SlideShare a Scribd company logo
© cortical.io inc. 2015
Empower your enterprise with
language intelligence
free access at
api.cortical.io
contact: f.webber@cortical.io
© cortical.io inc. 2015
who we are
• cortical.io inc. science startup in Vienna - Austria
• result of the CEPT project (Cortical Engine for Processing Text)
• advances in brain theory guided us to a fundamentally
new approach for natural language processing
• we are investor backed in the second round
• we made semantic fingerprinting accessible, robust,
scalable, intuitive and easy to use
© cortical.io inc. 2015
big (text) data
• businesses, organizations and
governments are threatened by the
big data explosion.
• a substantial part of this data
consists of text.
• computers ‘understand’ numbers
but ignore the meaning of
language
© cortical.io inc. 2015
the downsides
existing semantic systems are…
…hard to build (sometimes impossible)
…inaccurate & fragile (in real-world use)
…expensive to buy (licenses & services)
…tricky to integrate (setup, tuning, training)
…laborious to run (metadata management)
…hard to maintain (dictionaries, ontologies)
© cortical.io inc. 2015
Semantic Fingerprinting
5
• semantic fingerprinting bridges
the gap between natural
language processing and
knowledge management
• language is represented using
the same data format as found in
the neocortex (mammalian brain)
• the cortical.io Retina behaves like
a sensorial organ for language
• meaning is embodied in
thousands of self-learned
semantic features
© cortical.io inc. 2015
Semantic Fingerprinting
6
organ
piano
church liver
• the cortical.io Retina converts
every word into its semantic
fingerprint
• the fingerprints allow direct
semantic comparison of the
meanings between words
• similar fingerprints have similar
meanings
© cortical.io inc. 2015
Semantic Similarity
7
cat dogcat+dog
home & family 

aspects
cat specific

aspects
dog specific

aspects
biology

aspects
38%
© cortical.io inc. 2015
word sense
disambiguation
rock
apple
computer
sense 1
sense 2
sense …n
songwriter
vocals
spector
airplay
album
seeds
flowers
pollinators
pests
insects
trees
fruit
sense 2a
vegetables
berries
ingredients
sugar
diet
sense 2 …m
food
macintosh
microsoft
linux
software
hardware
© cortical.io inc. 2015
Meaning Based Computing
9
jaguar porsche tiger- =
© cortical.io inc. 2015
Text Fingerprinting
10
• word fingerprints can be
stacked together to form
fingerprints of any piece of text.
• all semantic fingerprint
properties remain: similar
fingerprints mean similar texts.
• representation is made through
more than 16K features.
aggregation+
sparsification
teens like to hear music on
their mobile phones
teens like to hear music on their mobile phones
© cortical.io inc. 2015
teens like playing good music
with their mobile phones
you can also consume chart
hits with your notebook27%
Text Similarity 1
11
© cortical.io inc. 2015
teens like playing good music
with their mobile phones
the fishermen are sailing out
of the harbor9%
Text Similarity 2
12
© cortical.io inc. 2015
similarity engineexample 

document
most similar
documents
ordered along
the users
information need
query document index
result set
ranking
NLP Functionality:
Search
© cortical.io inc. 2015
NLP Functionality:
classification
cow elephantdog spider frog
“mammal	
  or	
  
mammals	
  or	
  
mammalian”
most relevant
matching area
Literally:
© cortical.io inc. 2015
Demos @ cortical.io
Demonstrations
© cortical.io inc. 2015
Evaluation
16
There are very few comparable algorithms: a couple
of academic ones that cannot be readily used for
production purposes and Google’s Word2Vec.
The MEN Test Collection: http://clic.cimec.unitn.it/~elia.bruni/MEN.html
The RG-65 Test Collection: http://www.aclweb.org/aclwiki/index.php?title=RG-65_Test_Collection_(State_of_the_art)
The WordSimilarity-353 Test Collection: http://www.cs.technion.ac.il/~gabr/resources/data/wordsim353/
Yu&Dredzde 2014: http://arxiv.org/pdf/1411.4166.pdf
Distributed representations of words and phrases: http://papers.nips.cc/paper/5021-di
© cortical.io inc. 2015
disciplines
of
language intelligence
• locate documents
• find web content
• match people
• identify products
• monitor competitors
• file business information
• discover new knowledge
• track customer satisfaction
• avoid duplication of work
• advertise on the Internet
• mine for evidences
• improve security
© cortical.io inc. 2015
business applications
“Anything that can be expressed with text can be matched:
- products with LinkedIn profiles, 

