2/24(Wed) - PowerPoint Presentation
Upcoming SlideShare
Loading in...5
×
 

2/24(Wed) - PowerPoint Presentation

on

  • 1,654 views

 

Statistics

Views

Total Views
1,654
Slideshare-icon Views on SlideShare
1,654
Embed Views
0

Actions

Likes
0
Downloads
10
Comments
0

0 Embeds 0

No embeds

Accessibility

Categories

Upload Details

Uploaded via as Microsoft PowerPoint

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

    2/24(Wed) - PowerPoint Presentation 2/24(Wed) - PowerPoint Presentation Presentation Transcript

    • Mobile Ontology Cloud- Semantic Post-IT-
      IT Life and Ontology
      Key-Sun Choi (kschoi@kaist.edu)
      http://kschoi.kaist.ac.kr/
      CILab & Semantic Web Research
    • 1st day: what we will learn
      )
      • What is Semantic Post-it? (15 min)
      • Demo and Downloadable (5 min)
      • Enabling Technologies (15 min)
      • APIs for Technologies (5 min)
      • ontocore.org (what you can do),
      • Protégé API
      • Remaining in your home
      • References to read and to use
    • What is Semantic Post-it?: Contents
      • As Mobile App
      • Personal Ontology Editors
      • Benefits when interpreting the input messages
    • Introduction
      What is the Semantic Post-It?
      • A system that maps personal randomized message into well-organized personal information space based on collective intelligence.
      • Personal randomized message
      • Organizing by interpreting messages
      • Table information extraction from text
      • Relevant table information grouping
      • Personal information space
      • Usage of ontology that user can edit
      • Collective intelligence
      • Usage of pivot ontology based on Wikipedia (web-based encyclopedia that anyone can edit)
    • Windows Mobile
      isDevelopedBy
      Microsoft
      Windows Mobile
      isDevelopedBy
      Microsoft
      Omnia 2
      ISA
      smartphone
      Omnia 2
      ISA
      smartphone
      Flash memory
      ISA
      computer storage
      Flash memory
      ISA
      computer storage
      Omnia 2
      hasOS
      Windows Mobile
      Omnia 2
      hasOS
      Windows Mobile
      Omnia 2
      hasMemory
      Flash memory
      Omnia 2
      hasMemory
      Flash memory
      Introduction
      A working flow of Semantic Post-It
      Omnia 2 is a multimedia smartphone announced at Samsung. Omnia 2 runs Windows Mobile and comes with flash memory..
      Contents Space
      Flash memory is a non-volatile computer storage that
      can be electrically erased and reprogrammed.
      Windows Mobile is a compact mobile operating system developed by Microsoft
      Omnia 2 is a multimedia smartphone announced at Samsung. Omnia 2 runs Windows Mobile and comes with flash memory..
      Message Space
      Triple Message Space
      (Table information)
      hasMemory
      hasOS
      Linked Triple Message Space
    • Motivation
      Motivating Scenario
      Reading an article on “Omnia 2”
      Another similar Smartphone?
      More details on OS
      What is the recent trend of it?
      Company in competition
      What should we do?
    • Motivation
      Motivating Scenario
      CPU clock
      Reading an article on “Omnia 2”
      Another similar Smartphone?
      OS, platform
      More details on OS
      What is the recent trend of it?
      Manufacturer, design
      Company in competition
      Products of the company
      We have to think of what type of information are involved
    • Motivation
      Motivating Scenario
      nationality
      Reading an article on “Immanuel Kant”
      Where is he from?
      ?
      ?
      ?
      If new to philosophers,
      we are likely to have no idea about relevant information
    • Motivation
      What is the solution?
      • We need a system that retrieves relevant information
      • Data set that specifies attributes for each concepts is needed
      • Smartphone : manufacturer, OS, memory, …
      • Philosophers : nationality, follower, teacher, …
      • However, no one guy can describe every concepts
      • We can obtain the data set from collective intelligence
      author
      politician
      scientist
      engineer
      Philosophers
      Artist
    • Established
      February 16, 1971
      Type
      Government-run
      President
      Nam-Pyo Suh


      Motivation
      Wikipedia
      Wikipedia documents (2010/01/29)
      3,175,836 (ENG) - 11,527,437 users
      125,801 (KOR) - 100,498 users



