from big text to big knowledge - indian statistical …acmsc/wbda2015/slides/ppt/ppt-isi...from big...

149
Derry Wijaya Tom Mitchell Partha Talukdar Machine And Language Learning (MALL) Lab SERC & CSA, Indian Institute of Science Matt Gardner Bryan Kisiel From Big Text to Big Knowledge Carnegie Mellon University

Upload: dinhduong

Post on 12-Apr-2018

221 views

Category:

Documents


2 download

TRANSCRIPT

Derry WijayaTom Mitchell

Partha TalukdarMachine And Language Learning (MALL) Lab

SERC & CSA, Indian Institute of Science

Matt Gardner Bryan Kisiel

From Big Text to Big Knowledge

Carnegie Mellon University

IISc Overview

Indian Institute of Science (IISc), Bangalore

• Top research institute in India • Exceptional research freedom • Various programs: PhD, MSc,

Integrated PhD, MTech • Beautiful campus, great city

6

CSA : RESEARCH AREAS

MACHINE LEARNING, AI, PATTERN RECOGNITION,

DATA MINING, ANALYTICS, NLP M. N. Murty, Chiranjib Bhattacharyya Shirish Shevade, Shalabh Bhatnagar,

Susheela Devi, Shivani Agarwal, Ambedkar, Partha Talukdar

GAME THEORY AND MECHANISM DESIGN

Y. Narahari, Shalabh Bhatnagar,

Shirish Shevade Shivani Agarwal

STOCHASTIC CONTROL AND OPTIMIZATION,

REINFORCEMENT LEARNING

Shalabh Bhatnagar, Ambedkar, Chairanjib Bhattacharya,

Shivani Agarwal

ALGORITHMS, COMPLEXITY, GRAPH THEORY,

COMBINATORICS, GEOMETRY Sunil Chandran, Satish Govindarajan,

Vijay , Chandan, Arnab, R. Hariharan, R.Kannan, Neeldhara

INFO. THEORY, CODING,

ALGORITHMIC ALGEBRA

D. Ambedkar, Arnab, PVK, D. Patil, Bhavana

AUTOMATA THEORY, FORMAL METHODS,

LOGICS Deepak D’Souza, Aditya Kanade, K.V. Raghavan,

K. Gopinath

PROG. LANGUAGES, COMPILERS,

SOFTWARE ENGINEERING Y. N. Srikant, K.V. Raghavan,

Aditya Kanade, Murali Krishna, Uday Kumar, D. D’Souza,

R. Govindarajan,K. Gopinath,

ARCHITECTURE, OS, STORAGE, NETWORKS, DISTRIBUTED COMPUTING Matthew Jacob, R. Govindarajan,

K. Gopinath, R.C. Hansdah, Shalabh, Uday Kumar, Murali Krishna, Arpita,

Bhavana

DATABASE SYSTEMS

Jayant Haritsa, R.C. Hansdah,Partha Talukdar

CRYPTOLOGY, SECURITY

Sanjit Chatterjee, Arpita, Bhavana,

K. Gopinath, R.C. Hansdah

VISUALIZATION, GRAPHICS,

COMP. TOPOLOGY Vijay Natarajan

Satish Govindarajan

6

CSA : RESEARCH AREAS

MACHINE LEARNING, AI, PATTERN RECOGNITION,

DATA MINING, ANALYTICS, NLP M. N. Murty, Chiranjib Bhattacharyya Shirish Shevade, Shalabh Bhatnagar,

