SlideShare una empresa de Scribd logo
1 de 79
Descargar para leer sin conexión
ON ENTITIES AND EVALUATION
Krisztian Balog
University of Stavanger

@krisztianbalog
Keynote given at the 41st European Conference on Informa<on Retrieval (ECIR '19) | Cologne, Germany, April 2019
SPECIAL THANKS TO
• My former PhD advisor:
• Maarten de Rijke
• My former and current PhD students:
• Jan R. Benetka, Richard Berendsen, Marc Bron, Heng Ding,
Darío Garigliotti, Faegheh Hasibi, Trond Linjordet, Robert
Neumayer, Shuo Zhang
• Collaborators on material presented in this talk:
• Po-Yu Chuang, Peter Dekker, Maarten de Rijke, Kristian
Gingstad, Rolf Jagerman, Øyvind Jekteberg, Liadh Kelly, Tom
Kenter, Phillip Schaer, Anne Schuth, Narges Tavakolpoursaleh
Part I
ON ENTITIES
OUTLINE FOR PART I
• What is an entity? 

• Why care about entities? 

• What research has been done on entities in IR? 

• What’s next?
WHAT IS AN ENTITY?
An entity is an object or thing that can be uniquely identified.
entity catalog entity ID*
name(s)*
AN ENTITY
<dbr:Roger_Needham>
<dbo:Scientist>
<dbo:Person>
<dbo:Agent>
<owl:Thing>
<rdf:type>
<dbo:abstract>
"1935-08-26"
"Karen Spärck Jones"
<foaf:name>
<dbo:spouse>
<University_of_Cambridge>
<dbp:almaMater>
<dbr:Natural_language_processing>
<dbo:knownFor>
<dbc:Information_retrieval_researchers>
<dct:subject>
<dbc:British_women_computer_scientists>
<dbc:British_computer_scientists> <dbc:British_women_scientists>
"Karen Spärck Jones FBA (26 August
1935 – 4 April 2007) was a British
computer scientist."
<dbr:Karen_Spark_Jones>
<dbo:birthDate>
WHAT IS AN ENTITY?
An entity is a uniquely identifiable object or thing,
characterized by its name(s), type(s), attributes, and
relationships to other entities.
REPRESENTING ENTITIES 

AND THEIR PROPERTIES
entity catalog entity ID*
name(s)*
knowledge repository type(s)*
descriptions
relationships (non-typed links)
REPRESENTING ENTITIES 

AND THEIR PROPERTIES
entity catalog entity ID*
name(s)*
knowledge repository type(s)*
descriptions
relationships (non-typed links)
knowledge base (KB) /

knowledge graph (KG)
attributes
relationships (typed links)
WHY CARE ABOUT ENTITIES?
• From a user perspective, entities ...
• are natural units for organizing
information
• enable a richer and more effective
user experience
WHY CARE ABOUT ENTITIES?
• From a machine perspective, entities ...
• allow for a better understanding of queries,
document content, and of users
• enable search engines to be more
intelligent
Michael Schumacher (born 3 January 1969) is a German retired racing driver. He
is a seven-time Formula One World Champion and is widely regarded as one of
the greatest Formula One drivers of all time. He won two titles with Benetton in
1994 and 1995 before moving to Ferrari where he drove for eleven years. His
time with Ferrari yielded five consecutive titles between 2000 and 2004.
Michael Schumacher
Schuderia Ferrari
Benetton Formula
Racing driver
Formula One constructor
Formula One constructor
Formula One
Auto racing series
Part I En88es
RESEARCH ON ENTITIES IN IR
TRENDS IN THE IR LITERATURE
0
10
20
30
40
2000 2002 2004 2006 2008 2010 2012 2014 2016
entity OR entities Wikipedia
knowledge base knowledge graph
Numbers are based on boolean queries on paper titles from SIGIR, ECIR, CIKM, WSDM, and WWW
TRENDS IN THE IR LITERATURE
Numbers are based on boolean queries on paper titles from SIGIR, ECIR, CIKM, WSDM, and WWW
0
10
20
30
40
2000 2002 2004 2006 2008 2010 2012 2014 2016
entity OR entities
Wikipedia OR "knowledge base" OR "knowledge graph"
#1 ENTITIES AS THE UNIT OF RETRIEVAL
• A significant portion of queries mention or target entities
• Those queries are better answered with a ranked list of
entities (as opposed to a list of documents)
• Term-based entity representations can be effectively
ranked using document-based retrieval models
• Semantically informed retrieval models utilize entity-
specific properties (attributes, types, and relationships)
#2 ENTITIES FOR KNOWLEDGE
REPRESENTATION
• Entities help to bridge the gap between unstructured and
structured data
<entity>
<entity>
Entity linking
Knowledge base
population
#3 ENTITIES FOR AN ENHANCED
SEARCH EXPERIENCE
• Improve the search experience through the entire search
process
• Understanding search queries
• Improving document retrieval performance
• Query assistance services (auto-completion, suggestions)
• Entity recommendations
WANT TO KNOW MORE?
www.eos-book.org
OUTLINE FOR PART I
• What is an entity? 

• Why care about entities? 

• What research has been done on entities in IR? 

• What’s next?
SCENARIO #1
I would like to get some new strings
for my guitar
AIOK, would that be your electric guitar or
the acoustic one?
The electric one.
AIAlright. I can repeat your Amazon order of
3 months ago, or you can go by a music
store on Elm street on the way to your
dentist appointment this afternoon.
TRULY PERSONAL AI 

IS NOT POSSIBLE WITHOUT A
PERSONAL KNOWLEDGE GRAPH
PERSONAL KNOWLEDGE GRAPHS
A personal knowledge graph (PKG) is a source of
structured knowledge about entities and the relation
between them, where the entities and the relations
between them are of personal, rather than general,
importance.
PERSONAL KNOWLEDGE GRAPHS
User
Hometown
Mom
Social network
Jamie
High schoolGeneral
-purpose KG
Electric guitar
E-commerce
catalog
Mom’s dentist
Domain-specific KG
Acoustic guitar
Personal
Knowledge Graph
Part I En88es
A RESEARCH AGENDA 

FOR PERSONAL KNOWLEDGE GRAPHS
Part I En88es
#1 KNOWLEDGE REPRESENTATION
• Task: representing entities and their properties
• KGs are organized according to a knowledge model (schema)
• Peculiarities/challenges:
• Entities need to be (directly/indirectly) connected to the user
• Not duplicating attributes, focusing on what is personal
• Information about entities can be very sparse
• Some entities may not have any digital presence
• Strong temporality (relations can be ephemeral)
#1 KNOWLEDGE REPRESENTATION
• Task: representing entities and their properties
• KGs are organized according to a knowledge model (schema)
• Peculiarities/challenges:
• Entities need to be (directly/indirectly) connected to the user
• Not duplicating attributes, focusing on what is personal
• Information about entities can be very sparse
• Some entities may not have any digital presence
• Strong temporality (relations can be ephemeral)
What is the best way of representing entities and their
properties and relations, considering the vast but
sparse set of possible predicates?
RQ1
#2 SEMANTIC ANNOTATION OF TEXT
• Task: annotating text with respect to a knowledge
repository (commonly known as entity linking)
• Usually involves mention detection, entity disambiguation,
and NIL-detection steps
• Challenges
• Entities might have little to no digital presence
• Entities are not necessarily proper nouns
• Linking, NIL-detection, and KG population are intertwined
#2 SEMANTIC ANNOTATION OF TEXT
• Task: annotating text with respect to a knowledge
repository (commonly known as entity linking)
• Usually involves mention detection, entity disambiguation,
and NIL-detection steps
• Challenges
• Entities might have little to no digital presence
• Entities are not necessarily proper nouns
• Linking, NIL-detection, and KG population are intertwined
How can entity linking be performed against a
personal knowledge graph, where structured entity
information to rely on is potentially absent?
RQ2a
When should entity linking be performed against a
personal knowledge graph as opposed to a general-
purpose KG?
RQ2b
SCENARIO #2
I need to see a dentist. Mom recommended
hers at dinner yesterday.
AII can try to help you find this person. Do
you have any more information?
I reckon that him and Mom graduated from
the same high school the same year.
AIOK, that's enough to narrow it down. 

