SlideShare uma empresa Scribd logo
1 de 30
Baixar para ler offline
KAIST Education for the World, Research for the Future




  인간의 경험 공유를 위한
태스크 및 컨텍스트 추출 및 표현

        2012. 11. 29


          류지희

     웹사이언스공학 전공

   정보검색 및 자연어처리 연구실
Why Human Experience Sharing?
   Necessity of Experiential Problem Solving Knowledge




2                     © 2012 IR&NLP Lab. All rights reserved.
A. Change a Flat Tire When
                                   You Are a Woman Alone

                                         1. Loosen lug nuts on tire.

                                             2. Install spare tire.




user
           User Context Info
                                B. Change a Tire like a Real
                                   Woman
  [On U.S. highway]
                                                   1. Call AAA.
  [1 year driving experience]
                                           2. Be placed on “hold”.
  [Heading to New York]
  [Female]


       3                        © 2012 IR&NLP Lab. All rights reserved.
Experience Mining
   Building a Relational Knowledge about Experiences
                                     Experiential Knowledge Distillation

                            Web

                                                                                          Context-anchored

                     Experiential
                                                                                            Experiential
                     Sentences &
                                                                                            Knowledge
                       Context
                Automatic extraction
                                                                                    Aggregation & abstraction
    Event          People             Place           Time                 Event           People          Place     Time
Play Soccer       Yongho, …         Expo Park      2011-08-10              (Type)          (Type)         (Type)    (Type)
Play Baseball     Chulsoo, …       Gapchun Park    2009-09-02              (Sport)        (student)       (Park)   (Summer)
                               …                                                                      …

4                                               © 2012 IR&NLP Lab. All rights reserved.
From What?
   Various types of open contents on the Web!

       How-to                     Blog                           Microblog
       articles                   posts                            posts



       Human Task            Event Context                      Place Semantics
         mining                 mining                              mining




                             Human
                          Experiential KB

5                     © 2012 IR&NLP Lab. All rights reserved.
Human Task Mining




6    © 2012 IR&NLP Lab. All rights reserved.
Human Task Model
     Topic


    hasTopic


     Goal


hasAction

               hasNextAction
    Action



hasObject           hasTime     hasLocation


    Object            Time        Location



7                              © 2012 IR&NLP Lab. All rights reserved.
Human Task Extraction
                                                                                                                     Goal
Title   How to Make Omelet Soup                                                    Make Omelet Soup

                                                                                                     Action Sequence
Step 1 Place the water or canned chicken broth
        in a large saucepan.                                               (place, water)           (place, broth)

        Boil the sweet yellow onion for several                                       (boil, onion)
        minutes.
                                                                                      (add, broth)
Step 2 Add the powdered chicken broth along
                                                                                      (boil, soup)
        with the canned mushrooms.
                                                                                      (add, onion)
        Boil the soup for a few more minutes,
        and then add the chopped green onion.                                         (drop, egg)

Step 3 Drop the eggs into the simmering broth                                                            Ingredients
        a few minutes before you're ready to                               water                            broth
        serve the omelet soup.                                             soup             onion            egg


 8                               © 2012 IR&NLP Lab. All rights reserved.
Hybrid Extraction Method
                         Eat fruit every day.
      Sentences           Turn off the car.                           (eat, fruit)
                                                                    (turn off, car)

    Retrieve and apply                                  Yes            Extract
                                    Matched?
           a rule                                                verb and ingredients
                                          No                                   Yes
                                 Select the best
    Syntactic Patterns                                            Prob. > threshold
                                 label sequence



                                   CRFs Model




9                                    © 2012 IR&NLP Lab. All rights reserved.
Next Challenging Issues
    A large fraction of sentences (more than 40%) in how-to instructions are
     not imperative sentences.
    Difficulties arising from variations in writing        Case      Percentage
        Scoping ambiguity                                                             Scoping
            E.g. Clear or glitter nail polish should go on the nails.                                13.9%
                                                                                      Ambiguity
        Anaphora                                                                     Anaphora        13.1%
            E.g. Make it fun and unique                                              Condition       11.9%
        Condition                                                                      Ellipsis      1.9%
            E.g. If your computers are only a few years old                           Implicit
                                                                                                      1.3%
        Ellipsis                                                                      meaning
            E.g. So why don't you?                                                  Grammatical
                                                                                                      1.3%
        Implicit meaning                                                              mistake
            E.g. Studying improves grades. (Study hard!)                                 Etc.        56.6%
        Grammatical mistake                                                            Case Percentage in
                                                                                         all the clauses in
            E.g. IM a friend! (Make friend relationship in a instance messenger)      30 sample documents
10                                         © 2012 IR&NLP Lab. All rights reserved.
Feature Sets
Feature Type     Feature Name                                      Feature Values
                  Clause Type                                 main, subordinate
                    Person                        1st person, 2nd person, 3rd person
     Syntactic   Auxiliary Verb                  will, shall, can, may, must, able to, …
     Features        Voice                                    active, passive, n/a
                     Tense                                  past, present, future
                    Polarity                               negated, non-negated

Feature Type     Feature Name                                        Examples

                  Obligation                • You have to ask about the car.

                  Permission                • You can search for the world weather.
     Modality
     Features
                  Explanation               • The cost for delivery is already included.

                  Supposition               • You will have access to the weather.