- tweets with Facebook timelines, 

- job descriptions with CVs …”
© cortical.io inc. 2015
into a stream of semantic
fingerprints
not
matching
convert the

twitter firehose
to generate a realtime
content sub-stream
MATCHMATCHMATCH
Filter
application: 

streaming text filter
© cortical.io inc. 2015
resulting
filter
fingerprint
creating filter fingerprints
words
text
simple words, keywords
text or text-documents of any
size
profile descriptions or message
postings from social media
the expression builder allows
interactive design of boolean
specifications like:
jaguar - Porsche = tiger
the fingerprint editor allows the
“drawing” of fingerprints. The
meaning of the resulting
fingerprint can be monitored
through the context terms
© cortical.io inc. 2015
• match people by their profiles
• no keyword or field based
string matching limitations
• semantic similarity measure to
compare professional profiles
• different profiles for
professional, leisure, interests,
sports etc…
profile
fingerprint
activity
fingerprint
application: 

profile matching
© cortical.io inc. 2015
• create fingerprints from product
descriptions
• find similar products by
matching description
fingerprints
• create customer fingerprints
from purchased products
product description
fingerprint
Product recommendations
similar products
recommendationsmatch
application: 

product recommendation
© cortical.io inc. 2015
simplicity
• no prior expertise in natural language processing or linguistics
are needed.
• easy and intuitive definition of semantic filters or classifiers.
• all types of text (words, sentences, paragraphs, chapters, books,
etc…) are processed in the same way using fingerprints.
• easy expansion to other languages by switching to any of the
available language retinas.
• zero configuration and no parameter tweaking needed
cortical.io advantages
© cortical.io inc. 2015
cortical.io advantages
efficiency
• semantic fingerprints are small 2K byte sized binary vectors.
• only binary operators are used - no floating point operations
needed.
• linear scalability as the engine takes advantage of a parallel
computing infrastructure (multicore, cluster, virtualization) to
match any performance needed.
• high throughput as complex NLP operations are executed in a
single step and are therefore much faster than with traditional
statistical systems.
© cortical.io inc. 2015
quality
• higher precision on NLP operations due to the large number of semantic
features used (>16K).
• automatic disambiguation of human language due to the novel
approach.
• full language independence, equally high quality results in all languages
due to complete avoidance of any statistical language models.
• no unintended bias as no human input is needed as gold standard.
• automatic update as new words and concepts can be added
continuously.
cortical.io advantages
© cortical.io inc. 2015
Web
 : www.cortical.io
Service : api.cortical.io
Videos : www.cortical.io/company_media.html
Contact : f.webber@cortical.io

More Related Content

PDF
Social media - cortical.io business case
Dataconomy Media
 
PDF
"Updates on Semantic Fingerprinting", Francisco Webber, Inventor and Co-Found...
Dataconomy Media
 
PPTX
Career guidance talk it makaut_ppt_sabyasachi mukhopadhyay
Sabyasachi Mukhopadhyay
 
PPTX
Test strategy for Conversational AI
Shama Ugale
 
PPTX
Why Interop & Security are major issues in IOT?
Mobodexter
 
DOC
Rushabh_Doshi_1_
Rushabh Doshi
 
PDF
50 Billion Connected Things are Coming
Intel® Software
 
PPTX
#ATAGTR2019 Presentation "Security testing using ML(Machine learning), AI(Art...
Agile Testing Alliance
 
Social media - cortical.io business case
Dataconomy Media
 
"Updates on Semantic Fingerprinting", Francisco Webber, Inventor and Co-Found...
Dataconomy Media
 
Career guidance talk it makaut_ppt_sabyasachi mukhopadhyay
Sabyasachi Mukhopadhyay
 
Test strategy for Conversational AI
Shama Ugale
 
Why Interop & Security are major issues in IOT?
Mobodexter
 
Rushabh_Doshi_1_
Rushabh Doshi
 
50 Billion Connected Things are Coming
Intel® Software
 
#ATAGTR2019 Presentation "Security testing using ML(Machine learning), AI(Art...
Agile Testing Alliance
 

What's hot (15)