It must be Dr. John Pullman.
That must be him. I remember he had a fitting
name. Can you try make an appointment for
Thursday afternoon?
#3 POPULATION AND MAINTENANCE
• Task: extending a KG from external sources (KB
acceleration/population) or via internal inferencing
• Verification of facts in the KG
• Challenges:
• Single curator; more automation is desired than for KGs, but
the user should still be in control
• The first mention of an entity should trigger population
• Properties may be inferred from the context
#3 POPULATION AND MAINTENANCE
• Task: extending a KG from external sources (KB
acceleration/population) or via internal inferencing
• Verification of facts in the KG
• Challenges:
• Single curator; more automation is desired than for KGs, but
the user should still be in control
• The first mention of an entity should trigger population
• Properties may be inferred from the context
How can personal knowledge graphs be automatically
populated and reliably maintained?
RQ3
SCENARIO #3
AISince you're running a half marathon at
Hackney in May, may I suggest you
undertake a 10k run this weekend?
Yes, that sounds like a good idea. Any
suggestions for a not too popular route 

that I haven't done before?
AISure thing. I'll upload some routes to the
running app on your phone.
Cheers mate!
#4 QUERYING
• Task: Retrieving information (entities, types, relations, etc.)
from the PKG or from KGs with the help of the PKG
• Challenges:
• Sparsity of data
• Soft, subjective constraints
#4 QUERYING
• Task: Retrieving information (entities, types, relations, etc.)
from the PKG or from KGs with the help of the PKG
• Challenges:
• Sparsity of data
• Soft, subjective constraints
How to leverage the semantically rich but sparse
information in personal knowledge graphs for
answering natural language queries?
RQ4
#5 INTEGRATION WITH EXTERNAL
SOURCES
• Task: recognizing the same entity across multiple data
sources (a.k.a. object resolution, record linkage, ...)
• Challenges:
• One-to-many, as opposed to one-to-one linkage
• Continuous process, not a one-off effort
• Two-way synchronization would be desired
• Conflicting facts or relations need resolving by the user
#5 INTEGRATION WITH EXTERNAL
SOURCES
• Task: recognizing the same entity across multiple data
sources (a.k.a. object resolution, record linkage, ...)
• Challenges:
• One-to-many, as opposed to one-to-one linkage
• Continuous process, not a one-off effort
• Two-way synchronization would be desired
• Conflicting facts or relations need resolving by the user
How to provide continuous two-way integration with
external knowledge sources with the user in the loop?
RQ5
RESEARCH QUESTIONS 

FOR PERSONAL KNOWLEDGE GRAPHS
• What is the best way of representing entities and their properties
and relations, considering the vast but sparse set of possible
predicates?
• How can entity linking be performed against a personal knowledge
graph, where structured entity information to rely on is potentially
absent?
• How can personal knowledge graphs be automatically populated and
reliably maintained?
• How to leverage the semantically rich but sparse information in
personal knowledge graphs for answering natural language queries?
• How to provide continuous two-way integration with external
knowledge sources with the user in the loop?
THERE IS MORE...
• Implementation
• Where is it stored (on the device, cloud, etc.)?
• How can security and privacy be ensured?
• How to interact with a range of services with proper access
control?
• Evaluation
• How to build reusable test resources?
SUMMARY OF PART I
• Progress on entity-oriented search was enabled by large
open knowledge repositories
• Personal AI is not possible without the concept of a
personal knowledge graph
• Many interesting research opportunities are available
Part II
ON EVALUATION
OUTLINE FOR PART II
• Online evaluation and why we need it

• Living labs: methodology and lessons learned

• What's next?
EVALUATION METHODOLOGIES
• Offline evaluation ("TREC-style" studies)
• Online evaluation
• Lab-based studies
• Simulation of users
• ...
ONLINE EVALUATION 101
• See how regular users interact with a retrieval system
when just using it
• Observe implicit behavior
• Clicks, skips, saves, forwards, bookmarks, likes, etc.
• Try to infer differences in behavior from different flavors of
the live system
• A/B testing, interleaving
• Run statistical tests to confirm the difference is not due to
chance
CHALLENGES IN ONLINE EVALUATION
• It's a live service
• Complexity of modern SERPs
• Data is noisy
• There’s no “ground truth”
OFFLINE VS. ONLINE EVALUATION
Offline Online
Basic assumption Assessors tell you what is relevant
Observable user behavior can tell
you what is relevant
Quality Data is only as good as the guidelines
Real user data, real and
representative information needs
Realisticity
Simplified scenario, cannot go
beyond a certain level of complexity
Perfectly realistic setting (users are
not aware that they are guniea pigs)
Assessment cost Expensive Cheap
Scalability Doesn't scale Scales very well
Repeatability Repeatable Not repeatable
Throughput High Low
Risk None High
THE COMMUNITY NEEDS 

OPEN RESEARCH PLATFORMS
FOR ONLINE EVALUATION
LIVING LABS
Living labs is a new evaluation paradigm for IR,
where the experimentation platform is an existing
search engine. Researchers have the opportunity to
replace components of this search engine and
evaluate these components using interactions with
real, "unsuspecting" users of this search engine.
OVERVIEW
experimental
systems
users live site
?
organizaOon
ALL WE NEED IS A SITE:
LET'S TAKE AN EXISTING ONE
KEY IDEAS FOR OPERATIONALIZATION
• An API orchestrates all the data exchange between sites
(live search engines) and participants
• Focus on frequent (head) queries
• Enough traffic on them for experimentation
• Participants generate rankings offline and upload these
to the API
• Eliminates real-time requirement
• Freedom in choice of tools and environment
K. Balog, L. Kelly, andA. Schuth.Head First: Living Labs for Ad-hoc Search Evalua<on. CIKM'14
OVERVIEW
experimental
systems
users live site
API
K. Balog, L. Kelly, andA. Schuth.Head First: Living Labs for Ad-hoc Search Evalua<on. CIKM'14
METHODOLOGY (1)
experimental
system
users live site
API
• Sites make queries, candidate documents (items),
historical search and click data available through
the API
METHODOLOGY (2)
experimental
system
users live site
API
• Rankings are generated (offline) for each query and
uploaded to the API
METHODOLOGY (3)
experimental
system
API
• When any of the test queries is fired on the live
site, it requests an experimental ranking from the
API and interleaves it with that of the producOon
system
query
interleaved
ranking
query
experimental
ranking
METHODOLOGY (3)
experimental
system
API
• When any of the test queries is fired on the live
site, it requests an experimental ranking from the
API and interleaves it with that of the producOon
system
query
interleaved
ranking
query
experimental
ranking
doc 1
doc 2
doc 3
doc 4
doc 5
doc 2
doc 4
doc 7
doc 1
doc 3
system A system B
doc 1
doc 2
doc 4
doc 3
doc 7
interleaved list
METHODOLOGY (4)
• ParOcipants get detailed feedback on user
interacOons (clicks)
experimental
system
users live site
API
METHODOLOGY (5)
• Evaluation measure:
• where the number of “wins” and “losses” is against
the production system, aggregated over a period
of time
• An Outcome of > 0.5 means beating the production
system
Outcome =
#Wins
#Wins + #Losses
LIMITATIONS
• Head queries only: Considerable portion of traffic, but
only popular info needs
• Lack of context: No knowledge of the searcher’s location,
previous searches, etc.
• No real-time feedback: API provides detailed feedback,
but it’s not immediate
• Limited control: Experimentation is limited to single
searches, where results are interleaved with those of the
production system; no control over the entire result list
EVALUATION CAMPAIGNS
Part II Evalua8on
EVALUATION CAMPAIGNS
Product search
(Hungarian toy store)
Product search
(Hungarian toy store)
Academic search
(CiteSeerX, SSOAR,
Microsoft Academic)
Academic search
(CiteSeerX, SSOAR)
Web search (Czech
web search engine)
OS‘16 OS‘17
TREC OPENSEARCH
• Sites: academic search engines
• Task: ad hoc scientific literature search
• Multiple evaluation rounds (6 weeks each)
• Train/test queries
• Training queries: feedback on individual impressions
• Test queries: only aggregated feedback at the end of the
evaluation period
CITESEERX @TREC-OS 2016
Round 1 Round 2 Round 3
Impressions 359 571 4829
Clicks 144 128 651
ery
0
100
200
300
Numberofimpressions
2016 Round 1 - CiteSeerX
ery
0
100
200
300
400
Numberofimpressions
2016 Round 2 - CiteSeerX
ery
0
200
400
600
Numberofimpressions
2016 Round 3 - CiteSeerX
ery
0
5
10
15
Numberofclicks
2016 Round 1 - CiteSeerX
ery
0
5
10
15
20
Numberofclicks
2016 Round 2 - CiteSeerX
ery
0
5
10
15
20
Numberofclicks
2016 Round 3 - CiteSeerX
EVALUATION RESULTS

