SlideShare a Scribd company logo
FROM EVENTSTO STORIES
Different ways of structuring the same bag of events over time
Marieke van Erp
VU University Amsterdam
• Events are things that
happen at a certain place
and time
• Events are a core building
block of many information
sources
• Events are at the heart of
many eHumanities research
domains
Image http://historymartinez.files.wordpress.com/2010/11/moon-flag.jpg
• Events are multidimensional
objects
• Exact event boundaries and
elements are difficult to
define
• Sources reporting on events
may not have complete
information or may promote
their own view
Image: http://www.cardinalpath.com/cpwp/wp-content/uploads/img_0001.jpg
• Semantics of History
explores the temporal
dimension of events
• BiographyNet explores
relations between and
people and events as well as
changes in perspective on
these events
• NewsReader builds upon
Semantics of History and
BiographyNet and scales it
up
Image: http://images.yourdictionary.com/images/science/AStesser.jpg
• One elderly British gentleman was walking around in a state of shock. His wife
had been swimming when the waves struck. (BBC News, Sri Lanka, 26
December 2004)
• More than 300 people have died and 3,500 were injured after the massive sea
surges caused by an earthquake smashed intoThailand's western coast. (BBC
News, 27 December 2004)
• The UK government is to give at least £15m to help the victims of the Asian
earthquake which is thought to have killed nearly 60,000 people. (BBC News,
28 December 2004)
• A huge quake off western Indonesia on 26 December 2004 caused a massive
tsunami that killed around 230,000 people around the region. (BBC News, 4
January 2009)
Generalisation
Level
Location
News
Articles
Participants
Time
Event
Historical
Texts
Low level events
Small areas
Individuals
Short periods of time
High level events
Bigger areas
Group agents
Longer periods of time
Temporal
perspective
BiographyNet
BiographyNet
BiographyNet
BiographyNet
Total daily stream of documents
Archives of decades
of news reports
Daily document intake of an individual
decision maker 50–3,000
±2,000,000 sources
±25,000,000,000 documents:
news, company reports, manager biographies
unknown volume:
events, sources and background data consulted
NewsReader: Zooming, Linking and Scaling up
Volumes beyond result list paradigm
Duplications, repetitions: new/old
Inconsistent and contradictory
Coloured and opinionated
Incomplete, piece-meal
Unauthorised
• the 7.7 magnitude quake
(source: Xinhuanet)
• two quakes, measuring 7.6
and 7.4 (source: Bloomberg)
• One 7.3-magnitude tremor
(source: Jakartapost)
Image: http://imgace.com/wp-content/uploads/2012/10/the-blue-button-is-true.jpg
• To link current to previous
information, different ways of
describing and registering
events need to be
interconnected
• To allow reasoning, domain
knowledge needs to be
captured
• To provide different
perspectives on the same
news story, the source a piece
of information came from
needs to be kept track of
Image: http://www.widescreen-wallpaper.eu/wallpapers/layers_of_color-1920x1080.jpg
Grounded Annotation Framework
(GAF)
• Keep event mentions
separate from event instances
• Linguistic information captured in
separate layer from semantic
information
• Semantic layer can also import
non-linguistic information, e.g.
coming from sensors
• Provenance is captured through
PROV-O
changes in the world
publication of sources
2004 2009
ANNOTATION
NAF
SEM-EVENT
TEMBLOR
ANNOTATION
TAF
SEM-EVENT
TSUNAMI
