SlideShare a Scribd company logo
1 of 17
Download to read offline
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
Timo Honkela
Modeling Meaning and Knowledge
1 Feb 2016
timo.honkela@helsinki.fi
Spaces of Knowledge
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
http://www.cs.cornell.edu/Info/
Department/Annual95/Faculty/Salton.html
Advent of vector-based
information retrieval
●
Gerarg Salton: Documents and
queries represented as vectors of
term counts
● Similarity between a document
and a query is given by the cosine
between the term vector and the
document vector
● TF-IDF (term-frequency-inverse-
document frequency) for weighting
of a term in a document
● Inverse document frequency had
been introduced by Karen
Spärck-Jones in 1972
https://en.wikipedia.org/wiki/Gerard_Salton
https://en.wikipedia.org/wiki/Karen_Sp%C3%A4rck_Jones
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
University
Society
D
D
D
Q Q
Q
1
1
2
2
3
3
Document 1: The word “university”
appears three times and “society” once, etc.
Query 1: “university”
https://en.wikipedia.org/wiki/Cosine_similarity
https://en.wikipedia.org/wiki/Sine
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
Contexts tell about meaning
● John Rupert Firth: “You shall know a word
by the company it keeps”
● Ludwig Wittgenstein: “For a large class of
cases of the employment of the word
‘meaning’—though not for all—this way can be
explained in this way: the meaning of a word is
its use in the language” (PI 43)
https://en.wikipedia.org/wiki/John_Rupert_Firth
http://plato.stanford.edu/entries/wittgenstein/#Mea
https://en.wikipedia.org/wiki/Ludwig_Wittgenstein
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
Analysis of term-document matrices
● The same idea as in information retrieval can
also be applied in studying words and
expressions
● Statistical analysis of document-term matrices
gives rise to models of relationship between
words or documents
● Classical examples include
– Latent Semantic Analysis (Deerwester, Dumais et al. 1988)
– Self-Organizing Semantic Maps (Ritter & Kohonen 1989)
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
Word spaces, clusters, clouds, ...
● The analysis of the statistical information
related to word contexts can be turned into
visualizations of the word relations
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
Maps of words in Grimm fairy tales
Honkela, Pulkki & Kohonen 1995
Automated learning of word relations
using self-organizing map on text context data
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
Chemistry
Natural sciences
and engineering
Bio- and
environmental
sciences
Health
Culture and
society
Map of Finnish Science
(T. Honkela & M. Klami 2007)
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
From term weighting
to term selection
● TF-IDF is a widely used method for term
weighting
● Likey (Language Independent Keyphrase
Extraction) was developed to select terms
automally by camparing the corpus at hand
with another corpus, called a reference corpus
(Paukkeri et al. 2008, Paukkeri & Honkela 2010)
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
1. the  1276847
2. of  1067918
3. and    817852
4. in    625330
5. to    357453
6. for   225307
7. is    205723
8. on    162509
9. research 157251
10. be    151475
11. with    136854
12. will    135992
13. as      122707
14. are    116508
15. by   113878
16. university 98003
...
1. the  2023617
2. of    945622
3. to    883206
4. and    717718
5. in    611421
6. that    473739
7. a    445775
8. is    445119
9. we    305590
10. for    296092
11. i     290412
12. this    286924
13. on    274614
14. it    251343
15. be    246917
16. are    197082
...
Most frequent word forms (types) in
two corpora
Academy
corpus
Europarl
corpus
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
Documents
Terms
SOM
Document map
Likey
Reference
corpus
(EU partiament)
Academy
corpus
Term list
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
Extralinguistic contexts
● Human beings learn language in real world
contexts that include visual, tactile, etc.
perceptions
● In order to model meaning in a human-like
manner, these other modalities have to be taken
into account
● In a project called “Multimodally Grounded
Language Technology” we associated visual
patterns of human movements with expressions
that had been used to describe these
movements
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
RUNNING
WALKING
LIMPING
JOGGING
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
Modeling subjectivity
of meaning
● In our method Grounded Intersubjective
Concept Analysis (GICA), we added a new
“dimension” to the term-document matrices
● We did not assume that each person
understands and uses every word in a similar
manner but wanted to model the personal
variation
● This was achieved by using Subject-Object-
Context tensors (Honkela et al. 2012)
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
GICA: Grounded Intersubjective
Concept Analysis
Honkela,
Raitio,
Lagus &
Nieminen
2012
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
Analysis of “health” in the
State of the Union addresses
Subjects on objects in contexts:
Using GICA method to quantify
epistemological subjectivity.
Timo Honkela, Juha Raitio, Krista Lagus,
Ilari T. Nieminen, Nina Honkela, and Mika Pantzar.
Proc. of IJCNN 2012.
Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016
Thank you for
you attention!