11                       © 2012 IR&NLP Lab. All rights reserved.
Result: Actionable Clause Detection
      Task                Used Feature Sets                        F1(NB)         F1(DT)       F1(SVM)

                      Syntactic Features
 Actionable                                                         0.933          0.942         0.948
                      (micro only)
   Clause
 Detection            + Modality Features
                                                                    0.862          0.963         0.966
                      (micro &macro)

     NB : Naï Bayes
            ve                       DT : Decision Tree                   SVM : Support Vector Machines




12                                   © 2012 IR&NLP Lab. All rights reserved.
Bridge to Semantic Web




     AcTN knowledge representation                                 YAGO knowledge representation
13                             © 2012 IR&NLP Lab. All rights reserved.
Changing Data Representation
     Current Form                                                Ultimate Target Form
     Refined tabular                                                Well-designed
      data records                                                 ontology entries
       [plain text]                                               [well-formed RDF]




14                     © 2012 IR&NLP Lab. All rights reserved.
Event Context Mining




15     © 2012 IR&NLP Lab. All rights reserved.
What is an Event?
    Events are defined as situations that happen
        Punctual (example 1-2) or last for a period of time (example 3-4)
        States in which something holds true (example 5)
    Examples
     Ferdinand Magellan, a Portuguese explorer, first reached the islands in search
                                                                                     (1)
     of spices.
     A fresh flow of lava, gas and debris erupted there Saturday.                     (2)
     11,024 people were evacuated to 18 disaster relief centers.                     (3)
     “We’re expecting a major eruption,” he said in a telephone interview early to
                                                                                     (4)
     day.
     Israel has been scrambling to buy more masks abroad, after a shortage of sev
                                                                                     (5)
     eral hundred thousand gas masks.



16                             © 2012 IR&NLP Lab. All rights reserved.
Event Expressions
    Event may be expressed in the following forms
            Type                                                Example

            Verb            A fresh flow of lava, gas and debris erupted there Saturday.

                            Israel will ask the United States to delay a military strike ag
            Noun            ainst Iraq until the Jewish state is fully prepared for a possib
                            le Iraqi attack.

                            A Philippine volcano, dormant for six centuries, began expl
          Adjective
                            oding with searing gases, thick ash and deadly debris.

                            “There is no reason why we would not be prepared,” Mord
      Predicative clause
                            echai told the Yediot Ahronot daily.

     Prepositional phrase   All 75 people on board the Aeroflot Airbus died.

17                             © 2012 IR&NLP Lab. All rights reserved.
Feature Sets
    Basic Features
        Named entity (NE) tags and an indication of whether the target
         noun is prenominal or not.
    Lexical Semantic Features (LS)
        The set of target nouns’ lemmas and their WordNet hypernyms
    Dependency-based Features (DF)
        Nouns become events if they occur with a certain surrounding
         context, namely, syntactic dependencies
        Dependency-based Features sometimes need to be combined
         with Lexical Semantic Features



18                         © 2012 IR&NLP Lab. All rights reserved.
Comparing with Previous Work
    An improvement of about 0.22 (precision) and 0.09 (recall)
     over the state-of-the-art, respectively.
                               Llorens et al. (2010)             Proposed Method

                                                                                     0.727
     Precision
                                                                                                    0.95


                                                                0.483
        Recall
                                                                         0.577


                                                                          0.584
           F1
                                                                                  0.718

                 0.00   0.10    0.20    0.30       0.40      0.50      0.60   0.70    0.80   0.90   1.00

19                                  © 2012 IR&NLP Lab. All rights reserved.
Place Semantics Mining




20      © 2012 IR&NLP Lab. All rights reserved.
Place Semantics
    AS GPS-enabled mobile devices have come into wide use,
     Location based services catch popularity
    But it is hard to provide appropriate context-aware
     services to users when the system only use user’s location,
     i.e. GPS(latitude, longitude)

    Contrary to location, Place is space where people impart a
     meaning
    If we know the meaning of the place, Place Semantics, we
     can serve much better suitable services to users


21                      © 2012 IR&NLP Lab. All rights reserved.
Motivation
    Scenario
     Recently, Lena moved to Korea from USA. She doesn’t know Korean culture and
     geography at all because she didn’t leave outside USA before.


     Is there similar places with Brooklyn Bowl that
     I often visited in order to relieve stress?


                                     How about Olympic Bowling Alley?


     No. Thanks! It’s NOT the place I wanted.


     Brooklyn Bowl is a bowling alley in New York City. People enjoy bowling, have a
     party, drink beer and hold a music event in Brooklyn Bowl.
22                            © 2012 IR&NLP Lab. All rights reserved.
Place Semantics Mining
    People leave texts about “why they visit, what they do” when
     they check-in at Place on Foursquare
    We can know the perception of places from those texts
    We apply LDA to extract Place Semantics
        A document is composed of texts written in a place.


                                                             “text”




                                                           Place



23                               © 2012 IR&NLP Lab. All rights reserved.
Similarity between Two Places
Is there similar places with Brooklyn Bowl that
I often visited in order to relieve stress?

                                     How about XL Night Club?


                             Brooklyn Bowl                                   XL Night Club

 Have a party & Drink beer
                                                                             41%
                       32%
 Enjoy a music show

 After work                                        27%

                  5%                                                    3%
 Eat food                                                                                    26%
                      7%
 Watch sports game
                           11%            18%                                30%
 Others

24                            © 2012 IR&NLP Lab. All rights reserved.
Concluding Remarks




25    © 2012 IR&NLP Lab. All rights reserved.
Application of Our Results
    Semantic Annotation
        Adds diversity and richness to text processing




26                          © 2012 IR&NLP Lab. All rights reserved.
Thank you!