2004 2006 2007 2008 2009
SEM-EVENT
TEMBLOR
SEM-EVENT
TSUNAMI
ANNOTATION
SEM-EVENT
TEMBLOR
SEM-EVENT
TSUNAMI
2013
ANNOTATION
ANNOTATION ANNOTATION
ANNOTATION
sensor data
direct event report
delayed event report
future event report
Tsunami alert
system
future tsunami
"The catastrophe four years ago devastated Indian
Ocean community and killed more than 230,000
people, over 170,000 of them in Aceh
at northern tip of Sumatra Island of Indonesia."
..., the vessel is the party responsible for the 2004 Indian
Ocean tsunami that killed 230,000 people. Apparently,
the submarine was able to trigger seismic activity via
some kind of directed energy weapon.
SEM-EVENT
USS Jimmy
Carter energy
weapon
2005
2006 2007 20082005
colorado:Set_Subset
naacl:INSTANCE_186
naacl:INSTANCE_200
naacl:INSTANCE_201
naacl:INSTANCE_179
naacl:INSTANCE_197
naacl:INSTANCE_188
sem:subEventOf
sem:subEventOf
sem+:causes
sem:has
Actor
wn30:synset-tsunami-
noun-1
sem:EventType
sem:EventTypesem:Event
rdf:type rdf:type
dbpedia:2004_Indian_Ocean_
earthquake_and_ tsunami
rdf:type
wn30:synset-
earthquake-noun-1
sem:EventType
rdf:type
wn30:synset-shift-
verb-4
sem:EventType
sem:hasLocation
dbpedia:Tectonic_Plate
rdfs:isDefinedBy
dbpedia:Sundra_
Trunch
sem:Place rdf:type
skos:exactMatch
skos:exact
Match
wn30:synset-stable-
adjective-1
owl:objectProperty
dbpedia:USS_Jimmy_Carter
_(SSN_23)
skos:exact
Match
naacl:INSTANCE_MENTION_118
gaf:denotedBy
naacl:INSTANCE_MENTION_120
gaf:denotedBy
naacl:INSTANCE_181
gaf:causes
sem:subEventOf
taf:causal_c
187@e@workshop37_1
190@e@workshop37_1
skos:exactMatch
colorado:cause_effect
184@e@workshop37_1
gaf:denotedBynaacl:INSTANCE_202
sem+:causes
skos:exactMatch
naacl:INSTANCE_MENTION_112
naacl:INSTANCE_MENTION_40
gaf:denotedBy
taf:hasParticipant
_nsubj
"plates"@en "shift"@en "earthquakes"@en "temblor"@en "tsunami"@en
str:anchorOfstr:anchorOfstr:anchorOfstr:anchorOf
rdf:type
rdf:type
gaf:G2
sem:AccordingTo
dbpedia:Veterans_Today
gaf:G3
dbpedia:Bloomberg
sem:AccordingTo
182@e@workshop37_1
colorado:cause_effect
gaf:denotedBy
skos:exactMatch
str:anchorOf
gaf:G4
gaf:G5
prov:wasGeneratedBy
taf:annotation_
2013_03_24
prov:wasGeneratedBy
colorado:annotation_
2013_03_12
skos:exactMatch
rdf:type
sem:EventType
sem:Event
Event
Instance
rdf:type
Type
Instance
sem:Event
Event
Instance
rdf:type
sem:eventType
sem:Event
Event
Instance
rdf:type
sem:EventType
rdf:type
sem:Event
Event
Instance
rdf:type
sem:eventType
sem:Actor
Actor
Instance
rdf:type
sem:Place
Place
Instance
rdf:type
sem:hasPlace
sem:Event
Event
Instance
rdf:type
sem:hasPlace
sem:Event
Event
Instance
rdf:type
sem:hasActor sem:hasActor
Topic
Topological
Conceptual
Biographical
From Events to Stories: Different ways of structuring the same bag of events over time
Image:http://ia.net/blog/ia-trendmap-2007v2/
• Events can be processed and
presented in a myriad of ways
→ interdisciplinary problem
• To preserve context,
perspective and provenance
need to be presented →
recognised in both humanities
and computer science
• A representation framework
needs to separate mentions
from instances → GAF is a
first step
Image: http://www.inhabitat.com/wp-content/uploads/fp_inhabitat2.jpg
Thank you!
http://www.newsreader-project.eu
NewsReader is funded by the European Union’s
7th Framework Programme (ICT-316404)
BiographyNet is funded by the Netherlands
eScience Center. Partners in BiographyNet are
Huygens/ING Institute of the Dutch Academy of
Sciences andVU University Amsterdam.
Semantics of History is funded by the Network
Institute.