Susheela Devi, Shivani Agarwal, Ambedkar, Partha Talukdar

GAME THEORY AND MECHANISM DESIGN

Y. Narahari, Shalabh Bhatnagar,

Shirish Shevade Shivani Agarwal

STOCHASTIC CONTROL AND OPTIMIZATION,

REINFORCEMENT LEARNING

Shalabh Bhatnagar, Ambedkar, Chairanjib Bhattacharya,

Shivani Agarwal

ALGORITHMS, COMPLEXITY, GRAPH THEORY,

COMBINATORICS, GEOMETRY Sunil Chandran, Satish Govindarajan,

Vijay , Chandan, Arnab, R. Hariharan, R.Kannan, Neeldhara

INFO. THEORY, CODING,

ALGORITHMIC ALGEBRA

D. Ambedkar, Arnab, PVK, D. Patil, Bhavana

AUTOMATA THEORY, FORMAL METHODS,

LOGICS Deepak D’Souza, Aditya Kanade, K.V. Raghavan,

K. Gopinath

PROG. LANGUAGES, COMPILERS,

SOFTWARE ENGINEERING Y. N. Srikant, K.V. Raghavan,

Aditya Kanade, Murali Krishna, Uday Kumar, D. D’Souza,

R. Govindarajan,K. Gopinath,

ARCHITECTURE, OS, STORAGE, NETWORKS, DISTRIBUTED COMPUTING Matthew Jacob, R. Govindarajan,

K. Gopinath, R.C. Hansdah, Shalabh, Uday Kumar, Murali Krishna, Arpita,

Bhavana

DATABASE SYSTEMS

Jayant Haritsa, R.C. Hansdah,Partha Talukdar

CRYPTOLOGY, SECURITY

Sanjit Chatterjee, Arpita, Bhavana,

K. Gopinath, R.C. Hansdah

THEORY

VISUALIZATION, GRAPHICS,

COMP. TOPOLOGY Vijay Natarajan

Satish Govindarajan

6

CSA : RESEARCH AREAS

MACHINE LEARNING, AI, PATTERN RECOGNITION,

DATA MINING, ANALYTICS, NLP M. N. Murty, Chiranjib Bhattacharyya Shirish Shevade, Shalabh Bhatnagar,

Susheela Devi, Shivani Agarwal, Ambedkar, Partha Talukdar

GAME THEORY AND MECHANISM DESIGN

Y. Narahari, Shalabh Bhatnagar,

Shirish Shevade Shivani Agarwal

STOCHASTIC CONTROL AND OPTIMIZATION,

REINFORCEMENT LEARNING

Shalabh Bhatnagar, Ambedkar, Chairanjib Bhattacharya,

Shivani Agarwal

ALGORITHMS, COMPLEXITY, GRAPH THEORY,

COMBINATORICS, GEOMETRY Sunil Chandran, Satish Govindarajan,

Vijay , Chandan, Arnab, R. Hariharan, R.Kannan, Neeldhara

INFO. THEORY, CODING,

ALGORITHMIC ALGEBRA

D. Ambedkar, Arnab, PVK, D. Patil, Bhavana

AUTOMATA THEORY, FORMAL METHODS,

LOGICS Deepak D’Souza, Aditya Kanade, K.V. Raghavan,

K. Gopinath

PROG. LANGUAGES, COMPILERS,

SOFTWARE ENGINEERING Y. N. Srikant, K.V. Raghavan,

Aditya Kanade, Murali Krishna, Uday Kumar, D. D’Souza,

R. Govindarajan,K. Gopinath,

ARCHITECTURE, OS, STORAGE, NETWORKS, DISTRIBUTED COMPUTING Matthew Jacob, R. Govindarajan,

K. Gopinath, R.C. Hansdah, Shalabh, Uday Kumar, Murali Krishna, Arpita,

Bhavana

DATABASE SYSTEMS

Jayant Haritsa, R.C. Hansdah,Partha Talukdar

CRYPTOLOGY, SECURITY

Sanjit Chatterjee, Arpita, Bhavana,

K. Gopinath, R.C. Hansdah

THEORY

COMPUTER SYSTEMS

VISUALIZATION, GRAPHICS,

COMP. TOPOLOGY Vijay Natarajan

Satish Govindarajan

6

CSA : RESEARCH AREAS

MACHINE LEARNING, AI, PATTERN RECOGNITION,

DATA MINING, ANALYTICS, NLP M. N. Murty, Chiranjib Bhattacharyya Shirish Shevade, Shalabh Bhatnagar,