More Related Content

Similar to Timo Honkela: Spaces of Knowledge

Honkela, Korhonen, Lagus & Saarinen: Five-Dimensional Sentiment Analysis of C...
Honkela, Korhonen, Lagus & Saarinen: Five-Dimensional Sentiment Analysis of C...Honkela, Korhonen, Lagus & Saarinen: Five-Dimensional Sentiment Analysis of C...
Honkela, Korhonen, Lagus & Saarinen: Five-Dimensional Sentiment Analysis of C...Timo Honkela
 
Timo Honkela: Epistemological status of linguistic theories and models
Timo Honkela: Epistemological status of linguistic theories and modelsTimo Honkela: Epistemological status of linguistic theories and models
Timo Honkela: Epistemological status of linguistic theories and modelsTimo Honkela
 
Timo Honkela: Digital Preservation and Computational Modeling of Language and...
Timo Honkela: Digital Preservation and Computational Modeling of Language and...Timo Honkela: Digital Preservation and Computational Modeling of Language and...
Timo Honkela: Digital Preservation and Computational Modeling of Language and...Timo Honkela
 
Timo Honkela: Multimodally Grounded Translation by Humans and Machines
Timo Honkela: Multimodally Grounded Translation by Humans and MachinesTimo Honkela: Multimodally Grounded Translation by Humans and Machines
Timo Honkela: Multimodally Grounded Translation by Humans and MachinesTimo Honkela
 
20220602_QMC22_Slide.pdf
20220602_QMC22_Slide.pdf20220602_QMC22_Slide.pdf
20220602_QMC22_Slide.pdfShingo Nahatame
 
Automatize Document Topic And Subtopic Detection With Support Of A Corpus
Automatize Document Topic And Subtopic Detection With Support Of A CorpusAutomatize Document Topic And Subtopic Detection With Support Of A Corpus
Automatize Document Topic And Subtopic Detection With Support Of A CorpusRichard Hogue
 
김문형-Curriculum Vitae
김문형-Curriculum Vitae김문형-Curriculum Vitae
김문형-Curriculum VitaeMunhyong Kim
 
Timo Honkela: Research interests in text and metadata mining of literature
Timo Honkela: Research interests in text and metadata mining of literatureTimo Honkela: Research interests in text and metadata mining of literature
Timo Honkela: Research interests in text and metadata mining of literatureTimo Honkela
 
Timo Honkela: From Patterns of Movement to Subjectivity of Understanding
Timo Honkela: From Patterns of Movement to Subjectivity of UnderstandingTimo Honkela: From Patterns of Movement to Subjectivity of Understanding
Timo Honkela: From Patterns of Movement to Subjectivity of UnderstandingTimo Honkela
 
Functional English Design for Domestic Migrant Workers
Functional English Design for Domestic Migrant WorkersFunctional English Design for Domestic Migrant Workers
Functional English Design for Domestic Migrant Workersidhasaeful
 
Involving users in the design of apps for the writing processes. An experimen...
Involving users in the design of apps for the writing processes.An experimen...Involving users in the design of apps for the writing processes.An experimen...
Involving users in the design of apps for the writing processes. An experimen...Maria Ranieri
 
Timo Honkela: Self-Organizing Map as a Means for Gaining Perspectives
Timo Honkela: Self-Organizing Map as a Means for Gaining PerspectivesTimo Honkela: Self-Organizing Map as a Means for Gaining Perspectives
Timo Honkela: Self-Organizing Map as a Means for Gaining PerspectivesTimo Honkela
 
Timo Honkela: An introduction to machine learning and neural networks
Timo Honkela: An introduction to machine learning and neural networksTimo Honkela: An introduction to machine learning and neural networks
Timo Honkela: An introduction to machine learning and neural networksTimo Honkela
 
Listening comprehension in efl teaching
Listening comprehension in efl teachingListening comprehension in efl teaching
Listening comprehension in efl teachingmora-deyanira
 
Listening Comprehension in EFL Teaching
Listening Comprehension in EFL TeachingListening Comprehension in EFL Teaching
Listening Comprehension in EFL Teachingmora-deyanira
 
NLP applicata a LIS
NLP applicata a LISNLP applicata a LIS
NLP applicata a LISnoemiricci2
 