PPT
新生利用图书馆讲座
xiaobiye
 
PDF
The Convergence of Robotics, the Web, and the IoT
Intel® Software
 
PDF
Review on Computer Forensic
Editor IJCTER
 
PDF
Predicted! Top Software Development Trends for 2021
PixelCrayons
 
PDF
Mobile Applications for Internet of Things (IoT) Enabled Devices
Pratham Software (PSI)
 
PDF
Accelerate Your IoT and Robotics Development Using Web Technology and Apache ...
Intel® Software
 
PDF
[Text Book] IoT Class Material - CoAP, OCF, and IoTivity
Prof. Chung
 
PPTX
AI in Quality Control: How to perform Visual Inspection with AI
Skyl.ai
 
PDF
Outsourcing Internationalization (i18n) Services
Lingoport (www.lingoport.com)
 
PPTX
TatvaSoft Company Profile
Shweta Dastidar
 
PDF
Develop Future Proof IoT: Composable Semantics, Security, FuSa, and QoS
Intel® Software
 
PPTX
Top 5 Software Development Jobs In Trending
Myjobspace
 
PPTX
Kaspars Petersons - BYOD - more like BYOP
DevConFu
 
PDF
Embedded Development - to Fit the Unique Needs of Enterprises Around the Globe
Tizbi, Inc.
 
PPTX
IT Technologies Career perspective
Gopalakrishnan Kulasekaran
 
新生利用图书馆讲座
xiaobiye
 
The Convergence of Robotics, the Web, and the IoT
Intel® Software
 
Review on Computer Forensic
Editor IJCTER
 
Predicted! Top Software Development Trends for 2021
PixelCrayons
 
Mobile Applications for Internet of Things (IoT) Enabled Devices
Pratham Software (PSI)
 
Accelerate Your IoT and Robotics Development Using Web Technology and Apache ...
Intel® Software
 
[Text Book] IoT Class Material - CoAP, OCF, and IoTivity
Prof. Chung
 
AI in Quality Control: How to perform Visual Inspection with AI
Skyl.ai
 
Outsourcing Internationalization (i18n) Services
Lingoport (www.lingoport.com)
 
TatvaSoft Company Profile
Shweta Dastidar
 
Develop Future Proof IoT: Composable Semantics, Security, FuSa, and QoS
Intel® Software
 
Top 5 Software Development Jobs In Trending
Myjobspace
 
Kaspars Petersons - BYOD - more like BYOP
DevConFu
 
Embedded Development - to Fit the Unique Needs of Enterprises Around the Globe
Tizbi, Inc.
 
IT Technologies Career perspective
Gopalakrishnan Kulasekaran
 
Ad

Similar to Empower your Enterprise with language intelligence_Francisco Webber (20)

PDF
Ai One Presentation Semtech 2011 V3
tom_marsh
 
PDF
How AI and ML Can Accelerate and Optimize Software Development and Testing
Aggregage
 
PDF
Testing with an Accent: Internationalization Testing
TechWell
 
PDF
IRJET- Voice to Code Editor using Speech Recognition
IRJET Journal
 
PDF
IDE Code Compiler for the physically challenged (Deaf, Blind & Mute)
IRJET Journal
 
PPTX
The information supernova
Alaa Al-Agamawi
 
PPTX
BrainDocs Solution Update Feb 2013
Boulder Equity Analytics
 
PPTX
sample PPT.pptx
ManishDubey91569
 
PPTX
Algorithm Marketplace and the new "Algorithm Economy"
Diego Oppenheimer
 
PPTX
AI-Driven Development based on Natural Language framework_VercelMeetupLT#2
rikihoshinoejy
 
PPTX
Content Engineering and The Internet of “Smart” Things with Mark Lewis
Information Development World
 
PDF
Testing tools and AI - ideas what to try with some tool examples
Kari Kakkonen
 
PDF
ICIC 2013 New Product Introductions CEPT
Dr. Haxel Consult
 
PDF
Open source in India
Chetan Garg
 
PDF
Unlock the Power of Machine Translation
RDC
 
PPTX
Project on AIkuhkhyubv mbvh cvghym vgh.,vhy
burmundaburkumar72
 
PDF
Deploying Enterprise Search in PLM Context with Aras
Aras
 
PPTX
No Silver Bullet - Essence and Accidents of Software Engineering
Aditi Abhang
 
PDF
Citizen Developer Tools (session at SharePoint Saturday Twin Cities 4/14/2018...
Antti Koskela
 