Susheela Devi, Shivani Agarwal, Ambedkar, Partha Talukdar

GAME THEORY AND MECHANISM DESIGN

Y. Narahari, Shalabh Bhatnagar,

Shirish Shevade Shivani Agarwal

STOCHASTIC CONTROL AND OPTIMIZATION,

REINFORCEMENT LEARNING

Shalabh Bhatnagar, Ambedkar, Chairanjib Bhattacharya,

Shivani Agarwal

ALGORITHMS, COMPLEXITY, GRAPH THEORY,

COMBINATORICS, GEOMETRY Sunil Chandran, Satish Govindarajan,

Vijay , Chandan, Arnab, R. Hariharan, R.Kannan, Neeldhara

INFO. THEORY, CODING,

ALGORITHMIC ALGEBRA

D. Ambedkar, Arnab, PVK, D. Patil, Bhavana

AUTOMATA THEORY, FORMAL METHODS,

LOGICS Deepak D’Souza, Aditya Kanade, K.V. Raghavan,

K. Gopinath

PROG. LANGUAGES, COMPILERS,

SOFTWARE ENGINEERING Y. N. Srikant, K.V. Raghavan,

Aditya Kanade, Murali Krishna, Uday Kumar, D. D’Souza,

R. Govindarajan,K. Gopinath,

ARCHITECTURE, OS, STORAGE, NETWORKS, DISTRIBUTED COMPUTING Matthew Jacob, R. Govindarajan,

K. Gopinath, R.C. Hansdah, Shalabh, Uday Kumar, Murali Krishna, Arpita,

Bhavana

DATABASE SYSTEMS

Jayant Haritsa, R.C. Hansdah,Partha Talukdar

CRYPTOLOGY, SECURITY

Sanjit Chatterjee, Arpita, Bhavana,

K. Gopinath, R.C. Hansdah

THEORY

COMPUTER SYSTEMS

INTELLIGENT SYSTEMS

VISUALIZATION, GRAPHICS,

COMP. TOPOLOGY Vijay Natarajan

Satish Govindarajan

Publications (2008-2013)

■ Number of Publications Books and Monographs 11 Book Chapters 25 Journal Publications 151 Conference Publications 260

■ Journals include SIAM, IEEE, ACM, JMLR, NC, ML, JA, TCS, JGT, JCSS, I&C, DCG, JCT, SN, etc.

■ Conferences include STOC, FOCS, SODA, SOCG, ICALP, STACS, LFCS, ISAAC, CC, ICDE, VLDB, AAMAS, NIPS, ICML, UAI, ICDM, COLT, ICPR, IJCAI, AAAI, IJCNN, SIGIR, SIGKDD, SIGMOD, WINE, SDM, ICDAR, IEEE VIS, PLDI, POPL, ICSE, OOPSLA, CGO, EMSOFT, CASES, FORMATS, SAS, SC, FAST, HotOS, HotStorage, SIGMETRICS, PPoPP, PACT

Sponsors and Collaborators ■ Govt. of India: UGC (CAS), UGC (Infrastructure), DST-FIST, DST

SERC (12 Projects), DBT, DRDO, DIT ■ Universities: MIT, Technion, Harvard, UCB, UCD, UCSC, IITB, IITM,

CMI, ISI, JNU, TIFR, MPI, SUNY, MSU, Alberta, EURANDOM, CMI, Waterloo, Grenoble, Zurich, Leipzig, INRIA, CMU, York, Chalmers

■ Industry Collaborative Projects: IBM, Infosys, TRDDC, Motorola, GM R & D, SUN, NetApp, AOL, Xerox, TI, Microsoft Research India, Philips, Intel, AMD, Yahoo!, SAP, Nokia, Adobe

■ Industry Faculty Awards: IBM, TRDDC, GM R & D, Microsoft Research India, AMD, Yahoo!, Google, Bell Labs

