochgeladen

"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfRankYa
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024The Digital Insurer
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clashcharlottematthew16
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 

Kürzlich hochgeladen (20)

E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clash
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 

Exploratory search on topics through different perspectives with DBpedia

  • 1. Exploratory search on topics through different perspectives with DBpedia Nicolas Marie, Fabien Gandon, Alain Giboin, Émilie Palagi COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 2. CONTEXT PROPOSITION EVALUATION CONCLUSION 2 COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 3. CONTEXT PROPOSITION EVALUATION CONCLUSION 3 COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 4. Search is only a partially solved problem [White, 2009] Ambiguous queries, natural language queries, exploratory search tasks… COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 5. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub 10 blue links paradigm, simple, fast Exploratory search bottleneck
  • 6. Exploratory search systems are optimized to support exploratory search tasks, common functionalities: Overviews Faceted interfaces Results clustering Low-cost of browsing (going back-and-forth functionalities) Query-suggestions and refinement Serendipitous discoveries provocation In-session of account related memory features COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub
  • 7. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub Linked data are promising for supporting exploratory search: • new algorithms • new interaction models optimized for exploration.
  • 8. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub
  • 9. Discovery Hub Maturity COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 10. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 1 perspective
  • 11. I want to discover Claude Monet (painter)... In American culture COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub Topics are complex, multifaceted, One entity => multiple perspectives & knowledge nuances Entourage Art. movement In French culture Curiosities…
  • 12. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. MORE Aemoo
  • 13. CONTEXT PROPOSITION EVALUATION CONCLUSION 13 COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 14. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub The models and algorithms we propose unveil topic knowledge nuances by allowing the exploration of topics through several perspectives. In the graph context of linked data these perspectives correspond to different non exclusive sets of objects and relations that are informative on a topic regarding specific aspects. Flexible querying and data processing
  • 15. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 16. Building perspectives thanks to spreading activation …… Refer to the papers for the complete formalization COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 17. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 18. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 19. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 20. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 21. Discovery Hub 3 perspective-operations to expose knowledge nuances : • Criteria of interest specification • Controlled randomness injection • Data source selection COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 22. Discovery Hub Criteria of interest specification , dcterms:category, ?x , dcterms:category, ?x COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Classic similarity measure , dcterms:category, ?a | ?b | ?c |... , dcterms:category, ?a | ?b | ?c |... Criteria spec. similarity
  • 23. Discovery Hub Criteria of interest specification COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 24. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Classic – top 5 artists « French / not impressonist » criteria specification – top 5 artists « Not French / Impressonist » criteria specification – top 5 artists
  • 25. * r + (1-r)* Chosen level of randomness Randomness injection COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. * r + (1-r)* * r + (1-r)* * r + (1-r)* * r + (1-* r +
  • 26. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub Local Kgram instance Data source selection dbpedia.org/sparql de.dbpedia.org/sparql es.dbpedia.org/sparql fr.dbpedia.org/sparql it.dbpedia.org/sparql
  • 27. Discovery Hub Data source selection COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 28. CONTEXT PROPOSITION EVALUATION CONCLUSION 28 COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 29. Evaluated algorithm versions •Basis algorithm of Discovery Hub •Personalized algorithm through criteria specification •Randomized algorithm, with 0.5 threshold •Highly randomized algorithm (Highly R.), with 1.0 threshold COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub
  • 30. • Hypothesis 1: Users who specify their criteria of interest about a topic find the results of the search more relevant. • Hypothesis 2: Users who specify their criteria of interest about a topic do not find the results of the search less novel. • Hypothesis 3: The stronger is the level of randomness the more surprising the results are for the users. • Hypothesis 4: Even if the level of surprise is high, the majority of the top results are still relevant to the users. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub
  • 31. Discovery Hub 푃푒푟푠표푛푎푙푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > [퐵푎푠푖푠 ; 퐼푛푡푒푟푒푠푡] " ; 퐷푖푠푡푎푛푐푒 < [ " ; 퐷푖푠푡푎푛푐푒] 푃푒푟푠표푛푎푙푖푧푒푑 ; 푆푢푝푟푖푠푖푛푔 푅푒푠푢푙푡 > [퐵푎푠푖푠 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡] [ " ; Surprising Relation] > [ " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛] COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 퐻3 퐻1 퐻2 퐻푖푔ℎ푙푦 푅. ; 푆푢푝푟푖푠푖푛푔 푅푒푠푢푙푡 > 푅푎푛푑표푚푖푧푒푑 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡 > [퐵푎푠푖푠 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡] [ " ; Suprising Relation] > " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛 > [ " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛] (Highly R. : Highly Randomized) 퐻4 퐻푖푔ℎ푙푦 푅푎푛푑표푚푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > 퐴푣푒푟푎푔푒 (2,5) 푅푎푛푑표푚푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > 퐴푣푒푟푎푔푒 (2,5)
  • 32. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. A « good » result in ESS is… Our definitions Chosen metrics : Questions (Likert Scale) … A surprising result A result is surprising if : • You discovered an unknown resource or relation • You discovered something unexpected Surprising Result This result is suprising ? Surprising Relation This relation between the topic searched and the result is surprising ? … An intersting result A result is interesting if : • You think it is similar to the topic explored • You think you will remind or reuse it Interesting Result This result is interesting ? Distance between the Result and the topic searched This result is too distant from the topic searched ? Discovery Hub
  • 33. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub • 16 participants • Phase 1 : Selection of 2 topics in a list of 20 queries randomly choose in the query log of Discovery Hub - Information Visualization - Serge Gainsbourg (french singer) • Phase 2 : Specification of the categories of interest • Phase 3 : User Test (~1h) - Before the test - Interview (name, age, do they know Discovery Hub ?,…) - Presentation of Discovery Hub and the objective of the test - Presentation of the questions and simulation
  • 34. H1 : Users who specify their criteria of interest about a topic find the results of the search more relevant. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 퐻1 푃푒푟푠표푛푎푙푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > [퐵푎푠푖푠 ; 퐼푛푡푒푟푒푠푡] " ; 퐷푖푠푡푎푛푐푒 < [ " ; 퐷푖푠푡푎푛푐푒]
  • 35. H2: Users who specify their criteria of interest about a topic do not find the results of the search less novel COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 퐻2 푃푒푟푠표푛푎푙푖푧푒푑 ; 푆푢푝푟푖푠푖푛푔 푅푒푠푢푙푡 > [퐵푎푠푖푠 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡] [ " ; Surprising Relation] > [ " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛]
  • 36. H3: The stronger is the level of randomness the more surprising the results are for the users COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 퐻3 퐻푖푔ℎ푙푦 푅. ; 푆푢푝푟푖푠푖푛푔 푅푒푠푢푙푡 > 푅푎푛푑표푚푖푧푒푑 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡 > [퐵푎푠푖푠 ; 푆푢푟푝푟푖푠푖푛푔 푅푒푠푢푙푡] [ " ; Suprising Relation] > " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛 > [ " ; 푆푢푟푝푟푖푠푖푛푔 푅푒푙푎푡푖표푛] (Highly R. : Highly Randomized)
  • 37. H4: Even if the level of surprise is high, the majority of the top results are still relevant to the users COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. 퐻4 퐻푖푔ℎ푙푦 푅푎푛푑표푚푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > 퐴푣푒푟푎푔푒 (2,5) 푅푎푛푑표푚푖푧푒푑 ; 퐼푛푡푒푟푒푠푡 > 퐴푣푒푟푎푔푒 (2,5)
  • 38. CONTEXT PROPOSITION EVALUATION CONCLUSION 38 COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.
  • 39. COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub •We proposed a framework to enable multi-perspective exploratory search: - Formalization - Implementation - Evaluation • 3 operators : criteria spec., randomization, data selection • Evaluations globally positive, slight adjustements needed • Interesting propositions from the reviewers, thank you
  • 40. Thank you ! Questions ? http://semreco.inria.fr werarediscoveryhub@gmail.com COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Discovery Hub