Time factor updatemeeting-elc-01june2011-v8-last-release
Time factor updatemeeting-elc-01june2011-v8-last-releaseTime factor updatemeeting-elc-01june2011-v8-last-release
Time factor updatemeeting-elc-01june2011-v8-last-releaseMargarida Romero
 
Getting the Best of Both Worlds
Getting the Best of Both WorldsGetting the Best of Both Worlds
Getting the Best of Both Worldsdeining
 

Similar to Timo Honkela: Spaces of Knowledge (20)

Honkela, Korhonen, Lagus & Saarinen: Five-Dimensional Sentiment Analysis of C...
Honkela, Korhonen, Lagus & Saarinen: Five-Dimensional Sentiment Analysis of C...Honkela, Korhonen, Lagus & Saarinen: Five-Dimensional Sentiment Analysis of C...
Honkela, Korhonen, Lagus & Saarinen: Five-Dimensional Sentiment Analysis of C...
 
Timo Honkela: Epistemological status of linguistic theories and models
Timo Honkela: Epistemological status of linguistic theories and modelsTimo Honkela: Epistemological status of linguistic theories and models
Timo Honkela: Epistemological status of linguistic theories and models
 
Timo Honkela: Digital Preservation and Computational Modeling of Language and...
Timo Honkela: Digital Preservation and Computational Modeling of Language and...Timo Honkela: Digital Preservation and Computational Modeling of Language and...
Timo Honkela: Digital Preservation and Computational Modeling of Language and...
 
Timo Honkela: Multimodally Grounded Translation by Humans and Machines
Timo Honkela: Multimodally Grounded Translation by Humans and MachinesTimo Honkela: Multimodally Grounded Translation by Humans and Machines
Timo Honkela: Multimodally Grounded Translation by Humans and Machines
 
20220602_QMC22_Slide.pdf
20220602_QMC22_Slide.pdf20220602_QMC22_Slide.pdf
20220602_QMC22_Slide.pdf
 
Automatize Document Topic And Subtopic Detection With Support Of A Corpus
Automatize Document Topic And Subtopic Detection With Support Of A CorpusAutomatize Document Topic And Subtopic Detection With Support Of A Corpus
Automatize Document Topic And Subtopic Detection With Support Of A Corpus
 
김문형-Curriculum Vitae
김문형-Curriculum Vitae김문형-Curriculum Vitae
김문형-Curriculum Vitae
 
Timo Honkela: Research interests in text and metadata mining of literature
Timo Honkela: Research interests in text and metadata mining of literatureTimo Honkela: Research interests in text and metadata mining of literature
Timo Honkela: Research interests in text and metadata mining of literature
 
Timo Honkela: From Patterns of Movement to Subjectivity of Understanding
Timo Honkela: From Patterns of Movement to Subjectivity of UnderstandingTimo Honkela: From Patterns of Movement to Subjectivity of Understanding
Timo Honkela: From Patterns of Movement to Subjectivity of Understanding
 
Functional English Design for Domestic Migrant Workers
Functional English Design for Domestic Migrant WorkersFunctional English Design for Domestic Migrant Workers
Functional English Design for Domestic Migrant Workers
 
Involving users in the design of apps for the writing processes. An experimen...
Involving users in the design of apps for the writing processes.An experimen...Involving users in the design of apps for the writing processes.An experimen...
Involving users in the design of apps for the writing processes. An experimen...
 
Time factor Seminar
Time factor SeminarTime factor Seminar
Time factor Seminar
 
Presentation1.ppt
Presentation1.pptPresentation1.ppt
Presentation1.ppt
 
Timo Honkela: Self-Organizing Map as a Means for Gaining Perspectives
Timo Honkela: Self-Organizing Map as a Means for Gaining PerspectivesTimo Honkela: Self-Organizing Map as a Means for Gaining Perspectives
Timo Honkela: Self-Organizing Map as a Means for Gaining Perspectives
 
Timo Honkela: An introduction to machine learning and neural networks
Timo Honkela: An introduction to machine learning and neural networksTimo Honkela: An introduction to machine learning and neural networks
Timo Honkela: An introduction to machine learning and neural networks
 
Listening comprehension in efl teaching
Listening comprehension in efl teachingListening comprehension in efl teaching
Listening comprehension in efl teaching
 
Listening Comprehension in EFL Teaching
Listening Comprehension in EFL TeachingListening Comprehension in EFL Teaching
Listening Comprehension in EFL Teaching
 
NLP applicata a LIS
NLP applicata a LISNLP applicata a LIS
NLP applicata a LIS
 
Time factor updatemeeting-elc-01june2011-v8-last-release
Time factor updatemeeting-elc-01june2011-v8-last-releaseTime factor updatemeeting-elc-01june2011-v8-last-release
Time factor updatemeeting-elc-01june2011-v8-last-release
 