PDF
Tw Technology Radar Qtb Sep11
Adrian Treacy
 
Ai One Presentation Semtech 2011 V3
tom_marsh
 
How AI and ML Can Accelerate and Optimize Software Development and Testing
Aggregage
 
Testing with an Accent: Internationalization Testing
TechWell
 
IRJET- Voice to Code Editor using Speech Recognition
IRJET Journal
 
IDE Code Compiler for the physically challenged (Deaf, Blind & Mute)
IRJET Journal
 
The information supernova
Alaa Al-Agamawi
 
BrainDocs Solution Update Feb 2013
Boulder Equity Analytics
 
sample PPT.pptx
ManishDubey91569
 
Algorithm Marketplace and the new "Algorithm Economy"
Diego Oppenheimer
 
AI-Driven Development based on Natural Language framework_VercelMeetupLT#2
rikihoshinoejy
 
Content Engineering and The Internet of “Smart” Things with Mark Lewis
Information Development World
 
Testing tools and AI - ideas what to try with some tool examples
Kari Kakkonen
 
ICIC 2013 New Product Introductions CEPT
Dr. Haxel Consult
 
Open source in India
Chetan Garg
 
Unlock the Power of Machine Translation
RDC
 
Project on AIkuhkhyubv mbvh cvghym vgh.,vhy
burmundaburkumar72
 
Deploying Enterprise Search in PLM Context with Aras
Aras
 
No Silver Bullet - Essence and Accidents of Software Engineering
Aditi Abhang
 
Citizen Developer Tools (session at SharePoint Saturday Twin Cities 4/14/2018...
Antti Koskela
 
Tw Technology Radar Qtb Sep11
Adrian Treacy
 
Ad

More from Dataconomy Media (20)

PDF
Data Natives Paris v 10.0 | "Blockchain in Healthcare" - Lea Dias & David An...
Dataconomy Media
 
PDF
Data Natives Frankfurt v 11.0 | "Competitive advantages with knowledge graphs...
Dataconomy Media
 
PDF
Data Natives Frankfurt v 11.0 | "Can we be responsible for misuse of data & a...
Dataconomy Media
 
PDF
Data Natives Munich v 12.0 | "How to be more productive with Autonomous Data ...
Dataconomy Media
 
PPTX
Data Natives meets DataRobot | "Build and deploy an anti-money laundering mo...
Dataconomy Media
 
PPTX
Data Natives Munich v 12.0 | "Political Data Science: A tale of Fake News, So...
Dataconomy Media
 
PPTX
Data Natives Vienna v 7.0 | "Building Kubernetes Operators with KUDO for Dat...
Dataconomy Media
 
PDF
Data Natives Vienna v 7.0 | "The Ingredients of Data Innovation" - Robbert de...
Dataconomy Media
 
PPTX
Data Natives Cologne v 4.0 | "The Data Lorax: Planting the Seeds of Fairness...
Dataconomy Media
 
PDF
Data Natives Cologne v 4.0 | "How People Analytics Can Reveal the Hidden Aspe...
Dataconomy Media
 
PPTX
Data Natives Amsterdam v 9.0 | "Ten Little Servers: A Story of no Downtime" -...
Dataconomy Media
 
PDF
Data Natives Amsterdam v 9.0 | "Point in Time Labeling at Scale" - Timothy Th...
Dataconomy Media
 
PDF
Data Natives Hamburg v 6.0 | "Interpersonal behavior: observing Alex to under...
Dataconomy Media
 
PDF
Data Natives Hamburg v 6.0 | "About Surfing, Failing & Scaling" - Florian Sch...
Dataconomy Media
 
PDF
Data NativesBerlin v 20.0 | "Serving A/B experimentation platform end-to-end"...
Dataconomy Media
 
PPTX
Data Natives Berlin v 20.0 | "Ten Little Servers: A Story of no Downtime" - A...
Dataconomy Media
 
PDF
Big Data Frankfurt meets Thinkport | "The Cloud as a Driver of Innovation" - ...
Dataconomy Media
 
PPTX
Thinkport meets Frankfurt | "Financial Time Series Analysis using Wavelets" -...
Dataconomy Media
 
PPTX
Big Data Helsinki v 3 | "Distributed Machine and Deep Learning at Scale with ...
Dataconomy Media
 
PPTX
Big Data Helsinki v 3 | "Federated Learning and Privacy-preserving AI" - Oguz...
Dataconomy Media
 