27     © 2012 IR&NLP Lab. All rights reserved.
KAIST Education for the World, Research for the Future

    Jihee Ryu (jiheeryu@kaist.ac.kr)
              http://jihee.kr


   Yoonjae Jeong (hybris@kaist.ac.kr)




  Eunyoung Kim (ey_kim@kaist.ac.kr)




Sung-Hyon Myaeng (myaeng@kaist.ac.kr)
  http://ir.kaist.ac.kr/member/professor/


              IR&NLP Lab
            http://ir.kaist.ac.kr
Reference
1)    Jung, Y., Ryu, J., Kim, K., Myaeng, S.H.: Automatic Construction of a Large-Scale
      Situation Ontology by Mining How-to Instructions from the Web. Web Semantics:
      Science, Services and Agents on the World Wide Web (2010)
2)    Ryu, J., Jung, Y., Kim, K., Myaeng, S.H.: Automatic Extraction of Human Activity
      Knowledge from Method-Describing Web Articles. 1st Workshop on Automated
      Knowledge Base Construction (2010)
3)    Park, K.C., Jeong, Y., Myaeng, S.H.: Detecting Experiences from Weblogs. 48th
      Annual Meeting of the Association for Computational Linguistics (2010)
4)    Ryu, J., Jung, Y., Myaeng, S.H.: Actionable Clause Detection from Non-imperative
      Sentences in How-to Instructions: A Step for Actionable Information Extraction.
      15th International Conference on Text, Speech and Dialogue (2012)
5)    Jeong, Y., Myaeng, S.H.: Using Syntactic Dependencies and WordNet Classes for
      Noun Event Recognition. Workhop on Detection, Representation, and Exploitation
      of Events in the Semantic Web in conjunction with the 11th International Semantic
      Web Conference 2012 (2012)
6)    Carter, E., Donald, J.: Space and place: theories of identity and location. Lawrence
      & Wishart Ltd. (1993)

 29                              © 2012 IR&NLP Lab. All rights reserved.
Data Collection: How-to Articles
    General How-to Articles
        1,850,725 articles from eHow & 109,781 articles from wikiHow
             eHow Category Group                 # doc               wikiHow Category Group        # doc
     Computers & Software, Internet               323,289 Computers, Electronics                    18,265
     Home Building & Design & Safety              307,277 Family Life, Home, Pets, Relationships    18,220
     Culture, Holidays, Hobbies, Weddings         238,143 Hobbies, Holidays, Travel                 14,514
     Business, Investment, Personal Finance       153,458 Health, Sports                            14,161
     Arts, Entertainment, Music                   149,426 Youth                                      9,161
     Family, Parenting, Pets, Plants              135,909 Personal Care, Style                       7,031
     Cars, Car Repair                             108,386 Education, Communications                  6,775
     Healthcare, Fitness, Sports                  103,758 Finance, Business, Work                    6,729
     Education, Careers, Employment               103,717 Food, Entertaining                         6,099
     Electronics                                  101,403 Arts, Entertainment                        5,151
     Food, Recipes                                 63,553 Cars, Vehicles                             2,316
     Fashion, Beauty                               62,406 Philosophy, Religion                       1,359
     Total (As from December 2011)              1,850,725 Total (As from December 2011)            109,781

30                                     © 2012 IR&NLP Lab. All rights reserved.

Mais conteúdo relacionado

Destaque

Cappuccino 3 Slide Illustration
Cappuccino 3 Slide IllustrationCappuccino 3 Slide Illustration
Cappuccino 3 Slide IllustrationAshish Goel
 
Building high traffic http front-ends. theo schlossnagle. зал 1
Building high traffic http front-ends. theo schlossnagle. зал 1Building high traffic http front-ends. theo schlossnagle. зал 1
Building high traffic http front-ends. theo schlossnagle. зал 1rit2011
 
Social Media Benchmarking Report - preview of findings
Social Media Benchmarking Report - preview of findingsSocial Media Benchmarking Report - preview of findings
Social Media Benchmarking Report - preview of findingsB2B Marketing
 
CASE STUDY: Inbound: building trust into your marketing strategy
CASE STUDY: Inbound: building trust into your marketing strategyCASE STUDY: Inbound: building trust into your marketing strategy
CASE STUDY: Inbound: building trust into your marketing strategyB2B Marketing
 
модульное тестирование для Perl. алексей шруб. зал 4
модульное тестирование для Perl. алексей шруб. зал 4модульное тестирование для Perl. алексей шруб. зал 4
модульное тестирование для Perl. алексей шруб. зал 4rit2011
 

Destaque (6)

Cappuccino 3 Slide Illustration
Cappuccino 3 Slide IllustrationCappuccino 3 Slide Illustration
Cappuccino 3 Slide Illustration
 
Building high traffic http front-ends. theo schlossnagle. зал 1
Building high traffic http front-ends. theo schlossnagle. зал 1Building high traffic http front-ends. theo schlossnagle. зал 1
Building high traffic http front-ends. theo schlossnagle. зал 1
 
Social Media Benchmarking Report - preview of findings
Social Media Benchmarking Report - preview of findingsSocial Media Benchmarking Report - preview of findings
Social Media Benchmarking Report - preview of findings
 
The CMO 2.0
The CMO 2.0The CMO 2.0
The CMO 2.0
 
CASE STUDY: Inbound: building trust into your marketing strategy
CASE STUDY: Inbound: building trust into your marketing strategyCASE STUDY: Inbound: building trust into your marketing strategy
CASE STUDY: Inbound: building trust into your marketing strategy
 
модульное тестирование для Perl. алексей шруб. зал 4
модульное тестирование для Perl. алексей шруб. зал 4модульное тестирование для Perl. алексей шруб. зал 4
модульное тестирование для Perl. алексей шруб. зал 4
 