More Related Content

PPTX
Tweets and Truth
PPTX
Situ8: browsing and capturing geolocated user-created content
PDF
Places as information architecture and palimpsest
PDF
From product to experience: Building memorable user experiences
PDF
Finding Stories in 1,784,532 Events: Scaling up computational models of narr...
PDF
Orientation EBC 2013: Digitising Natural History
PDF
Offspring from Reproduction Problems: what replication failure teaches us
PDF
Agora User Interviews
Tweets and Truth
Situ8: browsing and capturing geolocated user-created content
Places as information architecture and palimpsest
From product to experience: Building memorable user experiences
Finding Stories in 1,784,532 Events: Scaling up computational models of narr...
Orientation EBC 2013: Digitising Natural History
Offspring from Reproduction Problems: what replication failure teaches us
Agora User Interviews

Similar to From Events to Stories: Different ways of structuring the same bag of events over time (20)

PDF
SNOW_WWW
PDF
EDF2014: Piek Vossen, Professor Computational Lexicology, VU University Amste...
PDF
Extracting intelligence from online news sources
PDF
Extracting intelligence from online news sources
PDF
Primary Sources For the 21st Century
PDF
Story Deduplication and Mutation with Antoine Amend and Andrew Morgan
PDF
NewsReader: Automating detective work
PPTX
Global Media Monitor - Marko Grobelnik
PDF
Entities, Time and Events in BiographyNet and NewsReader
PDF
Keynote: Global Media Monitoring - M. Grobelnik - ESWC SS 2014
PPTX
Contemporary Issues_Research Presentation
PDF
The Relevance of Events in News Articles
PPTX
Objectives 1.01 to_1.04[1]
PDF
Emergent Methods: Multilingual narrative tracking in the news - real-time exp...
PPTX
Generating Storylines (Literature Survey)
PDF
Samos Summit 2013 ARCOMEM - The Journalistic approach
PDF
A presentation of the ARCHIVES Project to the ISCRAM-MED Conference
PPT
Workshop a way-of_applying_an_events_model_to_national_archives_data
PPTX
Archiving news on the Web through RSS flows. A new tool for studying interna...
PPTX
What is history
SNOW_WWW
EDF2014: Piek Vossen, Professor Computational Lexicology, VU University Amste...
Extracting intelligence from online news sources
Extracting intelligence from online news sources
Primary Sources For the 21st Century
Story Deduplication and Mutation with Antoine Amend and Andrew Morgan
NewsReader: Automating detective work
Global Media Monitor - Marko Grobelnik
Entities, Time and Events in BiographyNet and NewsReader
Keynote: Global Media Monitoring - M. Grobelnik - ESWC SS 2014
Contemporary Issues_Research Presentation
The Relevance of Events in News Articles
Objectives 1.01 to_1.04[1]
Emergent Methods: Multilingual narrative tracking in the news - real-time exp...
Generating Storylines (Literature Survey)
Samos Summit 2013 ARCOMEM - The Journalistic approach
A presentation of the ARCHIVES Project to the ISCRAM-MED Conference
Workshop a way-of_applying_an_events_model_to_national_archives_data
Archiving news on the Web through RSS flows. A new tool for studying interna...
What is history
Ad

More from Marieke van Erp (20)

