40
COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. Exploratory search on topics through different perspectives with DBpedia Nicolas Marie, Fabien Gandon, Alain Giboin, Γ‰milie Palagi

Exploratory search on topics through different perspectives with DBpedia

Embed Size (px)

DESCRIPTION

Presentation at SEMANTICS2014: http://www.semantics.cc/www.semantics.cc/index.html Paper: Exploratory search on topics through different perspectives with DBpedia https://hal.inria.fr/hal-01057031 A promising scenario for combining linked data and search is exploratory search. During exploratory search, the search objective is ill-defined and favorable to discovery. A common limit of the existing linked data based exploratory search systems is that they constrain the exploration through single results selection and ranking schemes. The users can not influence the results to reveal specific aspects of knowledge that interest them. The models and algorithms we propose unveil such knowledge nuances by allowing the exploration of topics through several perspectives. The users adjust important computation parameters through three operations that help retrieving desired exploration perspectives: specification of interest criteria about the topic explored, controlled randomness injection to reveal unexpected knowledge and choice of the processed knowledge source(s). This paper describes the corresponding models, algorithms and the Discovery Hub implementation. It focuses on the three mentioned operations and presents their evaluations.

Citation preview

Page 1: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Exploratory search on topics through differentperspectives with DBpedia

Nicolas Marie, Fabien Gandon, Alain Giboin, Γ‰milie Palagi

Page 2: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

2

CONTEXTPROPOSITIONEVALUATIONCONCLUSION

Page 3: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

3

CONTEXTPROPOSITIONEVALUATIONCONCLUSION

Page 4: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Search is only a partially solved problem [White, 2009]Ambiguous queries, natural language queries, exploratory search tasks…

Page 5: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

10 blue links paradigm, simple, fast

Exploratory searchbottleneck

Discovery Hub

Page 6: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

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

Exploratory search systems are optimized to support exploratory search tasks, common functionalities:

Discovery Hub

Page 7: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Discovery Hub

Linked data are promising for supporting exploratory search: β€’ new algorithms β€’ new interaction models optimized for exploration.

Page 8: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Discovery Hub

Page 9: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

MaturityDiscovery Hub

Page 10: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

1 topic of interest => 1 entity => 1 results set to explore

1 perspective

Page 11: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Discovery HubTopics are complex, multifaceted,

One entity => multiple perspectives &knowledge nuances

Entourage Art. movement

Curiosities…In French culture

In American culture

I want to discover Claude Monet (painter)...

Page 12: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

MORE

Aemoo

Page 13: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

13

CONTEXTPROPOSITIONEVALUATIONCONCLUSION

Page 14: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Discovery Hub

The models and algorithms we proposeunveil 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

Page 15: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Page 16: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Refer to the papers for the complete formalization

Building perspectives thanks to spreading activation

……

Page 17: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Page 18: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Page 19: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Page 20: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Page 21: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Discovery Hub

3 perspective-operations to expose knowledge nuances :

β€’ Criteria of interest specificationβ€’ Controlled randomness injectionβ€’ Data source selection

Page 22: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Discovery Hub Criteria of interest specification

, dcterms:category, ?x

, dcterms:category, ?x

Classic similarity measure

, dcterms:category, ?a | ?b | ?c |...

, dcterms:category, ?a | ?b | ?c |...

Criteria spec. similarity

Page 23: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Discovery Hub Criteria of interest specification

Page 24: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Classic – top 5 artists

Β« French / not impressonist Β» criteria specification – top 5 artists

Β« Not French / Impressonist Β» criteria specification – top 5 artists

Page 25: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Chosen level of randomness

Randomness injection

* r + (1-r)*

* r + (1-r)*

* r + (1-r)*

* r + (1-r)*

* r + (1-r)*

* r + (1

Page 26: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Discovery Hub

Local Kgram instance

Data source selection

fr.dbpedia.org/sparql

it.dbpedia.org/sparql

de.dbpedia.org/sparql

es.dbpedia.org/sparql

dbpedia.org/sparql

Page 27: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Discovery HubData source selection

Page 28: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

28

CONTEXTPROPOSITIONEVALUATIONCONCLUSION

Page 29: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Evaluated algorithm versions

β€’Basis algorithm of Discovery Hub

β€’Personalized algorithm through criteria specification

β€’Randomized algorithm, with 0.5 threshold

β€’Highly randomized algorithm (Highly R.), with 1.0 threshold

Discovery Hub

Page 30: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

β€’ Hypothesis 1:

Users who specify their criteria of interest about a topic find the results of the search more relevant.