      ① Inter-page link
      ② Inter-Language link
      ③ Category
      ④ Infobox: table information

    • Background Technologies
      New paradigm
      • A few years have passed since a new paradigm was introduced.
      • Semantic Web
      • A machine-readable web
      • Ontology
      • A formal specification of knowledge
    • Background Technologies
      Semantic Web
      • An evolving development of the World Wide Web
      • The meaning (semantics) of information and services on the web is defined
      • For the web to "understand" and satisfy the requests of people and machines to use the web content
      Our focus
      Adapted from Wikipedia
      (http://en.wikipedia.org/wiki/Semantic_Web)
    • Background Technologies
      RDF
      • Resource Description Framework
      A Wikipedia article about Tony Benn
      <http://en.wikipedia.org/wiki/Tony_Benn> <http://purl.org/dc/elements/1.1/title> "Tony Benn" .
      <http://en.wikipedia.org/wiki/Tony_Benn> <http://purl.org/dc/elements/1.1/publisher> "Wikipedia" .
      <rdf:RDF
      xmlns:rdf=http://www.w3.org/1999/02/22-rdf-syntax-ns#
      xmlns:dc=http://purl.org/dc/elements/1.1/>
      <rdf:Descriptionrdf:about=http://en.wikipedia.org/wiki/Tony_Benn>
      <dc:title>Tony Benn</dc:title>
      <dc:publisher>Wikipedia</dc:publisher>
      </rdf:Description>
      </rdf:RDF>
      An expression of “triple”
      Adapted from Wikipedia
      (http://en.wikipedia.org/wiki/Resource_Description_Framework)
    • Background Technologies
      Ontology
      A formal specification of knowledge to be interpreted by computers
      Company
      isManufacturedBy
      supportSoftware
      OS
      releaseDate
      rdfs:subPropertyOf
      runsOn
      cameraPixelOf
      Mobile Phone
      hasMemorySize
      supportOnlineSoftware
      hasWebsite
      Mobile PhoneSoftware
      rdfs:subClassOf
      rdfs:subClassOf
      rdfs:subClassOf
      PDA
      Cellular
      Phone
      SmartPhone
      Cellular
      Phone
      Smart Phone
      PDA
      Schema
      Instance
      releaseDate
      2008
      Samsung
      i900 Omnia
      cameraPixelOf
      5 megapixels
      supportOnlineSoftware
      hasWebsite
      Skype
      www.skype.com
      hasMemorySize
      128 MB
      runsOn
      Windows
      Mobile 6.1
      isManufacturedBy
      Samsung
    • Illustrative Example
      Content Space -> Message Space
      Semantic Post-It
      (Message List)
      Typical Web Browser
      External Contents
      KAIST is located in Daejeon, South Korea. KAIST was established by Korean government in 1971
      Scrap
      Related Problems : Mash-Up
      How to extract text from heterogeneous contents (in a context, not a scientific issue)
    • Illustrative Example
      Message Space -> Triple Message Space (1/2)
      Semantic Post-It
      (Message List)
      Semantic Post-It
      (Detail View)
      Semantic Post-It
      (Detail View)
      KAIST is located in Daejeon, South Korea. KAIST was established by Korean government in 1971
      KAIST is located in Daejeon, South Korea. KAIST was established by Korean government in 1971.… The current KAIST President Nam Pyo Suhtaught for…
      KAIST is located in Daejeon, South Korea. KAIST was established by Korean government in 1971.… The current KAIST President Nam Pyo Suhtaught for…
      Person
      Smatphone’s UI is limited. Information should be shown by one-click.
      Related Problems : ISA relation recognition
    • Estabilshed
      1971
      Province
      Daejeon
      Country
      South Korea