PDF
Towards Culturally Aware AI Systems - TSDH Symposium
PDF
A Polyvocal and Contextualised Semantic Web
PDF
AI x Digital Humanities = > Inclusiviteit
PDF
Computationally Tracing Concepts Through Time and Space
PDF
The Hitchhiker's Guide to the Future of Digital Humanities
PDF
Why language technology can’t handle Game of Thrones (yet)
PDF
(Beyond) Combining Text and Tables for qualitative and quantitative research
PDF
Finding common ground between text, maps, and tables for quantitative and qua...
PDF
Slicing and Dicing a Newspaper Corpus for Historical Ecology Research
PDF
Lessons Learnt from the Named Entity rEcognition and Linking (NEEL) Challenge...
PDF
Good Lynx, bad Lynx: Document enrichment for historical ecologists
PDF
Towards Semantic Enrichment of Newspapers: a historical ecology use case
PDF
Natural Language Processing en Named Entity Recognition
PDF
HuC lecture - Digital and Humanities: Continuing the Conversation
PDF
Multilingual Fine-grained Entity Typing
PDF
Entity Typing Using Distributional Semantics and DBpedia
PDF
Entity Typing and Event Extraction
PDF
The domain as unifier, how focusing on social history can bring technical fie...
PDF
Evaluating entity linking an analysis of current benchmark datasets and a ro...
PDF
Evaluating Named Entity Recognition and Disambiguation in News and Tweets
Towards Culturally Aware AI Systems - TSDH Symposium
A Polyvocal and Contextualised Semantic Web
AI x Digital Humanities = > Inclusiviteit
Computationally Tracing Concepts Through Time and Space
The Hitchhiker's Guide to the Future of Digital Humanities
Why language technology can’t handle Game of Thrones (yet)
(Beyond) Combining Text and Tables for qualitative and quantitative research
Finding common ground between text, maps, and tables for quantitative and qua...
Slicing and Dicing a Newspaper Corpus for Historical Ecology Research
Lessons Learnt from the Named Entity rEcognition and Linking (NEEL) Challenge...
Good Lynx, bad Lynx: Document enrichment for historical ecologists
Towards Semantic Enrichment of Newspapers: a historical ecology use case
Natural Language Processing en Named Entity Recognition
HuC lecture - Digital and Humanities: Continuing the Conversation
Multilingual Fine-grained Entity Typing
Entity Typing Using Distributional Semantics and DBpedia
Entity Typing and Event Extraction
The domain as unifier, how focusing on social history can bring technical fie...
Evaluating entity linking an analysis of current benchmark datasets and a ro...
Evaluating Named Entity Recognition and Disambiguation in News and Tweets
Ad

Recently uploaded (20)

PDF
Assigned Numbers - 2025 - Bluetooth® Document
PDF
Getting Started with Data Integration: FME Form 101
PDF
Build a system with the filesystem maintained by OSTree @ COSCUP 2025
PPTX
Big Data Technologies - Introduction.pptx
PPTX
MYSQL Presentation for SQL database connectivity
PDF
Network Security Unit 5.pdf for BCA BBA.
PDF
Per capita expenditure prediction using model stacking based on satellite ima...
PDF
gpt5_lecture_notes_comprehensive_20250812015547.pdf
PPTX
Digital-Transformation-Roadmap-for-Companies.pptx
PDF
The Rise and Fall of 3GPP – Time for a Sabbatical?
PPTX
20250228 LYD VKU AI Blended-Learning.pptx
PDF
Spectral efficient network and resource selection model in 5G networks
PPTX
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
PDF
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
PPTX
Spectroscopy.pptx food analysis technology
PDF
cuic standard and advanced reporting.pdf
PDF
Dropbox Q2 2025 Financial Results & Investor Presentation
PPT
“AI and Expert System Decision Support & Business Intelligence Systems”
PDF
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
PDF
Mobile App Security Testing_ A Comprehensive Guide.pdf
Assigned Numbers - 2025 - Bluetooth® Document
Getting Started with Data Integration: FME Form 101
Build a system with the filesystem maintained by OSTree @ COSCUP 2025
Big Data Technologies - Introduction.pptx
MYSQL Presentation for SQL database connectivity
Network Security Unit 5.pdf for BCA BBA.
Per capita expenditure prediction using model stacking based on satellite ima...
gpt5_lecture_notes_comprehensive_20250812015547.pdf
Digital-Transformation-Roadmap-for-Companies.pptx
The Rise and Fall of 3GPP – Time for a Sabbatical?
20250228 LYD VKU AI Blended-Learning.pptx
Spectral efficient network and resource selection model in 5G networks
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
Spectroscopy.pptx food analysis technology
cuic standard and advanced reporting.pdf
Dropbox Q2 2025 Financial Results & Investor Presentation
“AI and Expert System Decision Support & Business Intelligence Systems”
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
Mobile App Security Testing_ A Comprehensive Guide.pdf

From Events to Stories: Different ways of structuring the same bag of events over time