CITESEERX, TREC-OS 2016, ROUND #3
Wins Ties Losses Outcome p-value
System 1 48 15 39 0.5517 0.3912
System 2 27 11 22 0.5510 0.5682
System 3 35 14 32 0.5224 0.8072
...
We would need to gather data for about six months for p  0.05 and
for about a year for p  0.01 (assuming a similar win/loss ratio).
LESSONS LEARNED
• Head first idea is feasible
• Running multiple campaigns without major technical hurdles
• Low traffic/click volume is an issue
• No statistically significant differences observed
• Possible remedy is to use more queries (tap into the long tail)
• Main challenges are more of an organizational than of a
technical nature
• Nontrivial infrastructure development on the service providers’ side
• Convincing large industrial partners as sites
• Attracting a large and active set of participants
R. Jagerman, K. Balog, and M. de Rijke.OpenSearch: Lessons Learned from an Online Evaluaon Campaign. Journal of
Data and Informaon Quality, 2018.
ALL WE NEED IS A SITE:
LET'S BUILD ONE
A SUCCESS STORY
Part II Evalua8on
run by GroupLens, a
research lab at the
University of Minnesota
OFFLINE DATASETS
• MovieLens-20M
• 20M item ratings
• 27K movies
• 138K users
• 465K tags
• links to YouTube trailers for 25K movies
ONLINE EXPERIMENTATION WITH 

NOVEL USER INTERFACES
PUBLICATIONS
BUILDING A SERVICE FOR
SCIENTIFIC LITERATURE
RECOMMENDATION
Part II Evalua8on
ARXIVDIGEST: THE SERVICE
• Recommendation service to help keep up with scientific
literature published on arxiv.org
• Users sign up and indicate their interests by providing
keywords, Google Scholar/DBLP profile, etc.
• Users receive recommendations regularly in a digest email
• Articles can be liked
• Users agree that their profile, the articles recommended to
them, and their feedback would be made available to
experimental systems
ARXIVDIGEST: THE EVALUATION
PLATFORM
• Broker-based architecture
• RESTful API for accessing article and user data and for
uploading recommendations
• Participating teams are given a window each day to
download new content and to generate
recommendations for all users
• Users receive interleaved rankings
• Performance is monitored continuously over time
CURRENT STATUS AND
OPPORTUNITIES
• All components of the broker in place
• https://github.com/iai-group/ArXivDigest
• Ensuring GDPR-compliance is in progress
• Opportunities for studying
• Personalized recommender algorithms
• Explainable recommendations
• Interleaving
• ...
Fork
m
e
on
G
itH
ub
SUMMARY OF PART II
• The community needs open online evaluation platforms
• Lessons learned from previous evaluation benchmarks
• Proposal: develop a service that we'd use ourselves
TAKE-HOME MESSAGES
• A truly personal AI is not possible without a personal
knowledge graph
• The community needs open research platforms for online
evaluation
THANK YOU!

Más contenido relacionado

La actualidad más candente

Towards Linked Ontologies and Data on the Semantic Web
Towards Linked Ontologies and Data on the Semantic WebTowards Linked Ontologies and Data on the Semantic Web
Towards Linked Ontologies and Data on the Semantic WebJie Bao
 
Rdf Overview Presentation
Rdf Overview PresentationRdf Overview Presentation
Rdf Overview PresentationKen Varnum
 
ESWC2015 opening ceremony
ESWC2015 opening ceremonyESWC2015 opening ceremony
ESWC2015 opening ceremonyFabien Gandon
 
Introduction To RDF and RDFS
Introduction To RDF and RDFSIntroduction To RDF and RDFS
Introduction To RDF and RDFSNilesh Wagmare
 
From the Semantic Web to the Web of Data: ten years of linking up
From the Semantic Web to the Web of Data: ten years of linking upFrom the Semantic Web to the Web of Data: ten years of linking up
From the Semantic Web to the Web of Data: ten years of linking upDavide Palmisano
 
Natural Language Search with Knowledge Graphs (Chicago Meetup)
Natural Language Search with Knowledge Graphs (Chicago Meetup)Natural Language Search with Knowledge Graphs (Chicago Meetup)
Natural Language Search with Knowledge Graphs (Chicago Meetup)Trey Grainger
 
Knowledge extraction in Web media: at the frontier of NLP, Machine Learning a...
Knowledge extraction in Web media: at the frontier of NLP, Machine Learning a...Knowledge extraction in Web media: at the frontier of NLP, Machine Learning a...
Knowledge extraction in Web media: at the frontier of NLP, Machine Learning a...Julien PLU
 
Semantic Web Foundations for Representing, Reasoning, and Traversing Contextu...
Semantic Web Foundations for Representing, Reasoning, and Traversing Contextu...Semantic Web Foundations for Representing, Reasoning, and Traversing Contextu...
Semantic Web Foundations for Representing, Reasoning, and Traversing Contextu...Artificial Intelligence Institute at UofSC
 
The Art of Social Media Analysis with Twitter & Python-OSCON 2012
The Art of Social Media Analysis with Twitter & Python-OSCON 2012The Art of Social Media Analysis with Twitter & Python-OSCON 2012
The Art of Social Media Analysis with Twitter & Python-OSCON 2012OSCON Byrum
 
SPARTIQULATION - Verbalizing SPARQL queries
SPARTIQULATION - Verbalizing SPARQL queriesSPARTIQULATION - Verbalizing SPARQL queries
SPARTIQULATION - Verbalizing SPARQL queriesBasil Ell
 
Natural Language Search with Knowledge Graphs (Activate 2019)
Natural Language Search with Knowledge Graphs (Activate 2019)Natural Language Search with Knowledge Graphs (Activate 2019)
Natural Language Search with Knowledge Graphs (Activate 2019)Trey Grainger
 
OWL-XML-Summer-School-09
OWL-XML-Summer-School-09OWL-XML-Summer-School-09
OWL-XML-Summer-School-09Duncan Hull
 
Web open standards for linked data and knowledge graphs as enablers of EU dig...
Web open standards for linked data and knowledge graphs as enablers of EU dig...Web open standards for linked data and knowledge graphs as enablers of EU dig...
Web open standards for linked data and knowledge graphs as enablers of EU dig...Fabien Gandon
 
Reflected Intelligence: Real world AI in Digital Transformation
Reflected Intelligence: Real world AI in Digital TransformationReflected Intelligence: Real world AI in Digital Transformation
Reflected Intelligence: Real world AI in Digital TransformationTrey Grainger
 
Two graph data models : RDF and Property Graphs
Two graph data models : RDF and Property GraphsTwo graph data models : RDF and Property Graphs
Two graph data models : RDF and Property Graphsandyseaborne
 
An introduction to Semantic Web and Linked Data
An introduction to Semantic Web and Linked DataAn introduction to Semantic Web and Linked Data
An introduction to Semantic Web and Linked DataFabien Gandon
 

La actualidad más candente (20)

Rdf
RdfRdf
Rdf
 
Towards Linked Ontologies and Data on the Semantic Web
Towards Linked Ontologies and Data on the Semantic WebTowards Linked Ontologies and Data on the Semantic Web
Towards Linked Ontologies and Data on the Semantic Web
 
Data in RDF
Data in RDFData in RDF
Data in RDF
 
Rdf Overview Presentation
Rdf Overview PresentationRdf Overview Presentation
Rdf Overview Presentation
 
ESWC2015 opening ceremony
ESWC2015 opening ceremonyESWC2015 opening ceremony
ESWC2015 opening ceremony
 
Introduction To RDF and RDFS
Introduction To RDF and RDFSIntroduction To RDF and RDFS
Introduction To RDF and RDFS
 
From the Semantic Web to the Web of Data: ten years of linking up
From the Semantic Web to the Web of Data: ten years of linking upFrom the Semantic Web to the Web of Data: ten years of linking up
From the Semantic Web to the Web of Data: ten years of linking up
 
Natural Language Search with Knowledge Graphs (Chicago Meetup)
Natural Language Search with Knowledge Graphs (Chicago Meetup)Natural Language Search with Knowledge Graphs (Chicago Meetup)
Natural Language Search with Knowledge Graphs (Chicago Meetup)
 
Knowledge extraction in Web media: at the frontier of NLP, Machine Learning a...
Knowledge extraction in Web media: at the frontier of NLP, Machine Learning a...Knowledge extraction in Web media: at the frontier of NLP, Machine Learning a...
Knowledge extraction in Web media: at the frontier of NLP, Machine Learning a...
 