      Illustrative Example
      Message Space -> Triple Message Space(2/2)
      Semantic Post-It
      (Table View)
      Semantic Post-It
      (Message List)
      Semantic Post-It
      (Message View)
      KAIST is located in Daejeon, South Korea. KAIST was established by Korean government in 1971
      KAIST is located in Daejeon, South Korea. KAIST was established by Korean government in 1971.… The current KAIST President Nam Pyo Suhtaught for…
      KAIST
      Summarization
      Display size is too small to do full browsing.
      Related Problems : Triple extraction from text
    • Illustrative Example
      Triple Message Space ->Linked Triple Message Space
      Semantic Post-It
      (Graph View)
      Semantic Post-It
      (Message List)
      Semantic Post-It
      (Message View)
      Suh was born in Korea on April 22, 1936, and immigrated to the U.S. in 1954….
      KAIST is located in Daejeon, South Korea. KAIST was established by Korean government in 1971
      KAIST is located in Daejeon, South Korea. KAIST was established by Korean government in 1971.… The current KAIST President Nam Pyo Suhtaught for…
      president
      KAIST is located in Daedeok…
      province
      Daejeon is a center of transportation in South Korea, where two major,
      Relevant messages
      Display size is too small to show text
      Related Problems : Relevant keyword search by traversing Ontology
    • Illustrative Example
      Linked Triple Message Space
      Semantic Post-It
      (Using Ontology 1)
      Semantic Post-It
      (Using Ontology 2)
      Ontology 1
      Ontology 2
      Suh was born in Korea on April 22, 1936, and immigrated to the U.S. in 1954….
      Suh was born in Korea on April 22, 1936, and immigrated to the U.S. in 1954….
      University
      University
      president
      president
      president
      president
      KAIST is located in Daedeok…
      KAIST is located in Daedeok…
      Person
      Person
      province
      province
      province
      locatedAt
      Settlement
      Country
      Daejeon is a center of transportation in South Korea, where two major,
      South Korea is a presidential republic consisting of 16 administrative…
      Related Problems : Personal ontology editing, logical consistency checking
    • Illustrative Example
      Personal Ontology Editor
      • Rename the property name
      • If you wish to see another label in the link
      • Ex) isManufacturedBy -> manufacturer
      • Modify constraints
      • If you wish to see the country name rather than the city name
      • Ex)
      • Remove : University-province-Settlement
      • Add : University-locatedAt-Country
      • Use the modified ontology in your Semantic Post-It
      How to embed this complex UI into Smartphone?
      http://protege.stanford.edu/
    • System architecture (1/2)
      Message Interpretation Services
      HTTP request
      Semantic Post-IT Server
      (HTTP server)
      Semantic Post-IT client
      TABLEGEN
      CAT2ISA
      HTTP response
      Ontology Access
      DBpedia Access
      Personal Ontology
      Local Message DB
      External Message Service
      System Message DB
      Twitter, Blog, Email, Calendar, …
    • System architecture (2/2)
      Semantic Post-IT client
      • Local Message DB controller
      • Message input interface
      • Message list viewer
      • HTTP service controller
      • Semantic Post-IT server
      • External message service
      • Message relation graph viewer
      • Personal ontology editor
      Semantic Post-IT client
      Personal Ontology
      Local Message DB
    • Demo and Downloadable
      http://swrc.kaist.ac.kr/SemanticToolkits/
    • What is Semantic Post-It?
      Memo Admin Service
      Evernote, quickies, etc.
      Semantic Service Mash-Up
    • Semantic Service Mash-up
      Definition of 3 types of applications
      Type 1 Application: Information zooming on specific ‘word’ of a memo
      Type 2 Application: Memo Contents Analysis
      Type 3 Application: Information zooming on whole context of a memo
    • Type 1 Application: Example
      DEMO: Semantic Post-It
    • Type 2 Application: Demo
      DEMO: Semantic Post-It
    • Type 3 Application: Demo
      DEMO: Semantic Post-It
    • Structure of Semantic Post-It
      Post-It Server
      Post-It Client
      Service
      Repository
      Communication between
      Server and Client
      Provide application List
      Application Install
      Request for new application
      Execute
      application
      Request
      Ontology
      Ontology Request Module
      Enterprise Part:
      Add-on of
      Semantic Applications
      Shared Memo Request Module
      Return shared memos which the client have requested
      Can download shared memo to local database
      Request
      Shared Memo
      Add new memo
      Delete memo
      Find
      Related
      Memo
      Change memo
      Synchronization Module
      • Synchronization between Server & Client