Getting the Best of Both Worlds
Getting the Best of Both WorldsGetting the Best of Both Worlds
Getting the Best of Both Worlds
 

More from Timo Honkela

Timo Honkela: Meaning negotiations as phenomenon and as languages technology...
 Timo Honkela: Meaning negotiations as phenomenon and as languages technology... Timo Honkela: Meaning negotiations as phenomenon and as languages technology...
Timo Honkela: Meaning negotiations as phenomenon and as languages technology...Timo Honkela
 
Timo Honkela: Meaning negotiations as phenomenon and as languages technology ...
Timo Honkela: Meaning negotiations as phenomenon and as languages technology ...Timo Honkela: Meaning negotiations as phenomenon and as languages technology ...
Timo Honkela: Meaning negotiations as phenomenon and as languages technology ...Timo Honkela
 
Timo Honkela: Peace Machine: Using Artificial Intelligence to Promote Peacefu...
Timo Honkela: Peace Machine: Using Artificial Intelligence to Promote Peacefu...Timo Honkela: Peace Machine: Using Artificial Intelligence to Promote Peacefu...
Timo Honkela: Peace Machine: Using Artificial Intelligence to Promote Peacefu...Timo Honkela
 
Timo Honkela: From early to later Wittgenstein and Artificial Intelligence
Timo Honkela: From early to later Wittgenstein and Artificial IntelligenceTimo Honkela: From early to later Wittgenstein and Artificial Intelligence
Timo Honkela: From early to later Wittgenstein and Artificial IntelligenceTimo Honkela
 
Timo Honkela: Peace Machine: Peace from a difference perspective - Dialogue o...
Timo Honkela: Peace Machine: Peace from a difference perspective - Dialogue o...Timo Honkela: Peace Machine: Peace from a difference perspective - Dialogue o...
Timo Honkela: Peace Machine: Peace from a difference perspective - Dialogue o...Timo Honkela
 
Timo Honkela: Kielellisten merkisten tilastollinen ja psykologinen luonne: Ko...
Timo Honkela: Kielellisten merkisten tilastollinen ja psykologinen luonne: Ko...Timo Honkela: Kielellisten merkisten tilastollinen ja psykologinen luonne: Ko...
Timo Honkela: Kielellisten merkisten tilastollinen ja psykologinen luonne: Ko...Timo Honkela
 
Timo Honkela, kutsuttu esitelmä Automaatiopäivillä 2017
Timo Honkela, kutsuttu esitelmä Automaatiopäivillä 2017Timo Honkela, kutsuttu esitelmä Automaatiopäivillä 2017
Timo Honkela, kutsuttu esitelmä Automaatiopäivillä 2017Timo Honkela
 
Timo Honkela: Turning quantity into quality and making concepts visible using...
Timo Honkela: Turning quantity into quality and making concepts visible using...Timo Honkela: Turning quantity into quality and making concepts visible using...
Timo Honkela: Turning quantity into quality and making concepts visible using...Timo Honkela
 
Timo Honkela: Tietokone lukemassa yli 100 miljoonaa eri kirjaa: Kielitieteen ...
Timo Honkela: Tietokone lukemassa yli 100 miljoonaa eri kirjaa: Kielitieteen ...Timo Honkela: Tietokone lukemassa yli 100 miljoonaa eri kirjaa: Kielitieteen ...
Timo Honkela: Tietokone lukemassa yli 100 miljoonaa eri kirjaa: Kielitieteen ...Timo Honkela
 
Timo Honkela: Introducing the book Encyclopedia of Artificial Intelligence (i...
Timo Honkela: Introducing the book Encyclopedia of Artificial Intelligence (i...Timo Honkela: Introducing the book Encyclopedia of Artificial Intelligence (i...
Timo Honkela: Introducing the book Encyclopedia of Artificial Intelligence (i...Timo Honkela
 
Timo Honkela: Tekoälyn ja koneoppimisen uhat ja mahdollisuudet, Turku, 27.10....
Timo Honkela: Tekoälyn ja koneoppimisen uhat ja mahdollisuudet, Turku, 27.10....Timo Honkela: Tekoälyn ja koneoppimisen uhat ja mahdollisuudet, Turku, 27.10....
Timo Honkela: Tekoälyn ja koneoppimisen uhat ja mahdollisuudet, Turku, 27.10....Timo Honkela
 