■ Overseas Agencies: ONR, Lawrence Livermore, AOARD, Swiss Bilateral, Indo-German, UKERI, Max-Planck

Supercomputer Education & Research Centre (SERC)

• A multi-disciplinary department in IISc • A state-of-the-art supercomputing research

facility with a cutting-edge research program

http://www.serc.iisc.in/

Research at SERC

Research at SERC

Computer Systems� CAD for VLSI � Cloud Computing � Computer Architecture � Database Systems � Distributed Systems � High Performance Computing � Information Systems � Middleware Research � Machine Learning and NLP � Parallel Computing � Visualization & Graphics � Video Analytics

Research at SERC

Computer Systems� CAD for VLSI � Cloud Computing � Computer Architecture � Database Systems � Distributed Systems � High Performance Computing � Information Systems � Middleware Research � Machine Learning and NLP � Parallel Computing � Visualization & Graphics � Video Analytics

Computational Science� Computational

Electromagnetics � Computational Photonics � Medical Imaging � Scientific Computing and

Mathematical Libraries � Computational Fluid

Dynamics � Computational Biology and

Bioinformatics � Quantum Computing

Machine Learning @ IISc

• 13+ faculty from multiple departments (CSA, SERC, ECE, EE)

• Highly active research group, strong international presence

• http://drona.csa.iisc.ernet.in/~mlcenter/index.html

Research Programs at IISc� Ph.D. and M.Sc [Engg] � Min. Qualification:

➢ ME / M Tech or BE / B Tech or equivalent degree in any Engineering discipline or

➢ M Sc or equivalent degree in Mathematics, Physics, Statistics, Electronics, Instrumentation or Computer Sciences or

➢ Master’s in Computer Application. � Selection process

➢ Shortlisting (GATE scores) and Interview

Research Programs at IISc� Ph.D. and M.Sc [Engg] � Min. Qualification:

➢ ME / M Tech or BE / B Tech or equivalent degree in any Engineering discipline or

➢ M Sc or equivalent degree in Mathematics, Physics, Statistics, Electronics, Instrumentation or Computer Sciences or

➢ Master’s in Computer Application. � Selection process

➢ Shortlisting (GATE scores) and Interview

Come Join Us!

Back to Text & Knowledge

Thesis

13

Background knowledge is key to Intelligent Decision Making

Thesis

13

Background knowledge is key to Intelligent Decision Making

Thesis

13

Background knowledge is key to Intelligent Decision Making

?

Thesis

13

Background knowledge is key to Intelligent Decision Making

?

Thesis

13

Background knowledge is key to Intelligent Decision Making

inventedCharacter

Explosion  of  Unstructured  Text  Data

14

Explosion  of  Unstructured  Text  Data

14

Sources: http://royal.pingdom.com/2012/01/17/internet-2011-in-numbers/, http://blog.twitter.com/2011/06/200-million-tweets-per-day.html

300  million  new  websites  added  in  2011  alone  (a  117%  growth)    

Explosion  of  Unstructured  Text  Data

500  million  Tweets  per  day  (circa  Oct  2012)

14

Sources: http://royal.pingdom.com/2012/01/17/internet-2011-in-numbers/, http://blog.twitter.com/2011/06/200-million-tweets-per-day.html

300  million  new  websites  added  in  2011  alone  (a  117%  growth)    

Explosion  of  Unstructured  Text  Data

500  million  Tweets  per  day  (circa  Oct  2012)Time  to  read  for  one  person:  31years

14

Sources: http://royal.pingdom.com/2012/01/17/internet-2011-in-numbers/, http://blog.twitter.com/2011/06/200-million-tweets-per-day.html

300  million  new  websites  added  in  2011  alone  (a  117%  growth)    

Explosion  of  Unstructured  Text  Data

500  million  Tweets  per  day  (circa  Oct  2012)Time  to  read  for  one  person:  31years

14

Sources: http://royal.pingdom.com/2012/01/17/internet-2011-in-numbers/, http://blog.twitter.com/2011/06/200-million-tweets-per-day.html

300  million  new  websites  added  in  2011  alone  (a  117%  growth)    

Need  to  harvest  knowledge  from  unstructured  text  data

What  is  Knowledge  HarvesBng  from  Unstructured  Text?