      Tag memo
      Synchroni-zation
      Attach ontology to memo
      Shared
      Memo
      Ontology
      Repository
      Local File System
      Personal
      Memos
      Wikipedia Documents
      PURE PART
    • Support for Semantic Post-It:OntoCloud
      Ontology derived from Wikipedia infoboxes
      Official Website:http://swrc.kaist.ac.kr/ontocloud/
    • Support for Type 2 Application:Semantic Annotation
      One of possible type 2 application: Table-form summary generator
      Semantic Annotation: Mark on the documents – ‘which part’ could be transformed into table?
    • Semantic Annotation Toolkit: COAT
      DEMO: COAT
    • From annotated data to Application: Machine Learning Feature
      Support Vector Machine(SVM)
    • Ontology Feature
      Modern GSM-based BlackBerry handhelds incorporate an ARM 7 or 9 processor, while older BlackBerry 950 and 957 handheldsused Intel 80386 processors.
      IT Ontology Package
      Gathering semantic Info
      Using Ontology
      CPU
      Intel 80386
      Modern GSM-based BlackBerry handhelds incorporate an ARM 7 or 9 processor, while older BlackBerry 950 and 957 handheldsused Intel 80386 processors.
      useCPU
    • Data Authority Policy
      Annotators can check his/her documents ONLY!
      To prevent cheating
      Simple annotation data viewer is available
      For administrators
      DEMO: COAT Viewer
    • Support for Type 3 Application:300M Wikipedia articles into Database
      Provide baseline for shared memo
      For type 3 application
      Build shared memo database with 300M wikipedia articles as its part
    • Screenshots
      3) Table information extraction
      1) User inputs message
      2) Ontology recommendation
      4) Relevant message grouping
    • Enabling Technologies
      • CAT2ISA
      • Table Generator  
    • Technologies
      Ontology expression
      OWL (Web Ontology Language)
      <owl:Class rdf:ID=“Mobile Phone"/>
      <owl:Class rdf:ID=“PDA">
      <rdfs:subClassOf rdf:resource=“# Mobile Phone"/>
      </owl:Class>
      <owl:Class rdf:ID=“SmartPhone">
      <rdfs:subClassOf rdf:resource="# Mobile Phone"/>
      </owl:Class>
      <owl:Class rdf:ID=“Cellular Phone">
      <rdfs:subClassOf rdf:resource="# Mobile Phone"/>
      </owl:Class>
      <owl:Class rdf:ID=“Mobile Phone Software"/>
      <owl:ObjectProperty rdf:ID=“hasSoftware">
      <rdfs:domain rdf:resource="#Mobile Phone”/>
      <rdfs:range rdf:resource=“# Mobile Phone Software"/>
      </owl:ObjectProperty>
      <owl:ObjectProperty rdf:ID=“hasOnlineSoftware">
      <rdfs:subPropertyOf rdf:resource=“#hasSoftware"/>
      </owl:ObjectProperty>
    • Technologies
      Ontology inference
      Text
      Text
      Samsung releases Omnia
      Text
      Apple releases
      iPhone
      IPTV service is launched
      Environmental
      Technology
      Apple supports Green technologies
      support
      ISA
      beginService
      Service
      TV Service
      Company
      instanceOf
      instanceOf
      instanceOf
      manufacture
      use
      instanceOf
      Samsung
      Apple
      Product
      instanceOf
      beginService
      Green
      Technology
      IPTV
      support
      manufacture
      manufacture
      ISA
      ISA
      HDTV
      Device
      Omnia
      Software
      ISA
      instanceOf
      iPhone
      Smartphone
      instanceOf
    • Technologies
      Ontology construction from Wikipedia Infobox
      class
      instance
      properties
      university
    • Technologies
      Ontology construction from text
      2. Taxonomy Construction
      is-a
      3. Relation Addition
      not is-a
      1. Term extraction and conceptualization
      The other
      Final Ontology
      Existing Ontology
      Part-of
      equipment-of
      4. Integration
      5. Verification
      Part-of
      equipment-of
    • Technologies
      COAT (CoreOnto Annotation Toolkit)
      • Term and relation annotation
    • Technologies
      Ontology construction cost reduction
      Improve Ontology extension tech. and automation
      Web-scale annotation by ontology extension tech.
      2
      Ontology extension cost reduction by automation
      1
      Devise ontology extension tech.
      Cost reduction
      • Manual annotation cost reduction by using COAT
      • Further reduction could be possible if we can automate the process
      COAT
      Auto
      COAT
      Before COAT
    • CAT2ISA (cdh4696@world.kaist)
      • Technology for expanding semantic infrastructure
      • Extract semantic information from anonymous category system
    • CAT2ISA
      • Extract isa/instanceOf relation
      • A instanceOf B: A is a member of set B
      • A is called 'instance', B is called 'concept'
      • A and B must share 'essential properties': Properties that makes something as itself
      • Example: <Key-Sun Choi, instanceOf, Professor>: X<Key-Sun Choi, instanceOf, Human>: O
      • B isa C: B is a subset of C
       
