crowdq: crowdsourced(query(understanding((...user keyword query on#line'complex'query...
TRANSCRIPT
![Page 1: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/1.jpg)
CrowdQ: Crowdsourced Query Understanding
Gianluca Demar8ni, Beth Trushkowsky, Tim Kraska, Michael J. Franklin
![Page 2: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/2.jpg)
Scenario
Find the birthdate of the mayor of the capital city of France
Gianluca Demar8ni 2
![Page 3: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/3.jpg)
Gianluca Demar8ni 3
![Page 4: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/4.jpg)
Gianluca Demar8ni 4
![Page 5: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/5.jpg)
Gianluca Demar8ni 5
![Page 6: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/6.jpg)
Gianluca Demar8ni 6
![Page 7: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/7.jpg)
Mo8va8on
• Web Search Engines can answer simple factual queries directly on the result page
• Users with complex informa8on needs are oQen unsa8sfied
• Purely automa8c techniques are not enough
• We want to solve it with Crowdsourcing!
Gianluca Demar8ni 7
![Page 8: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/8.jpg)
Background
• Crowdsourcing so far used for data processing – DB/SemWeb: Data integra8on and cleaning – IR: Relevance judgments
We use the crowd to understand the query
Gianluca Demar8ni 8
![Page 9: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/9.jpg)
CrowdQ
• CrowdQ is the first system that uses crowdsourcing to – Understand the intended meaning
– Build a structured query template – Answer the query over Linked Open Data
Gianluca Demar8ni 9
![Page 10: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/10.jpg)
Gianluca Demar8ni 10
![Page 11: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/11.jpg)
User
Keyword QueryOn#line'Complex'Query
ProcessingComplex
query classifier
CrowdsourcingPlatform
Vetrical selection,
Unstructured Search, ...
POS + NER tagging
Query Template Index
Crowd Manager
N
Y
Queries Templ +Answer Types
StructuredLOD Search
Result Joiner
Template Generation
SERP
t1t2t3
Off#line'Complex'QueryDecomposition
Structured Query
Query Logquery
N
Answ
erCo
mpo
sitio
n
LOD Open Data Cloud
Match with existingquery templates
CrowdQ Architecture
Gianluca Demar8ni 11
Off-‐line: query template genera8on with the help of the crowd On-‐line: query template matching using NLP and search over open data
![Page 12: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/12.jpg)
Hybrid Human-‐Machine Pipeline
Gianluca Demar8ni 12
Q= birthdate of actors of forrest gump
Query annota8on Noun Noun Named en8ty
Verifica8on
En8ty Rela8ons
Is forrest gump this en8ty in the query?
Which is the rela8on between: actors and forrest gump starring
Schema element Starring <dbpedia-‐owl:starring>
Verifica8on Is the rela8on between: Indiana Jones – Harrison Ford Back to the Future – Michael J. Fox of the same type as Forrest Gump -‐ actors
![Page 13: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/13.jpg)
Structured query genera8on
SELECT ?y ?x WHERE { ?y <dbpedia-‐owl:birthdate> ?x .
?z <dbpedia-‐owl:starring> ?y .
?z <rdfs:label> ‘Forrest Gump’ }
Gianluca Demar8ni 13
Results from BTC09:
Q= birthdate of actors of forrest gump MOVIE
MOVIE
![Page 14: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/14.jpg)
Current Status
• Realize the vision • Running demo: – Daniel Haas, Daniel Bruckner, Jonathan Harper
• Next Steps – Evalua8on of Crowd effec8veness at each step – Comparison hybrid vs machine pipeline
Gianluca Demar8ni 14
![Page 15: CrowdQ: Crowdsourced(Query(Understanding((...User Keyword Query On#line'Complex'Query Processing Complex query classifier Crowdsourcing Platform Vetrical selection, Unstructured Search,](https://reader034.vdocuments.mx/reader034/viewer/2022042023/5e7acb9e64e6923dbd7fc449/html5/thumbnails/15.jpg)
Conclusions
• CrowdQ: an hybrid approach to complex query understanding
• Combines techniques from DB, NLP, IR, Data Mining, and Human Intelligence
• Ini8al experiments show the poten8al of CrowdQ
Gianluca Demar8ni 15