Semantic Web Foundations for Representing, Reasoning, and Traversing Contextu...
Semantic Web Foundations for Representing, Reasoning, and Traversing Contextu...Semantic Web Foundations for Representing, Reasoning, and Traversing Contextu...
Semantic Web Foundations for Representing, Reasoning, and Traversing Contextu...
 
Ist16-04 An introduction to RDF
Ist16-04 An introduction to RDF Ist16-04 An introduction to RDF
Ist16-04 An introduction to RDF
 
The Art of Social Media Analysis with Twitter & Python-OSCON 2012
The Art of Social Media Analysis with Twitter & Python-OSCON 2012The Art of Social Media Analysis with Twitter & Python-OSCON 2012
The Art of Social Media Analysis with Twitter & Python-OSCON 2012
 
SPARTIQULATION - Verbalizing SPARQL queries
SPARTIQULATION - Verbalizing SPARQL queriesSPARTIQULATION - Verbalizing SPARQL queries
SPARTIQULATION - Verbalizing SPARQL queries
 
Natural Language Search with Knowledge Graphs (Activate 2019)
Natural Language Search with Knowledge Graphs (Activate 2019)Natural Language Search with Knowledge Graphs (Activate 2019)
Natural Language Search with Knowledge Graphs (Activate 2019)
 
GraphDB
GraphDBGraphDB
GraphDB
 
OWL-XML-Summer-School-09
OWL-XML-Summer-School-09OWL-XML-Summer-School-09
OWL-XML-Summer-School-09
 
Web open standards for linked data and knowledge graphs as enablers of EU dig...
Web open standards for linked data and knowledge graphs as enablers of EU dig...Web open standards for linked data and knowledge graphs as enablers of EU dig...
Web open standards for linked data and knowledge graphs as enablers of EU dig...
 
Reflected Intelligence: Real world AI in Digital Transformation
Reflected Intelligence: Real world AI in Digital TransformationReflected Intelligence: Real world AI in Digital Transformation
Reflected Intelligence: Real world AI in Digital Transformation
 
Two graph data models : RDF and Property Graphs
Two graph data models : RDF and Property GraphsTwo graph data models : RDF and Property Graphs
Two graph data models : RDF and Property Graphs
 
An introduction to Semantic Web and Linked Data
An introduction to Semantic Web and Linked DataAn introduction to Semantic Web and Linked Data
An introduction to Semantic Web and Linked Data
 

Similar a On Entities and Evaluation

ADV Slides: Graph Databases on the Edge
ADV Slides: Graph Databases on the EdgeADV Slides: Graph Databases on the Edge
ADV Slides: Graph Databases on the EdgeDATAVERSITY
 
Immersive Recommendation
Immersive RecommendationImmersive Recommendation
Immersive Recommendation承剛 謝
 
Human computation, crowdsourcing and social: An industrial perspective
Human computation, crowdsourcing and social: An industrial perspectiveHuman computation, crowdsourcing and social: An industrial perspective
Human computation, crowdsourcing and social: An industrial perspectiveoralonso
 
Machine Learning in Oil and Gas - April 18-19, 2018
Machine Learning in Oil and Gas - April 18-19, 2018Machine Learning in Oil and Gas - April 18-19, 2018
Machine Learning in Oil and Gas - April 18-19, 2018Mark Reynolds
 
Entity Search: The Last Decade and the Next
Entity Search: The Last Decade and the NextEntity Search: The Last Decade and the Next
Entity Search: The Last Decade and the Nextkrisztianbalog
 
Wimmics Research Team 2015 Activity Report
Wimmics Research Team 2015 Activity ReportWimmics Research Team 2015 Activity Report
Wimmics Research Team 2015 Activity ReportFabien Gandon
 
Tutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender SystemsTutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender SystemsYONG ZHENG
 
The How and Why of Feature Engineering
The How and Why of Feature EngineeringThe How and Why of Feature Engineering
The How and Why of Feature EngineeringAlice Zheng
 
Mining Web content for Enhanced Search
Mining Web content for Enhanced Search Mining Web content for Enhanced Search
Mining Web content for Enhanced Search Roi Blanco
 
Layman's Talk: Entities of Interest --- Discovery in Digital Traces
Layman's Talk: Entities of Interest --- Discovery in Digital TracesLayman's Talk: Entities of Interest --- Discovery in Digital Traces
Layman's Talk: Entities of Interest --- Discovery in Digital TracesDavid Graus
 
Data science for advanced dummies
Data science for advanced dummiesData science for advanced dummies
Data science for advanced dummiesSaurav Chakravorty
 
Introduction to Enterprise Search
Introduction to Enterprise SearchIntroduction to Enterprise Search
Introduction to Enterprise SearchFindwise
 
Introduction to Information Retrieval
Introduction to Information RetrievalIntroduction to Information Retrieval
Introduction to Information RetrievalCarsten Eickhoff
 
How to Feed a Data Hungry Organization – by Traveloka Data Team
How to Feed a Data Hungry Organization – by Traveloka Data TeamHow to Feed a Data Hungry Organization – by Traveloka Data Team
How to Feed a Data Hungry Organization – by Traveloka Data TeamTraveloka
 
Assembly of Japanese Bicycle Require Great Peace of Mind
Assembly of Japanese Bicycle Require Great Peace of MindAssembly of Japanese Bicycle Require Great Peace of Mind
Assembly of Japanese Bicycle Require Great Peace of MindPeter Leeson
 
Assembly of Japanese bicycle requires peace of mind - Peter Leeson
 Assembly of Japanese bicycle requires peace of mind - Peter Leeson Assembly of Japanese bicycle requires peace of mind - Peter Leeson
Assembly of Japanese bicycle requires peace of mind - Peter LeesonITCamp
 
Open Inclusion Consumer and Market Insights. WALL18 London, 08022018
Open Inclusion Consumer and Market Insights. WALL18 London, 08022018Open Inclusion Consumer and Market Insights. WALL18 London, 08022018
Open Inclusion Consumer and Market Insights. WALL18 London, 08022018Open Inclusion
 

Similar a On Entities and Evaluation (20)

ADV Slides: Graph Databases on the Edge
ADV Slides: Graph Databases on the EdgeADV Slides: Graph Databases on the Edge
ADV Slides: Graph Databases on the Edge
 
Immersive Recommendation
Immersive RecommendationImmersive Recommendation
Immersive Recommendation
 
2004 05 intelligence processing seminar
2004 05 intelligence processing seminar2004 05 intelligence processing seminar
2004 05 intelligence processing seminar
 
Human computation, crowdsourcing and social: An industrial perspective
Human computation, crowdsourcing and social: An industrial perspectiveHuman computation, crowdsourcing and social: An industrial perspective
Human computation, crowdsourcing and social: An industrial perspective
 
Machine Learning in Oil and Gas - April 18-19, 2018
Machine Learning in Oil and Gas - April 18-19, 2018Machine Learning in Oil and Gas - April 18-19, 2018
Machine Learning in Oil and Gas - April 18-19, 2018
 
Entity Search: The Last Decade and the Next
Entity Search: The Last Decade and the NextEntity Search: The Last Decade and the Next
Entity Search: The Last Decade and the Next
 
Wimmics Research Team 2015 Activity Report
Wimmics Research Team 2015 Activity ReportWimmics Research Team 2015 Activity Report
Wimmics Research Team 2015 Activity Report
 
Tutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender SystemsTutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender Systems
 
Data Mining Lecture_1.pptx
Data Mining Lecture_1.pptxData Mining Lecture_1.pptx
Data Mining Lecture_1.pptx
 
The How and Why of Feature Engineering
The How and Why of Feature EngineeringThe How and Why of Feature Engineering
The How and Why of Feature Engineering
 
Mining Web content for Enhanced Search
Mining Web content for Enhanced Search Mining Web content for Enhanced Search
Mining Web content for Enhanced Search
 
2004 06 intelligence analysis seminar
2004 06 intelligence analysis seminar2004 06 intelligence analysis seminar
2004 06 intelligence analysis seminar
 
Layman's Talk: Entities of Interest --- Discovery in Digital Traces
Layman's Talk: Entities of Interest --- Discovery in Digital TracesLayman's Talk: Entities of Interest --- Discovery in Digital Traces
Layman's Talk: Entities of Interest --- Discovery in Digital Traces
 