Semelhante a KAIST Education for Experiential Knowledge Mining

Eon nus hci_master_class
Eon nus hci_master_classEon nus hci_master_class
Eon nus hci_master_classTianwei_liu
 
EnglishCentral Presentation at KOTESOL 2012
EnglishCentral Presentation at KOTESOL 2012EnglishCentral Presentation at KOTESOL 2012
EnglishCentral Presentation at KOTESOL 2012English Central
 
Agile Business Analysis - The Key to Effective Requirements on Agile Projects
Agile Business Analysis - The Key to Effective Requirements on Agile ProjectsAgile Business Analysis - The Key to Effective Requirements on Agile Projects
Agile Business Analysis - The Key to Effective Requirements on Agile ProjectsLilian De Munno
 
Growing Talent for Tomorrow's Industries
Growing Talent for Tomorrow's IndustriesGrowing Talent for Tomorrow's Industries
Growing Talent for Tomorrow's IndustriesJames Ware, PhD
 
EESTEC Android Workshops - 101 Java, OOP and Introduction to Android
EESTEC Android Workshops - 101 Java, OOP and Introduction to AndroidEESTEC Android Workshops - 101 Java, OOP and Introduction to Android
EESTEC Android Workshops - 101 Java, OOP and Introduction to AndroidAntonis Kalipetis
 
AgileEE 2011: My Lightening Talk about "Definiton of READY"
AgileEE 2011: My Lightening Talk about "Definiton of READY"AgileEE 2011: My Lightening Talk about "Definiton of READY"
AgileEE 2011: My Lightening Talk about "Definiton of READY"Felix Ruessel
 
Introduction to Global English
Introduction to Global EnglishIntroduction to Global English
Introduction to Global EnglishJonn Kohl
 
How To Give A Good Presentation -- Getting Your Audience To Listen!
How To Give A Good Presentation -- Getting Your Audience To Listen!How To Give A Good Presentation -- Getting Your Audience To Listen!
How To Give A Good Presentation -- Getting Your Audience To Listen!Blue Elephant Consulting
 
eLearning Suite 6 Workflow
eLearning Suite 6 WorkfloweLearning Suite 6 Workflow
eLearning Suite 6 WorkflowKirsten Rourke
 
A vision workshop xp2012
A vision workshop xp2012A vision workshop xp2012
A vision workshop xp2012Bent_jensen
 
WorldSC Smartphones Applications Portfolio
WorldSC Smartphones Applications PortfolioWorldSC Smartphones Applications Portfolio
WorldSC Smartphones Applications PortfolioAhed Aladwan
 
Restructuring classes and behaviour
Restructuring classes and behaviourRestructuring classes and behaviour
Restructuring classes and behaviourWouter de Wild
 
Layar - Raimo at TNW 2011
Layar - Raimo at TNW 2011Layar - Raimo at TNW 2011
Layar - Raimo at TNW 2011Layar
 
Layar - Raimo at TNW 2011
Layar - Raimo at TNW 2011Layar - Raimo at TNW 2011
Layar - Raimo at TNW 2011Layar
 
Fast track to success in ones career
Fast track to success in ones careerFast track to success in ones career
Fast track to success in ones careeraiesechyderabad
 
Lightening Talk: definition of ready
Lightening Talk: definition of readyLightening Talk: definition of ready
Lightening Talk: definition of readyAgileee
 
A vision workshop xp2012
A vision workshop xp2012A vision workshop xp2012
A vision workshop xp2012BestBrains
 
In The Future We All Use Symfony2
In The Future We All Use Symfony2In The Future We All Use Symfony2
In The Future We All Use Symfony2Brent Shaffer
 
CIID Final project report
CIID Final project reportCIID Final project report
CIID Final project reporteilidh dickson
 
Introducing the FLUID Principles
Introducing the FLUID PrinciplesIntroducing the FLUID Principles
Introducing the FLUID PrinciplesKevlin Henney
 

Semelhante a KAIST Education for Experiential Knowledge Mining (20)

Eon nus hci_master_class
Eon nus hci_master_classEon nus hci_master_class
Eon nus hci_master_class
 
EnglishCentral Presentation at KOTESOL 2012
EnglishCentral Presentation at KOTESOL 2012EnglishCentral Presentation at KOTESOL 2012
EnglishCentral Presentation at KOTESOL 2012
 
Agile Business Analysis - The Key to Effective Requirements on Agile Projects
Agile Business Analysis - The Key to Effective Requirements on Agile ProjectsAgile Business Analysis - The Key to Effective Requirements on Agile Projects
Agile Business Analysis - The Key to Effective Requirements on Agile Projects
 
Growing Talent for Tomorrow's Industries
Growing Talent for Tomorrow's IndustriesGrowing Talent for Tomorrow's Industries
Growing Talent for Tomorrow's Industries
 
EESTEC Android Workshops - 101 Java, OOP and Introduction to Android
EESTEC Android Workshops - 101 Java, OOP and Introduction to AndroidEESTEC Android Workshops - 101 Java, OOP and Introduction to Android
EESTEC Android Workshops - 101 Java, OOP and Introduction to Android
 
AgileEE 2011: My Lightening Talk about "Definiton of READY"
AgileEE 2011: My Lightening Talk about "Definiton of READY"AgileEE 2011: My Lightening Talk about "Definiton of READY"
AgileEE 2011: My Lightening Talk about "Definiton of READY"
 
Introduction to Global English
Introduction to Global EnglishIntroduction to Global English
Introduction to Global English
 