15

What  is  Knowledge  HarvesBng  from  Unstructured  Text?

15

... Luke Ravenstahl is the current Mayor of

Pittsburgh ...

... After the death of then-mayor Bob O’Connor, Luke Ravenstahl became the

mayor in September 2006 ...

Document 1 Document 2

What  is  Knowledge  HarvesBng  from  Unstructured  Text?

15

Person

Luke  Ravenstahl

Bob  O’Connor

... Luke Ravenstahl is the current Mayor of

Pittsburgh ...

... After the death of then-mayor Bob O’Connor, Luke Ravenstahl became the

mayor in September 2006 ...

Document 1 Document 2

What  is  Knowledge  HarvesBng  from  Unstructured  Text?

15

Person

Luke  Ravenstahl

Bob  O’Connor

LocaBon

PiIsburgh

... Luke Ravenstahl is the current Mayor of

Pittsburgh ...

... After the death of then-mayor Bob O’Connor, Luke Ravenstahl became the

mayor in September 2006 ...

Document 1 Document 2

What  is  Knowledge  HarvesBng  from  Unstructured  Text?

15

Person

Luke  Ravenstahl

Bob  O’Connor

LocaBon

PiIsburgh

MayorOf

MayorOf

... Luke Ravenstahl is the current Mayor of

Pittsburgh ...

... After the death of then-mayor Bob O’Connor, Luke Ravenstahl became the

mayor in September 2006 ...

Document 1 Document 2

What  is  Knowledge  HarvesBng  from  Unstructured  Text?

15

Person MayorOf

Bob  O’Connor PiIsburgh

Valid  UnLl  Sep/2006

... Luke Ravenstahl is the current Mayor of

Pittsburgh ...

... After the death of then-mayor Bob O’Connor, Luke Ravenstahl became the

mayor in September 2006 ...

Document 1 Document 2

What  is  Knowledge  HarvesBng  from  Unstructured  Text?

15

Person MayorOf

Bob  O’Connor PiIsburgh

Valid  UnLl  Sep/2006

Person MayorOf

Luke  Ravenstahl PiIsburgh

Valid  From  Sep/2006

... Luke Ravenstahl is the current Mayor of

Pittsburgh ...

... After the death of then-mayor Bob O’Connor, Luke Ravenstahl became the

mayor in September 2006 ...

Document 1 Document 2

Use  of  Harvested  Knowledge:  Google  Knowledge  Graph

16

Use  of  Harvested  Knowledge:  Google  Knowledge  Graph

16

Improved Web Search

Experience, facilitated by Harvested Knowledge

Use  of  Harvested  Knowledge:  Google  Knowledge  Graph

16

Improved Web Search

Experience, facilitated by Harvested Knowledge

No Structured Information

Use  of  Harvested  Knowledge:  Google  Knowledge  Graph

16

Improved Web Search

Experience, facilitated by Harvested Knowledge

No Structured Information

http://venturebeat.com/2013/01/22/larry-page-on-googles-knowledge-graph-were-still-at-1-of-where-we-want-to-be/

“We’re  sBll  at  1  percent  of  where  we  should  be.”  -- Larry Page (Google CEO) on Knowledge Graph [Jan 22, 2013]

New  paradigm  for  Machine  Learning:

Never  Ending  Learning  agent

17

New  paradigm  for  Machine  Learning:

Never  Ending  Learning  agentPersistent  soSware  individual

17

New  paradigm  for  Machine  Learning:

Never  Ending  Learning  agentPersistent  soSware  individualLearns  many  funcLons  /  knowledge  types

17

New  paradigm  for  Machine  Learning:

Never  Ending  Learning  agentPersistent  soSware  individualLearns  many  funcLons  /  knowledge  typesLearns  easier  things  first,  then  more  difficult