Data science for advanced dummies
Data science for advanced dummiesData science for advanced dummies
Data science for advanced dummies
 
Introduction to Enterprise Search
Introduction to Enterprise SearchIntroduction to Enterprise Search
Introduction to Enterprise Search
 
Introduction to Information Retrieval
Introduction to Information RetrievalIntroduction to Information Retrieval
Introduction to Information Retrieval
 
How to Feed a Data Hungry Organization – by Traveloka Data Team
How to Feed a Data Hungry Organization – by Traveloka Data TeamHow to Feed a Data Hungry Organization – by Traveloka Data Team
How to Feed a Data Hungry Organization – by Traveloka Data Team
 
Assembly of Japanese Bicycle Require Great Peace of Mind
Assembly of Japanese Bicycle Require Great Peace of MindAssembly of Japanese Bicycle Require Great Peace of Mind
Assembly of Japanese Bicycle Require Great Peace of Mind
 
Assembly of Japanese bicycle requires peace of mind - Peter Leeson
 Assembly of Japanese bicycle requires peace of mind - Peter Leeson Assembly of Japanese bicycle requires peace of mind - Peter Leeson
Assembly of Japanese bicycle requires peace of mind - Peter Leeson
 
Open Inclusion Consumer and Market Insights. WALL18 London, 08022018
Open Inclusion Consumer and Market Insights. WALL18 London, 08022018Open Inclusion Consumer and Market Insights. WALL18 London, 08022018
Open Inclusion Consumer and Market Insights. WALL18 London, 08022018
 

Más de krisztianbalog

Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...
Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...
Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...krisztianbalog
 
Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...krisztianbalog
 
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?krisztianbalog
 
Table Retrieval and Generation
Table Retrieval and GenerationTable Retrieval and Generation
Table Retrieval and Generationkrisztianbalog
 
Overview of the TREC 2016 Open Search track: Academic Search Edition
Overview of the TREC 2016 Open Search track: Academic Search EditionOverview of the TREC 2016 Open Search track: Academic Search Edition
Overview of the TREC 2016 Open Search track: Academic Search Editionkrisztianbalog
 
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF Lab
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF LabOverview of the Living Labs for IR Evaluation (LL4IR) CLEF Lab
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF Labkrisztianbalog
 
Entity Retrieval (WSDM 2014 tutorial)
Entity Retrieval (WSDM 2014 tutorial)Entity Retrieval (WSDM 2014 tutorial)
Entity Retrieval (WSDM 2014 tutorial)krisztianbalog
 
Time-aware Evaluation of Cumulative Citation Recommendation Systems
Time-aware Evaluation of Cumulative Citation Recommendation SystemsTime-aware Evaluation of Cumulative Citation Recommendation Systems
Time-aware Evaluation of Cumulative Citation Recommendation Systemskrisztianbalog
 
Entity Retrieval (SIGIR 2013 tutorial)
Entity Retrieval (SIGIR 2013 tutorial)Entity Retrieval (SIGIR 2013 tutorial)
Entity Retrieval (SIGIR 2013 tutorial)krisztianbalog
 
Multi-step Classification Approaches to Cumulative Citation Recommendation
Multi-step Classification Approaches to Cumulative Citation RecommendationMulti-step Classification Approaches to Cumulative Citation Recommendation
Multi-step Classification Approaches to Cumulative Citation Recommendationkrisztianbalog
 
Entity Retrieval (WWW 2013 tutorial)
Entity Retrieval (WWW 2013 tutorial)Entity Retrieval (WWW 2013 tutorial)
Entity Retrieval (WWW 2013 tutorial)krisztianbalog
 
Semistructured Data Seach
Semistructured Data SeachSemistructured Data Seach
Semistructured Data Seachkrisztianbalog
 
Collection Ranking and Selection for Federated Entity Search
Collection Ranking and Selection for Federated Entity SearchCollection Ranking and Selection for Federated Entity Search
Collection Ranking and Selection for Federated Entity Searchkrisztianbalog
 

Más de krisztianbalog (14)

Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...
Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...
Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...
 
Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...
 
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
 
Table Retrieval and Generation
Table Retrieval and GenerationTable Retrieval and Generation
Table Retrieval and Generation
 
Overview of the TREC 2016 Open Search track: Academic Search Edition
Overview of the TREC 2016 Open Search track: Academic Search EditionOverview of the TREC 2016 Open Search track: Academic Search Edition
Overview of the TREC 2016 Open Search track: Academic Search Edition
 
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF Lab
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF LabOverview of the Living Labs for IR Evaluation (LL4IR) CLEF Lab
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF Lab
 
Entity Linking
Entity LinkingEntity Linking
Entity Linking
 
Entity Retrieval (WSDM 2014 tutorial)
Entity Retrieval (WSDM 2014 tutorial)Entity Retrieval (WSDM 2014 tutorial)
Entity Retrieval (WSDM 2014 tutorial)
 
Time-aware Evaluation of Cumulative Citation Recommendation Systems
Time-aware Evaluation of Cumulative Citation Recommendation SystemsTime-aware Evaluation of Cumulative Citation Recommendation Systems
Time-aware Evaluation of Cumulative Citation Recommendation Systems
 
Entity Retrieval (SIGIR 2013 tutorial)
Entity Retrieval (SIGIR 2013 tutorial)Entity Retrieval (SIGIR 2013 tutorial)
Entity Retrieval (SIGIR 2013 tutorial)
 
Multi-step Classification Approaches to Cumulative Citation Recommendation
Multi-step Classification Approaches to Cumulative Citation RecommendationMulti-step Classification Approaches to Cumulative Citation Recommendation
Multi-step Classification Approaches to Cumulative Citation Recommendation
 
Entity Retrieval (WWW 2013 tutorial)
Entity Retrieval (WWW 2013 tutorial)Entity Retrieval (WWW 2013 tutorial)
Entity Retrieval (WWW 2013 tutorial)
 
Semistructured Data Seach
Semistructured Data SeachSemistructured Data Seach
Semistructured Data Seach
 
Collection Ranking and Selection for Federated Entity Search
Collection Ranking and Selection for Federated Entity SearchCollection Ranking and Selection for Federated Entity Search
Collection Ranking and Selection for Federated Entity Search
 

Último

GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024Jene van der Heide
 
Pests of Sunflower_Binomics_Identification_Dr.UPR
Pests of Sunflower_Binomics_Identification_Dr.UPRPests of Sunflower_Binomics_Identification_Dr.UPR
Pests of Sunflower_Binomics_Identification_Dr.UPRPirithiRaju
 
Total Legal: A “Joint” Journey into the Chemistry of Cannabinoids
Total Legal: A “Joint” Journey into the Chemistry of CannabinoidsTotal Legal: A “Joint” Journey into the Chemistry of Cannabinoids
Total Legal: A “Joint” Journey into the Chemistry of CannabinoidsMarkus Roggen
 
cybrids.pptx production_advanges_limitation
cybrids.pptx production_advanges_limitationcybrids.pptx production_advanges_limitation
cybrids.pptx production_advanges_limitationSanghamitraMohapatra5
 
Speed Breeding in Vegetable Crops- innovative approach for present era of cro...
Speed Breeding in Vegetable Crops- innovative approach for present era of cro...Speed Breeding in Vegetable Crops- innovative approach for present era of cro...
Speed Breeding in Vegetable Crops- innovative approach for present era of cro...jana861314
 
Role of Gibberellins, mode of action and external applications.pptx
Role of Gibberellins, mode of action and external applications.pptxRole of Gibberellins, mode of action and external applications.pptx
Role of Gibberellins, mode of action and external applications.pptxjana861314
 
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep LearningCombining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learningvschiavoni
 
bonjourmadame.tumblr.com bhaskar's girls
bonjourmadame.tumblr.com bhaskar's girlsbonjourmadame.tumblr.com bhaskar's girls
bonjourmadame.tumblr.com bhaskar's girlshansessene
 
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer Zahana
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer ZahanaEGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer Zahana
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer ZahanaDr.Mahmoud Abbas
 
whole genome sequencing new and its types including shortgun and clone by clone
whole genome sequencing new  and its types including shortgun and clone by clonewhole genome sequencing new  and its types including shortgun and clone by clone
whole genome sequencing new and its types including shortgun and clone by clonechaudhary charan shingh university
 