Data Natives Paris v 10.0 | "Blockchain in Healthcare" - Lea Dias & David An...
Dataconomy Media
 
Data Natives Frankfurt v 11.0 | "Competitive advantages with knowledge graphs...
Dataconomy Media
 
Data Natives Frankfurt v 11.0 | "Can we be responsible for misuse of data & a...
Dataconomy Media
 
Data Natives Munich v 12.0 | "How to be more productive with Autonomous Data ...
Dataconomy Media
 
Data Natives meets DataRobot | "Build and deploy an anti-money laundering mo...
Dataconomy Media
 
Data Natives Munich v 12.0 | "Political Data Science: A tale of Fake News, So...
Dataconomy Media
 
Data Natives Vienna v 7.0 | "Building Kubernetes Operators with KUDO for Dat...
Dataconomy Media
 
Data Natives Vienna v 7.0 | "The Ingredients of Data Innovation" - Robbert de...
Dataconomy Media
 
Data Natives Cologne v 4.0 | "The Data Lorax: Planting the Seeds of Fairness...
Dataconomy Media
 
Data Natives Cologne v 4.0 | "How People Analytics Can Reveal the Hidden Aspe...
Dataconomy Media
 
Data Natives Amsterdam v 9.0 | "Ten Little Servers: A Story of no Downtime" -...
Dataconomy Media
 
Data Natives Amsterdam v 9.0 | "Point in Time Labeling at Scale" - Timothy Th...
Dataconomy Media
 
Data Natives Hamburg v 6.0 | "Interpersonal behavior: observing Alex to under...
Dataconomy Media
 
Data Natives Hamburg v 6.0 | "About Surfing, Failing & Scaling" - Florian Sch...
Dataconomy Media
 
Data NativesBerlin v 20.0 | "Serving A/B experimentation platform end-to-end"...
Dataconomy Media
 
Data Natives Berlin v 20.0 | "Ten Little Servers: A Story of no Downtime" - A...
Dataconomy Media
 
Big Data Frankfurt meets Thinkport | "The Cloud as a Driver of Innovation" - ...
Dataconomy Media
 
Thinkport meets Frankfurt | "Financial Time Series Analysis using Wavelets" -...
Dataconomy Media
 
Big Data Helsinki v 3 | "Distributed Machine and Deep Learning at Scale with ...
Dataconomy Media
 
Big Data Helsinki v 3 | "Federated Learning and Privacy-preserving AI" - Oguz...
Dataconomy Media
 

Recently uploaded (20)

PDF
Key_Statistical_Techniques_in_Analytics_by_CA_Suvidha_Chaplot.pdf
CA Suvidha Chaplot
 
PPTX
Introduction to Biostatistics Presentation.pptx
AtemJoshua
 
PDF
Practical Measurement Systems Analysis (Gage R&R) for design
Rob Schubert
 
PPTX
short term project on AI Driven Data Analytics
JMJCollegeComputerde
 
PDF
202501214233242351219 QASS Session 2.pdf
lauramejiamillan
 
PPTX
INFO8116 -Big data architecture and analytics
guddipatel10
 
PPTX
Pipeline Automatic Leak Detection for Water Distribution Systems
Sione Palu
 
PDF
blockchain123456789012345678901234567890
tanvikhunt1003
 
PDF
Blitz Campinas - Dia 24 de maio - Piettro.pdf
fabigreek
 
PDF
D9110.pdfdsfvsdfvsdfvsdfvfvfsvfsvffsdfvsdfvsd
minhn6673
 
PPTX
Fuzzy_Membership_Functions_Presentation.pptx
pythoncrazy2024
 
PPTX
Data Security Breach: Immediate Action Plan
varmabhuvan266
 
PDF
Blue Futuristic Cyber Security Presentation.pdf
tanvikhunt1003
 
PPTX
INFO8116 - Week 10 - Slides.pptx data analutics
guddipatel10
 
PDF
SUMMER INTERNSHIP REPORT[1] (AutoRecovered) (6) (1).pdf
pandeydiksha814
 
PPTX
Probability systematic sampling methods.pptx
PrakashRajput19
 
PPTX
World-population.pptx fire bunberbpeople
umutunsalnsl4402
 
PPTX
Blue and Dark Blue Modern Technology Presentation.pptx
ap177979
 
PPTX
Future_of_AI_Presentation for everyone.pptx
boranamanju07
 
PPTX
lecture 13 mind test academy it skills.pptx
ggesjmrasoolpark
 
Key_Statistical_Techniques_in_Analytics_by_CA_Suvidha_Chaplot.pdf
CA Suvidha Chaplot
 