      • isa/instanceOf relation: vital component in many semantic applications(e.g. semantic search, Q&A system, etc.)
       
       
    • Table Generator (cdh)
      • Summarize a text into table format based on its semantic tag
    • Table Generator
      • Information extraction using "Ontology"
      • Ontology: Formal representation of a set of concepts within a domain and the relationships between those concepts
      • Ontology-based information extraction:
    • Remaining for your home: references
      • History of Word Wide Web
      • Berners-Lee, Tim; Fischetti, Mark (1999). Weaving the Web. HarperSanFrancisco.
      • The Semantic Web
      • Berners-Lee, Tim; James Hendler and Ora Lassila (May 17, 2001). "The Semantic Web". Scientific American Magazine.
      • Grigoris Antoniou, Frank van Harmelen (March 31, 2008). A Semantic Web Primer, 2nd Edition
      • Ontology
      • Dean Allemang, James Hendler (May 9, 2008). Semantic Web for the Working Ontologist: Effective Modeling in RDFS and OWL. Morgan Kaufmann
    • Remaining for your home: Use experiences
      • [1] P. Mistry, P. Maes. Quickies: Intelligent Sticky Notes. In the Proceedings of 4th International Conference on Intelligent Environments (IE08). Seattle, USA. 2008
      • [2] Max Van Kleek, Michael Bernstein, Katrina Panovich, Greg Vargas, David Karger, and mc schraefel, Note-to-Self: Examining Personal Information Keeping in a Lightweight Note-Taking Tool.. CHI, 2009
      • [3] The Tabulator, http://www.w3.org/2005/ajar/tab
      • Read [1,2,3] and use the system [2,3]
      • Try also the following system
      • http://www.evernote.com/
      • Smartphone version is available
    • 2nd day
      • Deep story about semantic technology (20 min)
      • Wikipedia DbpediaOntocloud (kekeeo@world.kaist.ac.kr)
      • What are the upside?
      • Email 3.0
      • Information Zooming
      • Mobile hyperlink
      • Personal Preference Ontology and its use
      • Collective semantic intelligence of LOD + ontology cloud
      • Another demo (5 min)
      • What you can do immediately (review)
      • What you can contribute (review)
      • Big picture
      • Function, society
      • Technology to study
    • IT-Life Ontology
    • IT Campus Domain Ontology (Partial)
    • Wikipedia (http://en.wikipedia.org)
      • What is Wikipedia?
      • An online, collaboratively edited encyclopedia
      • Articles are available in over 250 languages
      • Freely available and freely distributable
      • Inter-language (interwiki) page links
    • DBpedia (http://dbpedia.org)
      • What is the DBpedia?
      • A community effort to extract structured information from Wikipedia
      • Available on the Web
      • Different types of structured information 
      • Infobox templates: summaries of the most relevant facts contained in an article
      • Categorization information
      • Images
      • Geo-coordinates
      • Links to external Web pages
    • OntoCloud
      • Our own constructed Ontology
      • Goals 
      • Making more intelligent IT systems focusing on devices and resources
      • Key classes
      • Device, Product, Resource, Technology, Person and Company
    • Structure of OntoCloud
      •  Template Ontology
      • Constructing the Pivot dataset
      • The infobox dataset from DBpedia3.4 (semi-automated)
      • IT CUO (IT Core Upper Ontology)