Interpreting SDSS extragalactic data in the era of JWST
Interpreting SDSS extragalactic data in the era of JWSTInterpreting SDSS extragalactic data in the era of JWST
Interpreting SDSS extragalactic data in the era of JWSTAlexander F. Mayer
 
Abnormal LFTs rate of deco and NAFLD.pptx
Abnormal LFTs rate of deco and NAFLD.pptxAbnormal LFTs rate of deco and NAFLD.pptx
Abnormal LFTs rate of deco and NAFLD.pptxzeus70441
 
Timeless Cosmology: Towards a Geometric Origin of Cosmological Correlations
Timeless Cosmology: Towards a Geometric Origin of Cosmological CorrelationsTimeless Cosmology: Towards a Geometric Origin of Cosmological Correlations
Timeless Cosmology: Towards a Geometric Origin of Cosmological CorrelationsDanielBaumann11
 
Immunoblott technique for protein detection.ppt
Immunoblott technique for protein detection.pptImmunoblott technique for protein detection.ppt
Immunoblott technique for protein detection.pptAmirRaziq1
 
Loudspeaker- direct radiating type and horn type.pptx
Loudspeaker- direct radiating type and horn type.pptxLoudspeaker- direct radiating type and horn type.pptx
Loudspeaker- direct radiating type and horn type.pptxpriyankatabhane
 
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPRPirithiRaju
 
BACTERIAL SECRETION SYSTEM by Dr. Chayanika Das
BACTERIAL SECRETION SYSTEM by Dr. Chayanika DasBACTERIAL SECRETION SYSTEM by Dr. Chayanika Das
BACTERIAL SECRETION SYSTEM by Dr. Chayanika DasChayanika Das
 
FBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptxFBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptxPayal Shrivastava
 
Environmental Acoustics- Speech interference level, acoustics calibrator.pptx
Environmental Acoustics- Speech interference level, acoustics calibrator.pptxEnvironmental Acoustics- Speech interference level, acoustics calibrator.pptx
Environmental Acoustics- Speech interference level, acoustics calibrator.pptxpriyankatabhane
 

Último (20)

GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024
 
Pests of Sunflower_Binomics_Identification_Dr.UPR
Pests of Sunflower_Binomics_Identification_Dr.UPRPests of Sunflower_Binomics_Identification_Dr.UPR
Pests of Sunflower_Binomics_Identification_Dr.UPR
 
Interferons.pptx.
Interferons.pptx.Interferons.pptx.
Interferons.pptx.
 
Total Legal: A “Joint” Journey into the Chemistry of Cannabinoids
Total Legal: A “Joint” Journey into the Chemistry of CannabinoidsTotal Legal: A “Joint” Journey into the Chemistry of Cannabinoids
Total Legal: A “Joint” Journey into the Chemistry of Cannabinoids
 
cybrids.pptx production_advanges_limitation
cybrids.pptx production_advanges_limitationcybrids.pptx production_advanges_limitation
cybrids.pptx production_advanges_limitation
 
Speed Breeding in Vegetable Crops- innovative approach for present era of cro...
Speed Breeding in Vegetable Crops- innovative approach for present era of cro...Speed Breeding in Vegetable Crops- innovative approach for present era of cro...
Speed Breeding in Vegetable Crops- innovative approach for present era of cro...
 
Role of Gibberellins, mode of action and external applications.pptx
Role of Gibberellins, mode of action and external applications.pptxRole of Gibberellins, mode of action and external applications.pptx
Role of Gibberellins, mode of action and external applications.pptx
 
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep LearningCombining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
 
bonjourmadame.tumblr.com bhaskar's girls
bonjourmadame.tumblr.com bhaskar's girlsbonjourmadame.tumblr.com bhaskar's girls
bonjourmadame.tumblr.com bhaskar's girls
 
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer Zahana
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer ZahanaEGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer Zahana
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer Zahana
 
whole genome sequencing new and its types including shortgun and clone by clone
whole genome sequencing new  and its types including shortgun and clone by clonewhole genome sequencing new  and its types including shortgun and clone by clone
whole genome sequencing new and its types including shortgun and clone by clone
 
Interpreting SDSS extragalactic data in the era of JWST
Interpreting SDSS extragalactic data in the era of JWSTInterpreting SDSS extragalactic data in the era of JWST
Interpreting SDSS extragalactic data in the era of JWST
 
Abnormal LFTs rate of deco and NAFLD.pptx
Abnormal LFTs rate of deco and NAFLD.pptxAbnormal LFTs rate of deco and NAFLD.pptx
Abnormal LFTs rate of deco and NAFLD.pptx
 
Timeless Cosmology: Towards a Geometric Origin of Cosmological Correlations
Timeless Cosmology: Towards a Geometric Origin of Cosmological CorrelationsTimeless Cosmology: Towards a Geometric Origin of Cosmological Correlations
Timeless Cosmology: Towards a Geometric Origin of Cosmological Correlations
 
Immunoblott technique for protein detection.ppt
Immunoblott technique for protein detection.pptImmunoblott technique for protein detection.ppt
Immunoblott technique for protein detection.ppt
 
Loudspeaker- direct radiating type and horn type.pptx
Loudspeaker- direct radiating type and horn type.pptxLoudspeaker- direct radiating type and horn type.pptx
Loudspeaker- direct radiating type and horn type.pptx
 
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
 
BACTERIAL SECRETION SYSTEM by Dr. Chayanika Das
BACTERIAL SECRETION SYSTEM by Dr. Chayanika DasBACTERIAL SECRETION SYSTEM by Dr. Chayanika Das
BACTERIAL SECRETION SYSTEM by Dr. Chayanika Das
 
FBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptxFBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptx
 
Environmental Acoustics- Speech interference level, acoustics calibrator.pptx
Environmental Acoustics- Speech interference level, acoustics calibrator.pptxEnvironmental Acoustics- Speech interference level, acoustics calibrator.pptx
Environmental Acoustics- Speech interference level, acoustics calibrator.pptx
 