β€’ Hypothesis 2:

Users who specify their criteria of interest about a topic do not find the results of the search less novel.

β€’ Hypothesis 3:

The stronger is the level of randomness the more surprising the results are for the users.

β€’ Hypothesis 4:

Even if the level of surprise is high, the majority of the top results are still relevant to the users.

Discovery Hub

Page 31: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

𝐻3 π»π‘–π‘”β„Žπ‘™π‘¦ 𝑅. ; π‘†π‘’π‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” 𝑅𝑒𝑠𝑒𝑙𝑑 > π‘…π‘Žπ‘›π‘‘π‘œπ‘šπ‘–π‘§π‘’π‘‘ ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” 𝑅𝑒𝑠𝑒𝑙𝑑 > [π΅π‘Žπ‘ π‘–π‘  ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” 𝑅𝑒𝑠𝑒𝑙𝑑]

[ " ; Suprising Relation] > " ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” π‘…π‘’π‘™π‘Žπ‘‘π‘–π‘œπ‘› > [ " ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” π‘…π‘’π‘™π‘Žπ‘‘π‘–π‘œπ‘›]

𝐻2 π‘ƒπ‘’π‘Ÿπ‘ π‘œπ‘›π‘Žπ‘™π‘–π‘§π‘’π‘‘ ; π‘†π‘’π‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” 𝑅𝑒𝑠𝑒𝑙𝑑 > [π΅π‘Žπ‘ π‘–π‘  ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” 𝑅𝑒𝑠𝑒𝑙𝑑]

[ " ; Surprising Relation] > [ " ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” π‘…π‘’π‘™π‘Žπ‘‘π‘–π‘œπ‘›]

𝐻1 π‘ƒπ‘’π‘Ÿπ‘ π‘œπ‘›π‘Žπ‘™π‘–π‘§π‘’π‘‘ ; πΌπ‘›π‘‘π‘’π‘Ÿπ‘’π‘ π‘‘ > [π΅π‘Žπ‘ π‘–π‘  ; πΌπ‘›π‘‘π‘’π‘Ÿπ‘’π‘ π‘‘]

" ; π·π‘–π‘ π‘‘π‘Žπ‘›π‘π‘’ < [ " ; π·π‘–π‘ π‘‘π‘Žπ‘›π‘π‘’]

𝐻4 π»π‘–π‘”β„Žπ‘™π‘¦ π‘…π‘Žπ‘›π‘‘π‘œπ‘šπ‘–π‘§π‘’π‘‘ ; πΌπ‘›π‘‘π‘’π‘Ÿπ‘’π‘ π‘‘ > π΄π‘£π‘’π‘Ÿπ‘Žπ‘”π‘’ (2,5)

π‘…π‘Žπ‘›π‘‘π‘œπ‘šπ‘–π‘§π‘’π‘‘ ; πΌπ‘›π‘‘π‘’π‘Ÿπ‘’π‘ π‘‘ > π΄π‘£π‘’π‘Ÿπ‘Žπ‘”π‘’ (2,5)

(Highly R. : Highly Randomized)

Discovery Hub

Page 32: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

A Β« good Β»

result in

ESS is…

Our definitions Chosen metrics : Questions

(Likert Scale)

… A

surprising

result

A result is surprising if :

β€’ You discovered an

unknown resource or

relation

β€’ 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 :

β€’ You think it is similar to

the topic explored

β€’ 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

Page 33: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

β€’ 16 participants

β€’ 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)