      • A middle level ontology for integration
      • Ontologies under IT domains
      • IT Service Ontology
      • IT Device Ontology
      • IT Core Ontology 
    • Mobile 3.0 and its Requirements (full picture: jha)
      • Email 3.0
      • Information Zooming
      • Mobile hyperlink
      • Personal Preference Ontology and its use
      • Collective semantic intelligence of LOD + ontology cloud
    • E-mail 3.0(email categorization)
      Automatically map into a class in ontology
      Related Problems
      • Topic detection
      Current Status
      • Categorization of long and well-formed text (e.g. Wikipedia documents)
      Challenges
      • Short message interpretation
      • Personal writing styles
    • E-mail 3.0(Recipient recommendation)
      Automatically recommend person to whom the message should be sent
      sender@abc.com
      Challenges
      • Task Ontology modeling
    • E-mail 3.0(Relevant information attachment)
      Automatically attach pictures
      sender@abc.com
      Automatically attach files in local disk
      Challenges
      • Semantic tags on multimedia data
      • Local file indexing
      The Samsung Group is composed of numerous international affiliated businesses, most of them united under the Samsung brand including Samsung Electronics, the world's largest electronics company,
    • Topic
      Information retrieval
      Deadline
      Mar 30, 2010
      Organizer
      Benno Stein
      E-mail 3.0(Mash-up Services)
      A message in inbox
      Automatically create to-do list
      The following list organizes classic and ongoing topics from the field
      of text-based IR for which contributions are welcome:
      - Theory. Retrieval models, language models, similarity measures,
      formal analysis
      - Mining and Classification. Category formation, clustering, entity
      resolution, document classification
      ---------------------------------------------------------------------------
      Important Dates:
      ---------------------------------------------------------------------------
      Mar 30, 2010 Deadline for paper submission
      Apr 20, 2010 Notification to authors
      May 17, 2010 Camera-ready copy due
      Aug 30, 2010 Workshop opens
      ---------------------------------------------------------------------------
      Workshop Organization:
      ---------------------------------------------------------------------------
      Benno Stein, Bauhaus University Weimar
      Michael Granitzer, Know-Center Graz & Graz University of Technology
      Contact: tir@webis.de
      Information about the workshop can be found at http://www.tir.webis.de
      Related Problems:
      • Table information extraction
      • Mash-up
      Current Status
      • Table information generation from text
      Challenges
      • Table information generation from semi-structured text
    • Information Zooming
      •  What is information zooming?
      • Show small amount of information first
      • When user requires more information about one part, shows more detailed information about that part.
      • Why is it necessary?
      • Mobile environment: small display
      • We cannot show all the necessary information at once! (Lack of space)
    • Information Zooming in Semantic Post-It
      •  Information zooming for one word
       