On Entities and Evaluation

  • 1. ON ENTITIES AND EVALUATION Krisztian Balog University of Stavanger
 @krisztianbalog Keynote given at the 41st European Conference on Informa<on Retrieval (ECIR '19) | Cologne, Germany, April 2019
  • 2. SPECIAL THANKS TO • My former PhD advisor: • Maarten de Rijke • My former and current PhD students: • Jan R. Benetka, Richard Berendsen, Marc Bron, Heng Ding, Darío Garigliotti, Faegheh Hasibi, Trond Linjordet, Robert Neumayer, Shuo Zhang • Collaborators on material presented in this talk: • Po-Yu Chuang, Peter Dekker, Maarten de Rijke, Kristian Gingstad, Rolf Jagerman, Øyvind Jekteberg, Liadh Kelly, Tom Kenter, Phillip Schaer, Anne Schuth, Narges Tavakolpoursaleh
  • 4. OUTLINE FOR PART I • What is an entity? 
 • Why care about entities? 
 • What research has been done on entities in IR? 
 • What’s next?
  • 5. WHAT IS AN ENTITY? An entity is an object or thing that can be uniquely identified. entity catalog entity ID* name(s)*
  • 6. AN ENTITY <dbr:Roger_Needham> <dbo:Scientist> <dbo:Person> <dbo:Agent> <owl:Thing> <rdf:type> <dbo:abstract> "1935-08-26" "Karen Spärck Jones" <foaf:name> <dbo:spouse> <University_of_Cambridge> <dbp:almaMater> <dbr:Natural_language_processing> <dbo:knownFor> <dbc:Information_retrieval_researchers> <dct:subject> <dbc:British_women_computer_scientists> <dbc:British_computer_scientists> <dbc:British_women_scientists> "Karen Spärck Jones FBA (26 August 1935 – 4 April 2007) was a British computer scientist." <dbr:Karen_Spark_Jones> <dbo:birthDate>
  • 7. WHAT IS AN ENTITY? An entity is a uniquely identifiable object or thing, characterized by its name(s), type(s), attributes, and relationships to other entities.
  • 8. REPRESENTING ENTITIES 
 AND THEIR PROPERTIES entity catalog entity ID* name(s)* knowledge repository type(s)* descriptions relationships (non-typed links)
  • 9. REPRESENTING ENTITIES 
 AND THEIR PROPERTIES entity catalog entity ID* name(s)* knowledge repository type(s)* descriptions relationships (non-typed links) knowledge base (KB) /
 knowledge graph (KG) attributes relationships (typed links)
  • 10. WHY CARE ABOUT ENTITIES? • From a user perspective, entities ... • are natural units for organizing information • enable a richer and more effective user experience
  • 11. WHY CARE ABOUT ENTITIES? • From a machine perspective, entities ... • allow for a better understanding of queries, document content, and of users • enable search engines to be more intelligent Michael Schumacher (born 3 January 1969) is a German retired racing driver. He is a seven-time Formula One World Champion and is widely regarded as one of the greatest Formula One drivers of all time. He won two titles with Benetton in 1994 and 1995 before moving to Ferrari where he drove for eleven years. His time with Ferrari yielded five consecutive titles between 2000 and 2004. Michael Schumacher Schuderia Ferrari Benetton Formula Racing driver Formula One constructor Formula One constructor Formula One Auto racing series
  • 12. Part I En88es RESEARCH ON ENTITIES IN IR
  • 13. TRENDS IN THE IR LITERATURE 0 10 20 30 40 2000 2002 2004 2006 2008 2010 2012 2014 2016 entity OR entities Wikipedia knowledge base knowledge graph Numbers are based on boolean queries on paper titles from SIGIR, ECIR, CIKM, WSDM, and WWW
  • 14. TRENDS IN THE IR LITERATURE Numbers are based on boolean queries on paper titles from SIGIR, ECIR, CIKM, WSDM, and WWW 0 10 20 30 40 2000 2002 2004 2006 2008 2010 2012 2014 2016 entity OR entities Wikipedia OR "knowledge base" OR "knowledge graph"
  • 15. #1 ENTITIES AS THE UNIT OF RETRIEVAL • A significant portion of queries mention or target entities • Those queries are better answered with a ranked list of entities (as opposed to a list of documents) • Term-based entity representations can be effectively ranked using document-based retrieval models • Semantically informed retrieval models utilize entity- specific properties (attributes, types, and relationships)
  • 16. #2 ENTITIES FOR KNOWLEDGE REPRESENTATION • Entities help to bridge the gap between unstructured and structured data <entity> <entity> Entity linking Knowledge base population
  • 17. #3 ENTITIES FOR AN ENHANCED SEARCH EXPERIENCE • Improve the search experience through the entire search process • Understanding search queries • Improving document retrieval performance • Query assistance services (auto-completion, suggestions) • Entity recommendations
  • 18. WANT TO KNOW MORE? www.eos-book.org
  • 19. OUTLINE FOR PART I • What is an entity? 
 • Why care about entities? 
 • What research has been done on entities in IR? 
 • What’s next?
  • 20. SCENARIO #1 I would like to get some new strings for my guitar AIOK, would that be your electric guitar or the acoustic one? The electric one. AIAlright. I can repeat your Amazon order of 3 months ago, or you can go by a music store on Elm street on the way to your dentist appointment this afternoon.
  • 21. TRULY PERSONAL AI 
 IS NOT POSSIBLE WITHOUT A PERSONAL KNOWLEDGE GRAPH
  • 22. PERSONAL KNOWLEDGE GRAPHS A personal knowledge graph (PKG) is a source of structured knowledge about entities and the relation between them, where the entities and the relations between them are of personal, rather than general, importance.
  • 23. PERSONAL KNOWLEDGE GRAPHS User Hometown Mom Social network Jamie High schoolGeneral -purpose KG Electric guitar E-commerce catalog Mom’s dentist Domain-specific KG Acoustic guitar Personal Knowledge Graph
  • 24. Part I En88es A RESEARCH AGENDA 
 FOR PERSONAL KNOWLEDGE GRAPHS Part I En88es
  • 25. #1 KNOWLEDGE REPRESENTATION • Task: representing entities and their properties • KGs are organized according to a knowledge model (schema) • Peculiarities/challenges: • Entities need to be (directly/indirectly) connected to the user • Not duplicating attributes, focusing on what is personal • Information about entities can be very sparse • Some entities may not have any digital presence • Strong temporality (relations can be ephemeral)
  • 26. #1 KNOWLEDGE REPRESENTATION • Task: representing entities and their properties • KGs are organized according to a knowledge model (schema) • Peculiarities/challenges: • Entities need to be (directly/indirectly) connected to the user • Not duplicating attributes, focusing on what is personal • Information about entities can be very sparse • Some entities may not have any digital presence • Strong temporality (relations can be ephemeral) What is the best way of representing entities and their properties and relations, considering the vast but sparse set of possible predicates? RQ1
  • 27. #2 SEMANTIC ANNOTATION OF TEXT • Task: annotating text with respect to a knowledge repository (commonly known as entity linking) • Usually involves mention detection, entity disambiguation, and NIL-detection steps • Challenges • Entities might have little to no digital presence • Entities are not necessarily proper nouns • Linking, NIL-detection, and KG population are intertwined
  • 28. #2 SEMANTIC ANNOTATION OF TEXT • Task: annotating text with respect to a knowledge repository (commonly known as entity linking) • Usually involves mention detection, entity disambiguation, and NIL-detection steps • Challenges • Entities might have little to no digital presence • Entities are not necessarily proper nouns • Linking, NIL-detection, and KG population are intertwined How can entity linking be performed against a personal knowledge graph, where structured entity information to rely on is potentially absent? RQ2a When should entity linking be performed against a personal knowledge graph as opposed to a general- purpose KG? RQ2b
  • 29. SCENARIO #2 I need to see a dentist. Mom recommended hers at dinner yesterday. AII can try to help you find this person. Do you have any more information? I reckon that him and Mom graduated from the same high school the same year. AIOK, that's enough to narrow it down. 
 It must be Dr. John Pullman. That must be him. I remember he had a fitting name. Can you try make an appointment for Thursday afternoon?
  • 30. #3 POPULATION AND MAINTENANCE • Task: extending a KG from external sources (KB acceleration/population) or via internal inferencing • Verification of facts in the KG • Challenges: • Single curator; more automation is desired than for KGs, but the user should still be in control • The first mention of an entity should trigger population • Properties may be inferred from the context
  • 31. #3 POPULATION AND MAINTENANCE • Task: extending a KG from external sources (KB acceleration/population) or via internal inferencing • Verification of facts in the KG • Challenges: • Single curator; more automation is desired than for KGs, but the user should still be in control • The first mention of an entity should trigger population • Properties may be inferred from the context How can personal knowledge graphs be automatically populated and reliably maintained? RQ3
  • 32. SCENARIO #3 AISince you're running a half marathon at Hackney in May, may I suggest you undertake a 10k run this weekend? Yes, that sounds like a good idea. Any suggestions for a not too popular route 
 that I haven't done before? AISure thing. I'll upload some routes to the running app on your phone. Cheers mate!
  • 33. #4 QUERYING • Task: Retrieving information (entities, types, relations, etc.) from the PKG or from KGs with the help of the PKG • Challenges: • Sparsity of data • Soft, subjective constraints
  • 34. #4 QUERYING • Task: Retrieving information (entities, types, relations, etc.) from the PKG or from KGs with the help of the PKG • Challenges: • Sparsity of data • Soft, subjective constraints How to leverage the semantically rich but sparse information in personal knowledge graphs for answering natural language queries? RQ4