Timo Honkela: Kohonen's Self-Organizing Maps for Intelligent Systems Developm...
Timo Honkela: Kohonen's Self-Organizing Maps for Intelligent Systems Developm...Timo Honkela: Kohonen's Self-Organizing Maps for Intelligent Systems Developm...
Timo Honkela: Kohonen's Self-Organizing Maps for Intelligent Systems Developm...Timo Honkela
 
Timo Honkela: Kylmä data kohtaa inhimillisen tulkinnan, Studia Generalia -esi...
Timo Honkela: Kylmä data kohtaa inhimillisen tulkinnan, Studia Generalia -esi...Timo Honkela: Kylmä data kohtaa inhimillisen tulkinnan, Studia Generalia -esi...
Timo Honkela: Kylmä data kohtaa inhimillisen tulkinnan, Studia Generalia -esi...Timo Honkela
 
Timo Honkela: Ihminen+ -esitelmä, Mikkeli, 22.9.2016
Timo Honkela: Ihminen+ -esitelmä, Mikkeli, 22.9.2016Timo Honkela: Ihminen+ -esitelmä, Mikkeli, 22.9.2016
Timo Honkela: Ihminen+ -esitelmä, Mikkeli, 22.9.2016Timo Honkela
 
Timo Honkela: Kynä ja kone alustus menetelmistä, 15.9.2016
Timo Honkela: Kynä ja kone alustus menetelmistä, 15.9.2016Timo Honkela: Kynä ja kone alustus menetelmistä, 15.9.2016
Timo Honkela: Kynä ja kone alustus menetelmistä, 15.9.2016Timo Honkela
 
Honkela. Lagus & Kanner: Parallel Conceptual Spaces and Systems in Health and...
Honkela. Lagus & Kanner: Parallel Conceptual Spaces and Systems in Health and...Honkela. Lagus & Kanner: Parallel Conceptual Spaces and Systems in Health and...
Honkela. Lagus & Kanner: Parallel Conceptual Spaces and Systems in Health and...Timo Honkela
 
Timo Honkela: Miten tekoäly muuttaa oppimista ja työtä? Kalajoen lukio, 17.8....
Timo Honkela: Miten tekoäly muuttaa oppimista ja työtä? Kalajoen lukio, 17.8....Timo Honkela: Miten tekoäly muuttaa oppimista ja työtä? Kalajoen lukio, 17.8....
Timo Honkela: Miten tekoäly muuttaa oppimista ja työtä? Kalajoen lukio, 17.8....Timo Honkela
 
Timo Honkela: Digitalisaatio tulevaisuudessa
Timo Honkela: Digitalisaatio tulevaisuudessaTimo Honkela: Digitalisaatio tulevaisuudessa
Timo Honkela: Digitalisaatio tulevaisuudessaTimo Honkela
 
Timo Honkela: Analysis of Qualitative Data using Machine Learning Methods
Timo Honkela: Analysis of Qualitative Data using Machine Learning MethodsTimo Honkela: Analysis of Qualitative Data using Machine Learning Methods
Timo Honkela: Analysis of Qualitative Data using Machine Learning MethodsTimo Honkela
 
Timo Honkela: Silta-tilaisuuden alustus, 7.6.2016
Timo Honkela: Silta-tilaisuuden alustus, 7.6.2016Timo Honkela: Silta-tilaisuuden alustus, 7.6.2016
Timo Honkela: Silta-tilaisuuden alustus, 7.6.2016Timo Honkela
 

More from Timo Honkela (20)

Timo Honkela: Meaning negotiations as phenomenon and as languages technology...
 Timo Honkela: Meaning negotiations as phenomenon and as languages technology... Timo Honkela: Meaning negotiations as phenomenon and as languages technology...
Timo Honkela: Meaning negotiations as phenomenon and as languages technology...
 
Timo Honkela: Meaning negotiations as phenomenon and as languages technology ...
Timo Honkela: Meaning negotiations as phenomenon and as languages technology ...Timo Honkela: Meaning negotiations as phenomenon and as languages technology ...
Timo Honkela: Meaning negotiations as phenomenon and as languages technology ...
 
Timo Honkela: Peace Machine: Using Artificial Intelligence to Promote Peacefu...
Timo Honkela: Peace Machine: Using Artificial Intelligence to Promote Peacefu...Timo Honkela: Peace Machine: Using Artificial Intelligence to Promote Peacefu...
Timo Honkela: Peace Machine: Using Artificial Intelligence to Promote Peacefu...
 