Introduction to Biostatistics Presentation.pptx
AtemJoshua
 
Practical Measurement Systems Analysis (Gage R&R) for design
Rob Schubert
 
short term project on AI Driven Data Analytics
JMJCollegeComputerde
 
202501214233242351219 QASS Session 2.pdf
lauramejiamillan
 
INFO8116 -Big data architecture and analytics
guddipatel10
 
Pipeline Automatic Leak Detection for Water Distribution Systems
Sione Palu
 
blockchain123456789012345678901234567890
tanvikhunt1003
 
Blitz Campinas - Dia 24 de maio - Piettro.pdf
fabigreek
 
D9110.pdfdsfvsdfvsdfvsdfvfvfsvfsvffsdfvsdfvsd
minhn6673
 
Fuzzy_Membership_Functions_Presentation.pptx
pythoncrazy2024
 
Data Security Breach: Immediate Action Plan
varmabhuvan266
 
Blue Futuristic Cyber Security Presentation.pdf
tanvikhunt1003
 
INFO8116 - Week 10 - Slides.pptx data analutics
guddipatel10
 
SUMMER INTERNSHIP REPORT[1] (AutoRecovered) (6) (1).pdf
pandeydiksha814
 
Probability systematic sampling methods.pptx
PrakashRajput19
 
World-population.pptx fire bunberbpeople
umutunsalnsl4402
 
Blue and Dark Blue Modern Technology Presentation.pptx
ap177979
 
Future_of_AI_Presentation for everyone.pptx
boranamanju07
 
lecture 13 mind test academy it skills.pptx
ggesjmrasoolpark
 

Empower your Enterprise with language intelligence_Francisco Webber

  • 1. © cortical.io inc. 2015 Empower your enterprise with language intelligence free access at api.cortical.io contact: [email protected]
  • 2. © cortical.io inc. 2015 who we are • cortical.io inc. science startup in Vienna - Austria • result of the CEPT project (Cortical Engine for Processing Text) • advances in brain theory guided us to a fundamentally new approach for natural language processing • we are investor backed in the second round • we made semantic fingerprinting accessible, robust, scalable, intuitive and easy to use
  • 3. © cortical.io inc. 2015 big (text) data • businesses, organizations and governments are threatened by the big data explosion. • a substantial part of this data consists of text. • computers ‘understand’ numbers but ignore the meaning of language
  • 4. © cortical.io inc. 2015 the downsides existing semantic systems are… …hard to build (sometimes impossible) …inaccurate & fragile (in real-world use) …expensive to buy (licenses & services) …tricky to integrate (setup, tuning, training) …laborious to run (metadata management) …hard to maintain (dictionaries, ontologies)
  • 5. © cortical.io inc. 2015 Semantic Fingerprinting 5 • semantic fingerprinting bridges the gap between natural language processing and knowledge management • language is represented using the same data format as found in the neocortex (mammalian brain) • the cortical.io Retina behaves like a sensorial organ for language • meaning is embodied in thousands of self-learned semantic features
  • 6. © cortical.io inc. 2015 Semantic Fingerprinting 6 organ piano church liver • the cortical.io Retina converts every word into its semantic fingerprint • the fingerprints allow direct semantic comparison of the meanings between words • similar fingerprints have similar meanings
  • 7. © cortical.io inc. 2015 Semantic Similarity 7 cat dogcat+dog home & family 
 aspects cat specific
 aspects dog specific
 aspects biology
 aspects 38%
  • 8. © cortical.io inc. 2015 word sense disambiguation rock apple computer sense 1 sense 2 sense …n songwriter vocals spector airplay album seeds flowers pollinators pests insects trees fruit sense 2a vegetables berries ingredients sugar diet sense 2 …m food macintosh microsoft linux software hardware
  • 9. © cortical.io inc. 2015 Meaning Based Computing 9 jaguar porsche tiger- =
  • 10. © cortical.io inc. 2015 Text Fingerprinting 10 • word fingerprints can be stacked together to form fingerprints of any piece of text. • all semantic fingerprint properties remain: similar fingerprints mean similar texts. • representation is made through more than 16K features. aggregation+ sparsification teens like to hear music on their mobile phones teens like to hear music on their mobile phones
  • 11. © cortical.io inc. 2015 teens like playing good music with their mobile phones you can also consume chart hits with your notebook27% Text Similarity 1 11
  • 12. © cortical.io inc. 2015 teens like playing good music with their mobile phones the fishermen are sailing out of the harbor9% Text Similarity 2 12
  • 13. © cortical.io inc. 2015 similarity engineexample 