       
       
       
       
       
      • Information zooming for whole memo
    • Mobile hyperlink
      •  What is mobile hyperlink?
      • Represent URL as barcode
      • Take a picture of the barcode using camera in cellphone and you move to that URL!
      •  Why is it necessary?
      • Mobile environment: small interface
      • Hard to type all the URL
      • Example of mobile hyperlink
       
       
      • QR code:
                                 
    • Personal Preference Ontology and its use
      • Task of packaging from a potentially large ontology, one or several significant sub-parts
      • Knowledge sharing and re-use crucial research issues
       
      • On-demand Extraction Service
      • Takes a concept and extract the relations
      •  
      • Interactive Service
      • The user have to select class and relations to consider
    • Collective semantic intelligence of LOD + ontology cloud
    • The Linked Open Data Cloud
    • What you can do immediately
      review
      discussion
    • What you can contribute
      • Data Synchronization for Mobile applications
      • Synchronization is a data transfer between computer and mobile device that aims to keep both of components in a coherent state
      • Knowledge-driven Security Handling for Mobile Applications
      • Several mobile applications attacks have beenrecently reported
      • Device  and environment
      • Ontology Packaging for Mobile field
      • Bacause of its physical aspect, a mobile device has a limited processing and computing capabilities
    • Big picture
      • Function, society and Technology to study
    • Windows Mobile
      isDevelopedBy
      Microsoft
      Windows Mobile
      isDevelopedBy
      Microsoft
      Omnia 2
      ISA
      smartphone
      Omnia 2
      ISA
      smartphone
      Flash memory
      ISA
      computer storage
      Flash memory
      ISA
      computer storage
      Omnia 2
      hasOS
      Windows Mobile
      Omnia 2
      hasOS
      Windows Mobile
      Omnia 2
      hasMemory
      Flash memory
      Omnia 2
      hasMemory
      Flash memory
      Big Picture
      A working flow of Semantic Post-It
      Contents Space
      Omnia 2 is a multimedia smartphone announced at Samsung. Omnia 2 runs Windows Mobile and comes with flash memory..
      Flash memory is a non-volatile computer storage that
      can be electrically erased and reprogrammed.
      Windows Mobile is a compact mobile operating system developed by Microsoft
      Message Space
      Omnia 2 is a multimedia smartphone announced at Samsung. Omnia 2 runs Windows Mobile and comes with flash memory..
      Triple Message Space
      (Table information)
      Linked Triple Message Space
      hasMemory
      hasOS
      What is the next step?
    • Windows Mobile
      isDevelopedBy
      Microsoft
      Omnia 2
      ISA
      smartphone
      Flash memory
      ISA
      computer storage
      Omnia 2
      hasOS
      Windows Mobile
      Omnia 2
      hasMemory
      Flash memory
      Big Picture
      Message generation
      Linked Triple Message Space
      hasMemory
      hasOS
      Personalized Message Space
      Omnia 2 is a multimedia smartphone announced at Samsung. Omnia 2 runs Windows Mobile developed by Microsoft and comes with flash memory which is a computer storage.
      How to do so?
      Do you have an idea how to utilize personalized ontology to generate sentences?
      Personalized ontology
    • Established
      1971
      Province
      Daejeon
      Country
      South Korea


      Big Picture
      Functions (1/2)
      • From text to presentation file
      • Challenges
      • Semantic Tagging to Image
      • Refer to http://www.image-net.org/
      KAIST is located in Daejeon, South Korea. KAIST was established by Korean government in 1971
      KAIST
      established
      1971
      province
      Daejeon
      Country
      South Korea
      Table information
      Table information + images
    • Big Picture
      Functions (2/2)
      • From table to text
      • Generate NL text by traversing table
      • KAIST-Province-Daejeon
      • Daejeon-Districts-fifth
      •  KAIST is located in Daejeon. Daejeon is the fifth largest city in the country.
      • Challenges
      • Transform a predicate into verb phrases
      • Ex) Province -> is located in
    • Big Picture
      Society
      Message Interpretation Services
      HTTP request
      Semantic Post-IT Server
      (HTTP server)
      Semantic Post-IT client
      TABLEGEN
      CAT2ISA
      HTTP response
      Personal Ontology
      Ontology Access
      DBpedia Access
      Local Message DB
      OpenAPI generator
      Make your own message interpretation modules and upload it.
      OpenAPI generator will make it available as an OpenAPI service.
    • Big Picture
      Technologies to study(interdisciplinary)
      Architecture
      /Urban design
      Software Engineering
      Graphics
      IR, AI, MachineLearning
      HCI
      CognitiveScience
      Internet of Things
      Cloud Computing
      Design
      DB &
      Data Mining
      ConvergenceNetworks
      Sociology
      Middleware
      Handle huge amount of messages
      Ex) manipulating Wikipedia documents
      Find person of my interests
      Ex) References in papers
      Which layout is suitable for the display?
      Ex) Table-memo for a tiny display
      Plug-in architecture
      Ex) Collect personal documents by using Google Desktop APIs
      How to extract table data from memo?
      Ex) information extraction from document
      Which type of memo? Writing style anaylsys
      Ex) To-do list, contact, documents
      Write message anywhere and anytime
      Ex) RFID-equipped notes
    • Deep story about semantic technology
      discussion!
    • Credits
      Dong-Hyun Choi, cdh4696@world.kaist.ac.kr
      Eun-Kyung Kim, kekeeo@world.kaist.ac.kr
      JinhyunAhn, jhahn@world.kaist.ac.kr
      Key-Sun Choi, kschoi@kaist.edu
      http://swrc.kaist.ac.kr/ontocloud
      http://swrc.kaist.ac.kr/SemanticToolkits/