Timo Honkela: From early to later Wittgenstein and Artificial Intelligence
Timo Honkela: From early to later Wittgenstein and Artificial IntelligenceTimo Honkela: From early to later Wittgenstein and Artificial Intelligence
Timo Honkela: From early to later Wittgenstein and Artificial Intelligence
 
Timo Honkela: Peace Machine: Peace from a difference perspective - Dialogue o...
Timo Honkela: Peace Machine: Peace from a difference perspective - Dialogue o...Timo Honkela: Peace Machine: Peace from a difference perspective - Dialogue o...
Timo Honkela: Peace Machine: Peace from a difference perspective - Dialogue o...
 
Timo Honkela: Kielellisten merkisten tilastollinen ja psykologinen luonne: Ko...
Timo Honkela: Kielellisten merkisten tilastollinen ja psykologinen luonne: Ko...Timo Honkela: Kielellisten merkisten tilastollinen ja psykologinen luonne: Ko...
Timo Honkela: Kielellisten merkisten tilastollinen ja psykologinen luonne: Ko...
 
Timo Honkela, kutsuttu esitelmä Automaatiopäivillä 2017
Timo Honkela, kutsuttu esitelmä Automaatiopäivillä 2017Timo Honkela, kutsuttu esitelmä Automaatiopäivillä 2017
Timo Honkela, kutsuttu esitelmä Automaatiopäivillä 2017
 
Timo Honkela: Turning quantity into quality and making concepts visible using...
Timo Honkela: Turning quantity into quality and making concepts visible using...Timo Honkela: Turning quantity into quality and making concepts visible using...
Timo Honkela: Turning quantity into quality and making concepts visible using...
 
Timo Honkela: Tietokone lukemassa yli 100 miljoonaa eri kirjaa: Kielitieteen ...
Timo Honkela: Tietokone lukemassa yli 100 miljoonaa eri kirjaa: Kielitieteen ...Timo Honkela: Tietokone lukemassa yli 100 miljoonaa eri kirjaa: Kielitieteen ...
Timo Honkela: Tietokone lukemassa yli 100 miljoonaa eri kirjaa: Kielitieteen ...
 
Timo Honkela: Introducing the book Encyclopedia of Artificial Intelligence (i...
Timo Honkela: Introducing the book Encyclopedia of Artificial Intelligence (i...Timo Honkela: Introducing the book Encyclopedia of Artificial Intelligence (i...
Timo Honkela: Introducing the book Encyclopedia of Artificial Intelligence (i...
 
Timo Honkela: Tekoälyn ja koneoppimisen uhat ja mahdollisuudet, Turku, 27.10....
Timo Honkela: Tekoälyn ja koneoppimisen uhat ja mahdollisuudet, Turku, 27.10....Timo Honkela: Tekoälyn ja koneoppimisen uhat ja mahdollisuudet, Turku, 27.10....
Timo Honkela: Tekoälyn ja koneoppimisen uhat ja mahdollisuudet, Turku, 27.10....
 
Timo Honkela: Kohonen's Self-Organizing Maps for Intelligent Systems Developm...
Timo Honkela: Kohonen's Self-Organizing Maps for Intelligent Systems Developm...Timo Honkela: Kohonen's Self-Organizing Maps for Intelligent Systems Developm...
Timo Honkela: Kohonen's Self-Organizing Maps for Intelligent Systems Developm...
 
Timo Honkela: Kylmä data kohtaa inhimillisen tulkinnan, Studia Generalia -esi...
Timo Honkela: Kylmä data kohtaa inhimillisen tulkinnan, Studia Generalia -esi...Timo Honkela: Kylmä data kohtaa inhimillisen tulkinnan, Studia Generalia -esi...
Timo Honkela: Kylmä data kohtaa inhimillisen tulkinnan, Studia Generalia -esi...
 
Timo Honkela: Ihminen+ -esitelmä, Mikkeli, 22.9.2016
Timo Honkela: Ihminen+ -esitelmä, Mikkeli, 22.9.2016Timo Honkela: Ihminen+ -esitelmä, Mikkeli, 22.9.2016
Timo Honkela: Ihminen+ -esitelmä, Mikkeli, 22.9.2016
 
Timo Honkela: Kynä ja kone alustus menetelmistä, 15.9.2016
Timo Honkela: Kynä ja kone alustus menetelmistä, 15.9.2016Timo Honkela: Kynä ja kone alustus menetelmistä, 15.9.2016
Timo Honkela: Kynä ja kone alustus menetelmistä, 15.9.2016
 
Honkela. Lagus & Kanner: Parallel Conceptual Spaces and Systems in Health and...
Honkela. Lagus & Kanner: Parallel Conceptual Spaces and Systems in Health and...Honkela. Lagus & Kanner: Parallel Conceptual Spaces and Systems in Health and...
Honkela. Lagus & Kanner: Parallel Conceptual Spaces and Systems in Health and...
 