How To Give A Good Presentation -- Getting Your Audience To Listen!
How To Give A Good Presentation -- Getting Your Audience To Listen!How To Give A Good Presentation -- Getting Your Audience To Listen!
How To Give A Good Presentation -- Getting Your Audience To Listen!
 
eLearning Suite 6 Workflow
eLearning Suite 6 WorkfloweLearning Suite 6 Workflow
eLearning Suite 6 Workflow
 
A vision workshop xp2012
A vision workshop xp2012A vision workshop xp2012
A vision workshop xp2012
 
WorldSC Smartphones Applications Portfolio
WorldSC Smartphones Applications PortfolioWorldSC Smartphones Applications Portfolio
WorldSC Smartphones Applications Portfolio
 
Restructuring classes and behaviour
Restructuring classes and behaviourRestructuring classes and behaviour
Restructuring classes and behaviour
 
Layar - Raimo at TNW 2011
Layar - Raimo at TNW 2011Layar - Raimo at TNW 2011
Layar - Raimo at TNW 2011
 
Layar - Raimo at TNW 2011
Layar - Raimo at TNW 2011Layar - Raimo at TNW 2011
Layar - Raimo at TNW 2011
 
Fast track to success in ones career
Fast track to success in ones careerFast track to success in ones career
Fast track to success in ones career
 
Lightening Talk: definition of ready
Lightening Talk: definition of readyLightening Talk: definition of ready
Lightening Talk: definition of ready
 
A vision workshop xp2012
A vision workshop xp2012A vision workshop xp2012
A vision workshop xp2012
 
In The Future We All Use Symfony2
In The Future We All Use Symfony2In The Future We All Use Symfony2
In The Future We All Use Symfony2
 
CIID Final project report
CIID Final project reportCIID Final project report
CIID Final project report
 
Introducing the FLUID Principles
Introducing the FLUID PrinciplesIntroducing the FLUID Principles
Introducing the FLUID Principles
 

Mais de Haklae Kim

The Semantic Web and Linked Open Data
The Semantic Web and Linked Open DataThe Semantic Web and Linked Open Data
The Semantic Web and Linked Open DataHaklae Kim
 
OKFN Korea 소개자료
OKFN Korea 소개자료OKFN Korea 소개자료
OKFN Korea 소개자료Haklae Kim
 
센서데이터 웹으로의 비상
센서데이터 웹으로의 비상센서데이터 웹으로의 비상
센서데이터 웹으로의 비상Haklae Kim
 
공공데이터 개방현황 및 포털 발전방향
공공데이터 개방현황 및 포털 발전방향공공데이터 개방현황 및 포털 발전방향
공공데이터 개방현황 및 포털 발전방향Haklae Kim
 
개인건강기록관리 플랫폼에서 링크드 데이터의 활용
개인건강기록관리 플랫폼에서  링크드 데이터의 활용 개인건강기록관리 플랫폼에서  링크드 데이터의 활용
개인건강기록관리 플랫폼에서 링크드 데이터의 활용 Haklae Kim
 
Extended open data and big data in public sector
Extended open data and big data in public sectorExtended open data and big data in public sector
Extended open data and big data in public sectorHaklae Kim
 
대한민국, 잇다!
대한민국, 잇다! 대한민국, 잇다!
대한민국, 잇다! Haklae Kim
 
Linked Data 이야기
Linked Data 이야기Linked Data 이야기
Linked Data 이야기Haklae Kim
 
Linked Data 이야기
Linked Data 이야기Linked Data 이야기
Linked Data 이야기Haklae Kim
 
오픈 데이터 현황과 과제
오픈 데이터 현황과 과제오픈 데이터 현황과 과제
오픈 데이터 현황과 과제Haklae Kim
 
서울시 링크드 데이터 서비스 사례 소개-모델링
서울시 링크드 데이터 서비스 사례 소개-모델링서울시 링크드 데이터 서비스 사례 소개-모델링
서울시 링크드 데이터 서비스 사례 소개-모델링Haklae Kim
 
서울시 링크드 데이터 서비스 사례 소개-모델링개요
서울시 링크드 데이터 서비스 사례 소개-모델링개요서울시 링크드 데이터 서비스 사례 소개-모델링개요
서울시 링크드 데이터 서비스 사례 소개-모델링개요Haklae Kim
 
서울시 Linked Data 서비스 소개-열린데이터광장
서울시 Linked Data 서비스 소개-열린데이터광장서울시 Linked Data 서비스 소개-열린데이터광장
서울시 Linked Data 서비스 소개-열린데이터광장Haklae Kim
 
서울시 링크드 데이터 서비스 소개-Overview
서울시 링크드 데이터 서비스 소개-Overview서울시 링크드 데이터 서비스 소개-Overview
서울시 링크드 데이터 서비스 소개-OverviewHaklae Kim
 
오픈 데이터에서 링크드 데이터로 진화
오픈 데이터에서 링크드 데이터로 진화 오픈 데이터에서 링크드 데이터로 진화
오픈 데이터에서 링크드 데이터로 진화 Haklae Kim
 
오픈 데이터에서 링크드 데이터로 진화
오픈 데이터에서 링크드 데이터로 진화 오픈 데이터에서 링크드 데이터로 진화
오픈 데이터에서 링크드 데이터로 진화 Haklae Kim
 
Data science-2013-heekim
Data science-2013-heekimData science-2013-heekim
Data science-2013-heekimHaklae Kim
 
Data science (조명대)
Data science (조명대)Data science (조명대)
Data science (조명대)Haklae Kim
 
Open Data and Linked Data
Open Data and Linked Data Open Data and Linked Data
Open Data and Linked Data Haklae Kim
 