17

New  paradigm  for  Machine  Learning:

Never  Ending  Learning  agentPersistent  soSware  individualLearns  many  funcLons  /  knowledge  typesLearns  easier  things  first,  then  more  difficultThe  more  it  learns,  the  more  it  can  learn  next

17

New  paradigm  for  Machine  Learning:

Never  Ending  Learning  agentPersistent  soSware  individualLearns  many  funcLons  /  knowledge  typesLearns  easier  things  first,  then  more  difficultThe  more  it  learns,  the  more  it  can  learn  nextLearns  from  experience,  and  from  advice

17

NELL:  Never  Ending  Language  Learner

18

NELL:  Never  Ending  Language  LearnerInputs:

18

NELL:  Never  Ending  Language  LearnerInputs:•iniLal  ontology  

18

NELL:  Never  Ending  Language  LearnerInputs:•iniLal  ontology  •few  seed  examples  of  each  ontology  predicate

18

NELL:  Never  Ending  Language  LearnerInputs:•iniLal  ontology  •few  seed  examples  of  each  ontology  predicate•the  web

18

NELL:  Never  Ending  Language  LearnerInputs:•iniLal  ontology  •few  seed  examples  of  each  ontology  predicate•the  web•occasional  interacLon  with  human  trainers

18

NELL:  Never  Ending  Language  LearnerInputs:•iniLal  ontology  •few  seed  examples  of  each  ontology  predicate•the  web•occasional  interacLon  with  human  trainers

18

NELL:  Never  Ending  Language  LearnerInputs:•iniLal  ontology  •few  seed  examples  of  each  ontology  predicate•the  web•occasional  interacLon  with  human  trainers

The  task:

18

NELL:  Never  Ending  Language  LearnerInputs:•iniLal  ontology  •few  seed  examples  of  each  ontology  predicate•the  web•occasional  interacLon  with  human  trainers

The  task:• run  24x7,  forever

18

NELL:  Never  Ending  Language  LearnerInputs:•iniLal  ontology  •few  seed  examples  of  each  ontology  predicate•the  web•occasional  interacLon  with  human  trainers

The  task:• run  24x7,  forever• each  day:

18

NELL:  Never  Ending  Language  LearnerInputs:•iniLal  ontology  •few  seed  examples  of  each  ontology  predicate•the  web•occasional  interacLon  with  human  trainers

The  task:• run  24x7,  forever• each  day:

• extract  more  facts  from  the  web  

18

NELL:  Never  Ending  Language  LearnerInputs:•iniLal  ontology  •few  seed  examples  of  each  ontology  predicate•the  web•occasional  interacLon  with  human  trainers

The  task:• run  24x7,  forever• each  day:

• extract  more  facts  from  the  web  • learn  to  read  (perform  #1)  beIer  than  yesterday

18

NELL  Today

19

NELL  TodayRunning  24x7,  since  January,  12,  2010  

Result:    KB  with  >  70  million  candidate  beliefs,  growing  daily    learning  to  reason,  as  well  as  read    automaLcally  extending  its  ontology

19

NELL  TodayRunning  24x7,  since  January,  12,  2010  

Result:    KB  with  >  70  million  candidate  beliefs,  growing  daily    learning  to  reason,  as  well  as  read    automaLcally  extending  its  ontology