Timo Honkela: Miten tekoäly muuttaa oppimista ja työtä? Kalajoen lukio, 17.8....
Timo Honkela: Miten tekoäly muuttaa oppimista ja työtä? Kalajoen lukio, 17.8....Timo Honkela: Miten tekoäly muuttaa oppimista ja työtä? Kalajoen lukio, 17.8....
Timo Honkela: Miten tekoäly muuttaa oppimista ja työtä? Kalajoen lukio, 17.8....
 
Timo Honkela: Digitalisaatio tulevaisuudessa
Timo Honkela: Digitalisaatio tulevaisuudessaTimo Honkela: Digitalisaatio tulevaisuudessa
Timo Honkela: Digitalisaatio tulevaisuudessa
 
Timo Honkela: Analysis of Qualitative Data using Machine Learning Methods
Timo Honkela: Analysis of Qualitative Data using Machine Learning MethodsTimo Honkela: Analysis of Qualitative Data using Machine Learning Methods
Timo Honkela: Analysis of Qualitative Data using Machine Learning Methods
 
Timo Honkela: Silta-tilaisuuden alustus, 7.6.2016
Timo Honkela: Silta-tilaisuuden alustus, 7.6.2016Timo Honkela: Silta-tilaisuuden alustus, 7.6.2016
Timo Honkela: Silta-tilaisuuden alustus, 7.6.2016
 

Recently uploaded

This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.christianmathematics
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfSherif Taha
 
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptxCOMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptxannathomasp01
 
REMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptxREMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptxDr. Ravikiran H M Gowda
 
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfUGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfNirmal Dwivedi
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.pptRamjanShidvankar
 
Salient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functionsSalient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functionsKarakKing
 
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...pradhanghanshyam7136
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...ZurliaSoop
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024Elizabeth Walsh
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfAdmir Softic
 
Graduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - EnglishGraduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - Englishneillewis46
 
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptxHMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptxmarlenawright1
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Jisc
 
Towards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxTowards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxJisc
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and ModificationsMJDuyan
 
NO1 Top Black Magic Specialist In Lahore Black magic In Pakistan Kala Ilam Ex...
NO1 Top Black Magic Specialist In Lahore Black magic In Pakistan Kala Ilam Ex...NO1 Top Black Magic Specialist In Lahore Black magic In Pakistan Kala Ilam Ex...
NO1 Top Black Magic Specialist In Lahore Black magic In Pakistan Kala Ilam Ex...Amil baba
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibitjbellavia9
 
Exploring_the_Narrative_Style_of_Amitav_Ghoshs_Gun_Island.pptx
Exploring_the_Narrative_Style_of_Amitav_Ghoshs_Gun_Island.pptxExploring_the_Narrative_Style_of_Amitav_Ghoshs_Gun_Island.pptx
Exploring_the_Narrative_Style_of_Amitav_Ghoshs_Gun_Island.pptxPooja Bhuva
 

Recently uploaded (20)

This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdf
 
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptxCOMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
 
REMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptxREMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptx
 
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfUGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
Salient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functionsSalient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functions
 
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
Graduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - EnglishGraduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - English
 
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptxHMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)
 
Towards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxTowards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptx
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and Modifications
 
NO1 Top Black Magic Specialist In Lahore Black magic In Pakistan Kala Ilam Ex...
NO1 Top Black Magic Specialist In Lahore Black magic In Pakistan Kala Ilam Ex...NO1 Top Black Magic Specialist In Lahore Black magic In Pakistan Kala Ilam Ex...
NO1 Top Black Magic Specialist In Lahore Black magic In Pakistan Kala Ilam Ex...
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibit
 
Exploring_the_Narrative_Style_of_Amitav_Ghoshs_Gun_Island.pptx
Exploring_the_Narrative_Style_of_Amitav_Ghoshs_Gun_Island.pptxExploring_the_Narrative_Style_of_Amitav_Ghoshs_Gun_Island.pptx
Exploring_the_Narrative_Style_of_Amitav_Ghoshs_Gun_Island.pptx
 