시민이 함께 만들어가는 서울 열린 데이터광장
시민이 함께 만들어가는 서울 열린 데이터광장시민이 함께 만들어가는 서울 열린 데이터광장
시민이 함께 만들어가는 서울 열린 데이터광장Haklae Kim
 

Mais de Haklae Kim (20)

The Semantic Web and Linked Open Data
The Semantic Web and Linked Open DataThe Semantic Web and Linked Open Data
The Semantic Web and Linked Open Data
 
OKFN Korea 소개자료
OKFN Korea 소개자료OKFN Korea 소개자료
OKFN Korea 소개자료
 
센서데이터 웹으로의 비상
센서데이터 웹으로의 비상센서데이터 웹으로의 비상
센서데이터 웹으로의 비상
 
공공데이터 개방현황 및 포털 발전방향
공공데이터 개방현황 및 포털 발전방향공공데이터 개방현황 및 포털 발전방향
공공데이터 개방현황 및 포털 발전방향
 
개인건강기록관리 플랫폼에서 링크드 데이터의 활용
개인건강기록관리 플랫폼에서  링크드 데이터의 활용 개인건강기록관리 플랫폼에서  링크드 데이터의 활용
개인건강기록관리 플랫폼에서 링크드 데이터의 활용
 
Extended open data and big data in public sector
Extended open data and big data in public sectorExtended open data and big data in public sector
Extended open data and big data in public sector
 
대한민국, 잇다!
대한민국, 잇다! 대한민국, 잇다!
대한민국, 잇다!
 
Linked Data 이야기
Linked Data 이야기Linked Data 이야기
Linked Data 이야기
 
Linked Data 이야기
Linked Data 이야기Linked Data 이야기
Linked Data 이야기
 
오픈 데이터 현황과 과제
오픈 데이터 현황과 과제오픈 데이터 현황과 과제
오픈 데이터 현황과 과제
 
서울시 링크드 데이터 서비스 사례 소개-모델링
서울시 링크드 데이터 서비스 사례 소개-모델링서울시 링크드 데이터 서비스 사례 소개-모델링
서울시 링크드 데이터 서비스 사례 소개-모델링
 
서울시 링크드 데이터 서비스 사례 소개-모델링개요
서울시 링크드 데이터 서비스 사례 소개-모델링개요서울시 링크드 데이터 서비스 사례 소개-모델링개요
서울시 링크드 데이터 서비스 사례 소개-모델링개요
 
서울시 Linked Data 서비스 소개-열린데이터광장
서울시 Linked Data 서비스 소개-열린데이터광장서울시 Linked Data 서비스 소개-열린데이터광장
서울시 Linked Data 서비스 소개-열린데이터광장
 
서울시 링크드 데이터 서비스 소개-Overview
서울시 링크드 데이터 서비스 소개-Overview서울시 링크드 데이터 서비스 소개-Overview
서울시 링크드 데이터 서비스 소개-Overview
 
오픈 데이터에서 링크드 데이터로 진화
오픈 데이터에서 링크드 데이터로 진화 오픈 데이터에서 링크드 데이터로 진화
오픈 데이터에서 링크드 데이터로 진화
 
오픈 데이터에서 링크드 데이터로 진화
오픈 데이터에서 링크드 데이터로 진화 오픈 데이터에서 링크드 데이터로 진화
오픈 데이터에서 링크드 데이터로 진화
 
Data science-2013-heekim
Data science-2013-heekimData science-2013-heekim
Data science-2013-heekim
 
Data science (조명대)
Data science (조명대)Data science (조명대)
Data science (조명대)
 
Open Data and Linked Data
Open Data and Linked Data Open Data and Linked Data
Open Data and Linked Data
 
시민이 함께 만들어가는 서울 열린 데이터광장
시민이 함께 만들어가는 서울 열린 데이터광장시민이 함께 만들어가는 서울 열린 데이터광장
시민이 함께 만들어가는 서울 열린 데이터광장
 

Último

Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxhariprasad279825
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
unit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxunit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxBkGupta21
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxLoriGlavin3
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxLoriGlavin3
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningLars Bell
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxLoriGlavin3
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenHervé Boutemy
 
Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rick Flair
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxLoriGlavin3
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxLoriGlavin3
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 

Último (20)

Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
unit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxunit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptx
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptx
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine Tuning
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache Maven
 
Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 

KAIST Education for Experiential Knowledge Mining

  • 1. KAIST Education for the World, Research for the Future 인간의 경험 공유를 위한 태스크 및 컨텍스트 추출 및 표현 2012. 11. 29 류지희 웹사이언스공학 전공 정보검색 및 자연어처리 연구실
  • 2. Why Human Experience Sharing?  Necessity of Experiential Problem Solving Knowledge 2 © 2012 IR&NLP Lab. All rights reserved.
  • 3. A. Change a Flat Tire When You Are a Woman Alone 1. Loosen lug nuts on tire. 2. Install spare tire. user User Context Info B. Change a Tire like a Real Woman [On U.S. highway] 1. Call AAA. [1 year driving experience] 2. Be placed on “hold”. [Heading to New York] [Female] 3 © 2012 IR&NLP Lab. All rights reserved.
  • 4. Experience Mining  Building a Relational Knowledge about Experiences Experiential Knowledge Distillation Web Context-anchored Experiential Experiential Sentences & Knowledge Context Automatic extraction Aggregation & abstraction Event People Place Time Event People Place Time Play Soccer Yongho, … Expo Park 2011-08-10 (Type) (Type) (Type) (Type) Play Baseball Chulsoo, … Gapchun Park 2009-09-02 (Sport) (student) (Park) (Summer) … … 4 © 2012 IR&NLP Lab. All rights reserved.
  • 5. From What?  Various types of open contents on the Web! How-to Blog Microblog articles posts posts Human Task Event Context Place Semantics mining mining mining Human Experiential KB 5 © 2012 IR&NLP Lab. All rights reserved.
  • 6. Human Task Mining 6 © 2012 IR&NLP Lab. All rights reserved.
  • 7. Human Task Model Topic hasTopic Goal hasAction hasNextAction Action hasObject hasTime hasLocation Object Time Location 7 © 2012 IR&NLP Lab. All rights reserved.
  • 8. Human Task Extraction Goal Title How to Make Omelet Soup Make Omelet Soup Action Sequence Step 1 Place the water or canned chicken broth in a large saucepan. (place, water) (place, broth) Boil the sweet yellow onion for several (boil, onion) minutes. (add, broth) Step 2 Add the powdered chicken broth along (boil, soup) with the canned mushrooms. (add, onion) Boil the soup for a few more minutes, and then add the chopped green onion. (drop, egg) Step 3 Drop the eggs into the simmering broth Ingredients a few minutes before you're ready to water broth serve the omelet soup. soup onion egg 8 © 2012 IR&NLP Lab. All rights reserved.
  • 9. Hybrid Extraction Method Eat fruit every day. Sentences Turn off the car. (eat, fruit) (turn off, car) Retrieve and apply Yes Extract Matched? a rule verb and ingredients No Yes Select the best Syntactic Patterns Prob. > threshold label sequence CRFs Model 9 © 2012 IR&NLP Lab. All rights reserved.
  • 10. Next Challenging Issues  A large fraction of sentences (more than 40%) in how-to instructions are not imperative sentences.  Difficulties arising from variations in writing Case Percentage  Scoping ambiguity Scoping  E.g. Clear or glitter nail polish should go on the nails. 13.9% Ambiguity  Anaphora Anaphora 13.1%  E.g. Make it fun and unique Condition 11.9%  Condition Ellipsis 1.9%  E.g. If your computers are only a few years old Implicit 1.3%  Ellipsis meaning  E.g. So why don't you? Grammatical 1.3%  Implicit meaning mistake  E.g. Studying improves grades. (Study hard!) Etc. 56.6%  Grammatical mistake Case Percentage in all the clauses in  E.g. IM a friend! (Make friend relationship in a instance messenger) 30 sample documents 10 © 2012 IR&NLP Lab. All rights reserved.
  • 11. Feature Sets Feature Type Feature Name Feature Values Clause Type main, subordinate Person 1st person, 2nd person, 3rd person Syntactic Auxiliary Verb will, shall, can, may, must, able to, … Features Voice active, passive, n/a Tense past, present, future Polarity negated, non-negated Feature Type Feature Name Examples Obligation • You have to ask about the car. Permission • You can search for the world weather. Modality Features Explanation • The cost for delivery is already included. Supposition • You will have access to the weather. 11 © 2012 IR&NLP Lab. All rights reserved.
  • 12. Result: Actionable Clause Detection Task Used Feature Sets F1(NB) F1(DT) F1(SVM) Syntactic Features Actionable 0.933 0.942 0.948 (micro only) Clause Detection + Modality Features 0.862 0.963 0.966 (micro &macro) NB : Naï Bayes ve DT : Decision Tree SVM : Support Vector Machines 12 © 2012 IR&NLP Lab. All rights reserved.
  • 13. Bridge to Semantic Web AcTN knowledge representation YAGO knowledge representation 13 © 2012 IR&NLP Lab. All rights reserved.
  • 14. Changing Data Representation Current Form Ultimate Target Form Refined tabular Well-designed data records ontology entries [plain text] [well-formed RDF] 14 © 2012 IR&NLP Lab. All rights reserved.
  • 15. Event Context Mining 15 © 2012 IR&NLP Lab. All rights reserved.
  • 16. What is an Event?  Events are defined as situations that happen  Punctual (example 1-2) or last for a period of time (example 3-4)  States in which something holds true (example 5)  Examples Ferdinand Magellan, a Portuguese explorer, first reached the islands in search (1) of spices. A fresh flow of lava, gas and debris erupted there Saturday. (2) 11,024 people were evacuated to 18 disaster relief centers. (3) “We’re expecting a major eruption,” he said in a telephone interview early to (4) day. Israel has been scrambling to buy more masks abroad, after a shortage of sev (5) eral hundred thousand gas masks. 16 © 2012 IR&NLP Lab. All rights reserved.
  • 17. Event Expressions  Event may be expressed in the following forms Type Example Verb A fresh flow of lava, gas and debris erupted there Saturday. Israel will ask the United States to delay a military strike ag Noun ainst Iraq until the Jewish state is fully prepared for a possib le Iraqi attack. A Philippine volcano, dormant for six centuries, began expl Adjective oding with searing gases, thick ash and deadly debris. “There is no reason why we would not be prepared,” Mord Predicative clause echai told the Yediot Ahronot daily. Prepositional phrase All 75 people on board the Aeroflot Airbus died. 17 © 2012 IR&NLP Lab. All rights reserved.