β€’ Phase 2 : Specification of the categories of interest

β€’ 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

Discovery Hub

Page 34: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

𝐻1 π‘ƒπ‘’π‘Ÿπ‘ π‘œπ‘›π‘Žπ‘™π‘–π‘§π‘’π‘‘ ; πΌπ‘›π‘‘π‘’π‘Ÿπ‘’π‘ π‘‘ > [π΅π‘Žπ‘ π‘–π‘  ; πΌπ‘›π‘‘π‘’π‘Ÿπ‘’π‘ π‘‘]

" ; π·π‘–π‘ π‘‘π‘Žπ‘›π‘π‘’ < [ " ; π·π‘–π‘ π‘‘π‘Žπ‘›π‘π‘’]

H1 : Users who specify their criteria of interest about a topic find the results of the search more relevant.

Page 35: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

𝐻2 π‘ƒπ‘’π‘Ÿπ‘ π‘œπ‘›π‘Žπ‘™π‘–π‘§π‘’π‘‘ ; π‘†π‘’π‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” 𝑅𝑒𝑠𝑒𝑙𝑑 > [π΅π‘Žπ‘ π‘–π‘  ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” 𝑅𝑒𝑠𝑒𝑙𝑑]

[ " ; Surprising Relation] > [ " ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” π‘…π‘’π‘™π‘Žπ‘‘π‘–π‘œπ‘›]

H2: Users who specify their criteria of interest about a topic do not find the results of the search less novel

Page 36: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

𝐻3 π»π‘–π‘”β„Žπ‘™π‘¦ 𝑅. ; π‘†π‘’π‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” 𝑅𝑒𝑠𝑒𝑙𝑑 > π‘…π‘Žπ‘›π‘‘π‘œπ‘šπ‘–π‘§π‘’π‘‘ ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” 𝑅𝑒𝑠𝑒𝑙𝑑 > [π΅π‘Žπ‘ π‘–π‘  ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” 𝑅𝑒𝑠𝑒𝑙𝑑]

[ " ; Suprising Relation] > " ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” π‘…π‘’π‘™π‘Žπ‘‘π‘–π‘œπ‘› > [ " ; π‘†π‘’π‘Ÿπ‘π‘Ÿπ‘–π‘ π‘–π‘›π‘” π‘…π‘’π‘™π‘Žπ‘‘π‘–π‘œπ‘›]

(Highly R. : Highly Randomized)

H3: The stronger is the level of randomness the more surprising the results are for the users

Page 37: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

𝐻4 π»π‘–π‘”β„Žπ‘™π‘¦ π‘…π‘Žπ‘›π‘‘π‘œπ‘šπ‘–π‘§π‘’π‘‘ ; πΌπ‘›π‘‘π‘’π‘Ÿπ‘’π‘ π‘‘ > π΄π‘£π‘’π‘Ÿπ‘Žπ‘”π‘’ (2,5)

π‘…π‘Žπ‘›π‘‘π‘œπ‘šπ‘–π‘§π‘’π‘‘ ; πΌπ‘›π‘‘π‘’π‘Ÿπ‘’π‘ π‘‘ > π΄π‘£π‘’π‘Ÿπ‘Žπ‘”π‘’ (2,5)

H4: Even if the level of surprise is high, the majority of the top results are still relevant to the users

Page 38: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

38

CONTEXTPROPOSITIONEVALUATIONCONCLUSION

Page 39: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

Discovery Hub

β€’ We proposed a framework to enable multi-perspective exploratory search:

- Formalization

- Implementation

- Evaluation

β€’ 3 operators : criteria spec., randomization, data selection

β€’ Evaluations globally positive, slight adjustements needed

β€’ Interesting propositions from the reviewers, thank you

Page 40: Exploratory search on topics through different perspectives with DBpedia

COPYRIGHT Β© 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED.

http://semreco.inria.fr

[email protected]

Thank you ! Questions ?

Discovery Hub