Timo Honkela: Spaces of Knowledge

  • 1. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 Timo Honkela Modeling Meaning and Knowledge 1 Feb 2016 timo.honkela@helsinki.fi Spaces of Knowledge
  • 2. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 http://www.cs.cornell.edu/Info/ Department/Annual95/Faculty/Salton.html Advent of vector-based information retrieval ● Gerarg Salton: Documents and queries represented as vectors of term counts ● Similarity between a document and a query is given by the cosine between the term vector and the document vector ● TF-IDF (term-frequency-inverse- document frequency) for weighting of a term in a document ● Inverse document frequency had been introduced by Karen Spärck-Jones in 1972 https://en.wikipedia.org/wiki/Gerard_Salton https://en.wikipedia.org/wiki/Karen_Sp%C3%A4rck_Jones
  • 3. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 University Society D D D Q Q Q 1 1 2 2 3 3 Document 1: The word “university” appears three times and “society” once, etc. Query 1: “university” https://en.wikipedia.org/wiki/Cosine_similarity https://en.wikipedia.org/wiki/Sine
  • 4. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 Contexts tell about meaning ● John Rupert Firth: “You shall know a word by the company it keeps” ● Ludwig Wittgenstein: “For a large class of cases of the employment of the word ‘meaning’—though not for all—this way can be explained in this way: the meaning of a word is its use in the language” (PI 43) https://en.wikipedia.org/wiki/John_Rupert_Firth http://plato.stanford.edu/entries/wittgenstein/#Mea https://en.wikipedia.org/wiki/Ludwig_Wittgenstein
  • 5. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 Analysis of term-document matrices ● The same idea as in information retrieval can also be applied in studying words and expressions ● Statistical analysis of document-term matrices gives rise to models of relationship between words or documents ● Classical examples include – Latent Semantic Analysis (Deerwester, Dumais et al. 1988) – Self-Organizing Semantic Maps (Ritter & Kohonen 1989)
  • 6. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 Word spaces, clusters, clouds, ... ● The analysis of the statistical information related to word contexts can be turned into visualizations of the word relations
  • 7. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 Maps of words in Grimm fairy tales Honkela, Pulkki & Kohonen 1995 Automated learning of word relations using self-organizing map on text context data
  • 8. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 Chemistry Natural sciences and engineering Bio- and environmental sciences Health Culture and society Map of Finnish Science (T. Honkela & M. Klami 2007)
  • 9. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 From term weighting to term selection ● TF-IDF is a widely used method for term weighting ● Likey (Language Independent Keyphrase Extraction) was developed to select terms automally by camparing the corpus at hand with another corpus, called a reference corpus (Paukkeri et al. 2008, Paukkeri & Honkela 2010)
  • 10. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 1. the  1276847 2. of  1067918 3. and    817852 4. in    625330 5. to    357453 6. for   225307 7. is    205723 8. on    162509 9. research 157251 10. be    151475 11. with    136854 12. will    135992 13. as      122707 14. are    116508 15. by   113878 16. university 98003 ... 1. the  2023617 2. of    945622 3. to    883206 4. and    717718 5. in    611421 6. that    473739 7. a    445775 8. is    445119 9. we    305590 10. for    296092 11. i     290412 12. this    286924 13. on    274614 14. it    251343 15. be    246917 16. are    197082 ... Most frequent word forms (types) in two corpora Academy corpus Europarl corpus
  • 11. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 Documents Terms SOM Document map Likey Reference corpus (EU partiament) Academy corpus Term list
  • 12. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 Extralinguistic contexts ● Human beings learn language in real world contexts that include visual, tactile, etc. perceptions ● In order to model meaning in a human-like manner, these other modalities have to be taken into account ● In a project called “Multimodally Grounded Language Technology” we associated visual patterns of human movements with expressions that had been used to describe these movements
  • 13. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 RUNNING WALKING LIMPING JOGGING
  • 14. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 Modeling subjectivity of meaning ● In our method Grounded Intersubjective Concept Analysis (GICA), we added a new “dimension” to the term-document matrices ● We did not assume that each person understands and uses every word in a similar manner but wanted to model the personal variation ● This was achieved by using Subject-Object- Context tensors (Honkela et al. 2012)
  • 15. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 GICA: Grounded Intersubjective Concept Analysis Honkela, Raitio, Lagus & Nieminen 2012
  • 16. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 Analysis of “health” in the State of the Union addresses Subjects on objects in contexts: Using GICA method to quantify epistemological subjectivity. Timo Honkela, Juha Raitio, Krista Lagus, Ilari T. Nieminen, Nina Honkela, and Mika Pantzar. Proc. of IJCNN 2012.
  • 17. Timo Honkela, Modeling Meaning and Knowledge, Spaces of Knowledge, 1.2.2016 Thank you for you attention!