  • 18. Feature Sets  Basic Features  Named entity (NE) tags and an indication of whether the target noun is prenominal or not.  Lexical Semantic Features (LS)  The set of target nouns’ lemmas and their WordNet hypernyms  Dependency-based Features (DF)  Nouns become events if they occur with a certain surrounding context, namely, syntactic dependencies  Dependency-based Features sometimes need to be combined with Lexical Semantic Features 18 © 2012 IR&NLP Lab. All rights reserved.
  • 19. Comparing with Previous Work  An improvement of about 0.22 (precision) and 0.09 (recall) over the state-of-the-art, respectively. Llorens et al. (2010) Proposed Method 0.727 Precision 0.95 0.483 Recall 0.577 0.584 F1 0.718 0.00 0.10 0.20 0.30 0.40 0.50 0.60 0.70 0.80 0.90 1.00 19 © 2012 IR&NLP Lab. All rights reserved.
  • 20. Place Semantics Mining 20 © 2012 IR&NLP Lab. All rights reserved.
  • 21. Place Semantics  AS GPS-enabled mobile devices have come into wide use, Location based services catch popularity  But it is hard to provide appropriate context-aware services to users when the system only use user’s location, i.e. GPS(latitude, longitude)  Contrary to location, Place is space where people impart a meaning  If we know the meaning of the place, Place Semantics, we can serve much better suitable services to users 21 © 2012 IR&NLP Lab. All rights reserved.
  • 22. Motivation  Scenario Recently, Lena moved to Korea from USA. She doesn’t know Korean culture and geography at all because she didn’t leave outside USA before. Is there similar places with Brooklyn Bowl that I often visited in order to relieve stress? How about Olympic Bowling Alley? No. Thanks! It’s NOT the place I wanted. Brooklyn Bowl is a bowling alley in New York City. People enjoy bowling, have a party, drink beer and hold a music event in Brooklyn Bowl. 22 © 2012 IR&NLP Lab. All rights reserved.
  • 23. Place Semantics Mining  People leave texts about “why they visit, what they do” when they check-in at Place on Foursquare  We can know the perception of places from those texts  We apply LDA to extract Place Semantics  A document is composed of texts written in a place. “text” Place 23 © 2012 IR&NLP Lab. All rights reserved.
  • 24. Similarity between Two Places Is there similar places with Brooklyn Bowl that I often visited in order to relieve stress? How about XL Night Club? Brooklyn Bowl XL Night Club Have a party & Drink beer 41% 32% Enjoy a music show After work 27% 5% 3% Eat food 26% 7% Watch sports game 11% 18% 30% Others 24 © 2012 IR&NLP Lab. All rights reserved.
  • 25. Concluding Remarks 25 © 2012 IR&NLP Lab. All rights reserved.
  • 26. Application of Our Results  Semantic Annotation  Adds diversity and richness to text processing 26 © 2012 IR&NLP Lab. All rights reserved.
  • 27. Thank you! 27 © 2012 IR&NLP Lab. All rights reserved.
  • 28. KAIST Education for the World, Research for the Future Jihee Ryu (jiheeryu@kaist.ac.kr) http://jihee.kr Yoonjae Jeong (hybris@kaist.ac.kr) Eunyoung Kim (ey_kim@kaist.ac.kr) Sung-Hyon Myaeng (myaeng@kaist.ac.kr) http://ir.kaist.ac.kr/member/professor/ IR&NLP Lab http://ir.kaist.ac.kr
  • 29. Reference 1) Jung, Y., Ryu, J., Kim, K., Myaeng, S.H.: Automatic Construction of a Large-Scale Situation Ontology by Mining How-to Instructions from the Web. Web Semantics: Science, Services and Agents on the World Wide Web (2010) 2) Ryu, J., Jung, Y., Kim, K., Myaeng, S.H.: Automatic Extraction of Human Activity Knowledge from Method-Describing Web Articles. 1st Workshop on Automated Knowledge Base Construction (2010) 3) Park, K.C., Jeong, Y., Myaeng, S.H.: Detecting Experiences from Weblogs. 48th Annual Meeting of the Association for Computational Linguistics (2010) 4) Ryu, J., Jung, Y., Myaeng, S.H.: Actionable Clause Detection from Non-imperative Sentences in How-to Instructions: A Step for Actionable Information Extraction. 15th International Conference on Text, Speech and Dialogue (2012) 5) Jeong, Y., Myaeng, S.H.: Using Syntactic Dependencies and WordNet Classes for Noun Event Recognition. Workhop on Detection, Representation, and Exploitation of Events in the Semantic Web in conjunction with the 11th International Semantic Web Conference 2012 (2012) 6) Carter, E., Donald, J.: Space and place: theories of identity and location. Lawrence & Wishart Ltd. (1993) 29 © 2012 IR&NLP Lab. All rights reserved.
  • 30. Data Collection: How-to Articles  General How-to Articles  1,850,725 articles from eHow & 109,781 articles from wikiHow eHow Category Group # doc wikiHow Category Group # doc Computers & Software, Internet 323,289 Computers, Electronics 18,265 Home Building & Design & Safety 307,277 Family Life, Home, Pets, Relationships 18,220 Culture, Holidays, Hobbies, Weddings 238,143 Hobbies, Holidays, Travel 14,514 Business, Investment, Personal Finance 153,458 Health, Sports 14,161 Arts, Entertainment, Music 149,426 Youth 9,161 Family, Parenting, Pets, Plants 135,909 Personal Care, Style 7,031 Cars, Car Repair 108,386 Education, Communications 6,775 Healthcare, Fitness, Sports 103,758 Finance, Business, Work 6,729 Education, Careers, Employment 103,717 Food, Entertaining 6,099 Electronics 101,403 Arts, Entertainment 5,151 Food, Recipes 63,553 Cars, Vehicles 2,316 Fashion, Beauty 62,406 Philosophy, Religion 1,359 Total (As from December 2011) 1,850,725 Total (As from December 2011) 109,781 30 © 2012 IR&NLP Lab. All rights reserved.