 document most similar documents ordered along the users information need query document index result set ranking NLP Functionality: Search
  • 14. © cortical.io inc. 2015 NLP Functionality: classification cow elephantdog spider frog “mammal  or   mammals  or   mammalian” most relevant matching area Literally:
  • 15. © cortical.io inc. 2015 Demos @ cortical.io Demonstrations
  • 16. © cortical.io inc. 2015 Evaluation 16 There are very few comparable algorithms: a couple of academic ones that cannot be readily used for production purposes and Google’s Word2Vec. The MEN Test Collection: http://clic.cimec.unitn.it/~elia.bruni/MEN.html The RG-65 Test Collection: http://www.aclweb.org/aclwiki/index.php?title=RG-65_Test_Collection_(State_of_the_art) The WordSimilarity-353 Test Collection: http://www.cs.technion.ac.il/~gabr/resources/data/wordsim353/ Yu&Dredzde 2014: http://arxiv.org/pdf/1411.4166.pdf Distributed representations of words and phrases: http://papers.nips.cc/paper/5021-di
  • 17. © cortical.io inc. 2015 disciplines of language intelligence • locate documents • find web content • match people • identify products • monitor competitors • file business information • discover new knowledge • track customer satisfaction • avoid duplication of work • advertise on the Internet • mine for evidences • improve security
  • 18. © cortical.io inc. 2015 business applications “Anything that can be expressed with text can be matched: - products with LinkedIn profiles, 
 - tweets with Facebook timelines, 
 - job descriptions with CVs …”
  • 19. © cortical.io inc. 2015 into a stream of semantic fingerprints not matching convert the
 twitter firehose to generate a realtime content sub-stream MATCHMATCHMATCH Filter application: 
 streaming text filter
  • 20. © cortical.io inc. 2015 resulting filter fingerprint creating filter fingerprints words text simple words, keywords text or text-documents of any size profile descriptions or message postings from social media the expression builder allows interactive design of boolean specifications like: jaguar - Porsche = tiger the fingerprint editor allows the “drawing” of fingerprints. The meaning of the resulting fingerprint can be monitored through the context terms
  • 21. © cortical.io inc. 2015 • match people by their profiles • no keyword or field based string matching limitations • semantic similarity measure to compare professional profiles • different profiles for professional, leisure, interests, sports etc… profile fingerprint activity fingerprint application: 
 profile matching
  • 22. © cortical.io inc. 2015 • create fingerprints from product descriptions • find similar products by matching description fingerprints • create customer fingerprints from purchased products product description fingerprint Product recommendations similar products recommendationsmatch application: 
 product recommendation
  • 23. © cortical.io inc. 2015 simplicity • no prior expertise in natural language processing or linguistics are needed. • easy and intuitive definition of semantic filters or classifiers. • all types of text (words, sentences, paragraphs, chapters, books, etc…) are processed in the same way using fingerprints. • easy expansion to other languages by switching to any of the available language retinas. • zero configuration and no parameter tweaking needed cortical.io advantages
  • 24. © cortical.io inc. 2015 cortical.io advantages efficiency • semantic fingerprints are small 2K byte sized binary vectors. • only binary operators are used - no floating point operations needed. • linear scalability as the engine takes advantage of a parallel computing infrastructure (multicore, cluster, virtualization) to match any performance needed. • high throughput as complex NLP operations are executed in a single step and are therefore much faster than with traditional statistical systems.
  • 25. © cortical.io inc. 2015 quality • higher precision on NLP operations due to the large number of semantic features used (>16K). • automatic disambiguation of human language due to the novel approach. • full language independence, equally high quality results in all languages due to complete avoidance of any statistical language models. • no unintended bias as no human input is needed as gold standard. • automatic update as new words and concepts can be added continuously. cortical.io advantages
  • 26. © cortical.io inc. 2015 Web : www.cortical.io Service : api.cortical.io Videos : www.cortical.io/company_media.html Contact : [email protected]