  • 35. #5 INTEGRATION WITH EXTERNAL SOURCES • Task: recognizing the same entity across multiple data sources (a.k.a. object resolution, record linkage, ...) • Challenges: • One-to-many, as opposed to one-to-one linkage • Continuous process, not a one-off effort • Two-way synchronization would be desired • Conflicting facts or relations need resolving by the user
  • 36. #5 INTEGRATION WITH EXTERNAL SOURCES • Task: recognizing the same entity across multiple data sources (a.k.a. object resolution, record linkage, ...) • Challenges: • One-to-many, as opposed to one-to-one linkage • Continuous process, not a one-off effort • Two-way synchronization would be desired • Conflicting facts or relations need resolving by the user How to provide continuous two-way integration with external knowledge sources with the user in the loop? RQ5
  • 37. RESEARCH QUESTIONS 
 FOR PERSONAL KNOWLEDGE GRAPHS • What is the best way of representing entities and their properties and relations, considering the vast but sparse set of possible predicates? • How can entity linking be performed against a personal knowledge graph, where structured entity information to rely on is potentially absent? • How can personal knowledge graphs be automatically populated and reliably maintained? • How to leverage the semantically rich but sparse information in personal knowledge graphs for answering natural language queries? • How to provide continuous two-way integration with external knowledge sources with the user in the loop?
  • 38. THERE IS MORE... • Implementation • Where is it stored (on the device, cloud, etc.)? • How can security and privacy be ensured? • How to interact with a range of services with proper access control? • Evaluation • How to build reusable test resources?
  • 39. SUMMARY OF PART I • Progress on entity-oriented search was enabled by large open knowledge repositories • Personal AI is not possible without the concept of a personal knowledge graph • Many interesting research opportunities are available
  • 41. OUTLINE FOR PART II • Online evaluation and why we need it
 • Living labs: methodology and lessons learned
 • What's next?
  • 42. EVALUATION METHODOLOGIES • Offline evaluation ("TREC-style" studies) • Online evaluation • Lab-based studies • Simulation of users • ...
  • 43. ONLINE EVALUATION 101 • See how regular users interact with a retrieval system when just using it • Observe implicit behavior • Clicks, skips, saves, forwards, bookmarks, likes, etc. • Try to infer differences in behavior from different flavors of the live system • A/B testing, interleaving • Run statistical tests to confirm the difference is not due to chance
  • 44. CHALLENGES IN ONLINE EVALUATION • It's a live service • Complexity of modern SERPs • Data is noisy • There’s no “ground truth”
  • 45. OFFLINE VS. ONLINE EVALUATION Offline Online Basic assumption Assessors tell you what is relevant Observable user behavior can tell you what is relevant Quality Data is only as good as the guidelines Real user data, real and representative information needs Realisticity Simplified scenario, cannot go beyond a certain level of complexity Perfectly realistic setting (users are not aware that they are guniea pigs) Assessment cost Expensive Cheap Scalability Doesn't scale Scales very well Repeatability Repeatable Not repeatable Throughput High Low Risk None High
  • 46. THE COMMUNITY NEEDS 
 OPEN RESEARCH PLATFORMS FOR ONLINE EVALUATION
  • 47. LIVING LABS Living labs is a new evaluation paradigm for IR, where the experimentation platform is an existing search engine. Researchers have the opportunity to replace components of this search engine and evaluate these components using interactions with real, "unsuspecting" users of this search engine.
  • 49. ALL WE NEED IS A SITE: LET'S TAKE AN EXISTING ONE
  • 50. KEY IDEAS FOR OPERATIONALIZATION • An API orchestrates all the data exchange between sites (live search engines) and participants • Focus on frequent (head) queries • Enough traffic on them for experimentation • Participants generate rankings offline and upload these to the API • Eliminates real-time requirement • Freedom in choice of tools and environment K. Balog, L. Kelly, andA. Schuth.Head First: Living Labs for Ad-hoc Search Evalua<on. CIKM'14
  • 51. OVERVIEW experimental systems users live site API K. Balog, L. Kelly, andA. Schuth.Head First: Living Labs for Ad-hoc Search Evalua<on. CIKM'14
  • 52. METHODOLOGY (1) experimental system users live site API • Sites make queries, candidate documents (items), historical search and click data available through the API
  • 53. METHODOLOGY (2) experimental system users live site API • Rankings are generated (offline) for each query and uploaded to the API
  • 54. METHODOLOGY (3) experimental system API • When any of the test queries is fired on the live site, it requests an experimental ranking from the API and interleaves it with that of the producOon system query interleaved ranking query experimental ranking
  • 55. METHODOLOGY (3) experimental system API • When any of the test queries is fired on the live site, it requests an experimental ranking from the API and interleaves it with that of the producOon system query interleaved ranking query experimental ranking doc 1 doc 2 doc 3 doc 4 doc 5 doc 2 doc 4 doc 7 doc 1 doc 3 system A system B doc 1 doc 2 doc 4 doc 3 doc 7 interleaved list
  • 56. METHODOLOGY (4) • ParOcipants get detailed feedback on user interacOons (clicks) experimental system users live site API
  • 57. METHODOLOGY (5) • Evaluation measure: • where the number of “wins” and “losses” is against the production system, aggregated over a period of time • An Outcome of > 0.5 means beating the production system Outcome = #Wins #Wins + #Losses
  • 58. LIMITATIONS • Head queries only: Considerable portion of traffic, but only popular info needs • Lack of context: No knowledge of the searcher’s location, previous searches, etc. • No real-time feedback: API provides detailed feedback, but it’s not immediate • Limited control: Experimentation is limited to single searches, where results are interleaved with those of the production system; no control over the entire result list
  • 60. EVALUATION CAMPAIGNS Product search (Hungarian toy store) Product search (Hungarian toy store) Academic search (CiteSeerX, SSOAR, Microsoft Academic) Academic search (CiteSeerX, SSOAR) Web search (Czech web search engine) OS‘16 OS‘17
  • 61. TREC OPENSEARCH • Sites: academic search engines • Task: ad hoc scientific literature search • Multiple evaluation rounds (6 weeks each) • Train/test queries • Training queries: feedback on individual impressions • Test queries: only aggregated feedback at the end of the evaluation period
  • 62. CITESEERX @TREC-OS 2016 Round 1 Round 2 Round 3 Impressions 359 571 4829 Clicks 144 128 651 ery 0 100 200 300 Numberofimpressions 2016 Round 1 - CiteSeerX ery 0 100 200 300 400 Numberofimpressions 2016 Round 2 - CiteSeerX ery 0 200 400 600 Numberofimpressions 2016 Round 3 - CiteSeerX ery 0 5 10 15 Numberofclicks 2016 Round 1 - CiteSeerX ery 0 5 10 15 20 Numberofclicks 2016 Round 2 - CiteSeerX ery 0 5 10 15 20 Numberofclicks 2016 Round 3 - CiteSeerX
  • 63. EVALUATION RESULTS
 CITESEERX, TREC-OS 2016, ROUND #3 Wins Ties Losses Outcome p-value System 1 48 15 39 0.5517 0.3912 System 2 27 11 22 0.5510 0.5682 System 3 35 14 32 0.5224 0.8072 ... We would need to gather data for about six months for p 0.05 and for about a year for p 0.01 (assuming a similar win/loss ratio).
  • 64. LESSONS LEARNED • Head first idea is feasible • Running multiple campaigns without major technical hurdles • Low traffic/click volume is an issue • No statistically significant differences observed • Possible remedy is to use more queries (tap into the long tail) • Main challenges are more of an organizational than of a technical nature • Nontrivial infrastructure development on the service providers’ side • Convincing large industrial partners as sites • Attracting a large and active set of participants R. Jagerman, K. Balog, and M. de Rijke.OpenSearch: Lessons Learned from an Online Evaluaon Campaign. Journal of Data and Informaon Quality, 2018.
  • 65. ALL WE NEED IS A SITE: LET'S BUILD ONE
  • 66. A SUCCESS STORY Part II Evalua8on
  • 67. run by GroupLens, a research lab at the University of Minnesota
  • 68.
  • 69. OFFLINE DATASETS • MovieLens-20M • 20M item ratings • 27K movies • 138K users • 465K tags • links to YouTube trailers for 25K movies
  • 70. ONLINE EXPERIMENTATION WITH 
 NOVEL USER INTERFACES
  • 72. BUILDING A SERVICE FOR SCIENTIFIC LITERATURE RECOMMENDATION Part II Evalua8on
  • 73. ARXIVDIGEST: THE SERVICE • Recommendation service to help keep up with scientific literature published on arxiv.org • Users sign up and indicate their interests by providing keywords, Google Scholar/DBLP profile, etc. • Users receive recommendations regularly in a digest email • Articles can be liked • Users agree that their profile, the articles recommended to them, and their feedback would be made available to experimental systems
  • 74.
  • 75. ARXIVDIGEST: THE EVALUATION PLATFORM • Broker-based architecture • RESTful API for accessing article and user data and for uploading recommendations • Participating teams are given a window each day to download new content and to generate recommendations for all users • Users receive interleaved rankings • Performance is monitored continuously over time
  • 76. CURRENT STATUS AND OPPORTUNITIES • All components of the broker in place • https://github.com/iai-group/ArXivDigest • Ensuring GDPR-compliance is in progress • Opportunities for studying • Personalized recommender algorithms • Explainable recommendations • Interleaving • ... Fork m e on G itH ub
  • 77. SUMMARY OF PART II • The community needs open online evaluation platforms • Lessons learned from previous evaluation benchmarks • Proposal: develop a service that we'd use ourselves
  • 78. TAKE-HOME MESSAGES • A truly personal AI is not possible without a personal knowledge graph • The community needs open research platforms for online evaluation