19

NELL  Knowledge  Fragment

20

Globe and Mail

Stanley Cup

hockey

NHL

Toronto

CFRB

HockeyTeam

playhasClass

wonToronto

Maple Leafs

home town

city paper league

Sundin

Milson

writer

radio

Air Canada Centre

team stadium

Canada

city stadium

politiciancountry

Miller

airport

member

Toskala

Pearson

Skydome

Connaught

Sunnybrook

hospital

city company

skates helmet

uses equipment

wonRed

Wings

Detroit

hometown

GM

city company

competes with

Toyota

plays in

league

Prius

Corrola

createdHino

acquired

automobile

economic sector

city stadium

climbing

football

uses equipment

NELL  Knowledge  Fragment

20

Globe and Mail

Stanley Cup

hockey

NHL

Toronto

CFRB

HockeyTeam

playhasClass

wonToronto

Maple Leafs

home town

city paper league

Sundin

Milson

writer

radio

Air Canada Centre

team stadium

Canada

city stadium

politiciancountry

Miller

airport

member

Toskala

Pearson

Skydome

Connaught

Sunnybrook

hospital

city company

skates helmet

uses equipment

wonRed

Wings

Detroit

hometown

GM

city company

competes with

Toyota

plays in

league

Prius

Corrola

createdHino

acquired

automobile

economic sector

city stadium

climbing

football

uses equipment

NELL  KB:  hIp://rtw.ml.cmu.edu  TwiIer:  @cmunell

NELL  Knowledge  Fragment

20

Globe and Mail

Stanley Cup

hockey

NHL

Toronto

CFRB

HockeyTeam

playhasClass

wonToronto

Maple Leafs

home town

city paper league

Sundin

Milson

writer

radio

Air Canada Centre

team stadium

Canada

city stadium

politiciancountry

Miller

airport

member

Toskala

Pearson

Skydome

Connaught

Sunnybrook

hospital

city company

skates helmet

uses equipment

wonRed

Wings

Detroit

hometown

GM

city company

competes with

Toyota

plays in

league

Prius

Corrola

createdHino

acquired

automobile

economic sector

city stadium

climbing

football

uses equipment

NELL  KB:  hIp://rtw.ml.cmu.edu  TwiIer:  @cmunell

Which relation?

NELL  Knowledge  Fragment

20

Globe and Mail

Stanley Cup

hockey

NHL

Toronto

CFRB

HockeyTeam

playhasClass

wonToronto

Maple Leafs

home town

city paper league

Sundin

Milson

writer

radio

Air Canada Centre

team stadium

Canada

city stadium

politiciancountry

Miller

airport

member

Toskala

Pearson

Skydome

Connaught

Sunnybrook

hospital

city company

skates helmet

uses equipment

wonRed

Wings

Detroit

hometown

GM

city company

competes with

Toyota

plays in

league

Prius

Corrola

createdHino

acquired

automobile

economic sector

city stadium

climbing

football

uses equipment

NELL  KB:  hIp://rtw.ml.cmu.edu  TwiIer:  @cmunell

When?: Temporal Scoping

Which relation?

Other Related Efforts

21

AAAI 2015

NELL’s Growth over Time

24

NELL’s Accuracy over Time

Need knowledge to be …

25

Need knowledge to be …

•Available or inferable

25

Need knowledge to be …

•Available or inferable

•Fresh (temporally scoped)

25

Need knowledge to be …

•Available or inferable

•Fresh (temporally scoped)

25

KB Inference

If: x1 competes with

(x1,x2)

x2 economic sector (x2,

x3)

x3

Then: economic sector (x1, x3)

PRA: Inference by KB Random Walks [Lao et al, EMNLP 2011]

KB:

Random walk path type:

logistic function for R(x,y) ith feature: probability of arriving at node y starting at node x, and taking a random walk along path type i

model Pr(R(x,y)):

x competes with ? economic

sector y

Feature = Typed Path CityInState, CityInstate-1, CityLocatedInCountry 0.8 0.32 AtLocation-1, AtLocation, CityLocatedInCountry 0.6 0.20 … … …

Pittsburgh

Pennsylvania

CityInS

tate

CityInState-1

CityInState -1

PhiladelphiaHarisburg

…(14)

U.S.

Feature Value

Logistic Regresssion

Weight

CityLocatedInCountry(Pittsburgh) = U.S. p=0.58

CityLocatedInCountry

DeltaPPG

AtLocation -1 AtLocationAtlanta

DallasTokyo

Japan

CityLocatedInCountry(Pittsburgh) = ?

City

Loca

tedI

nCou

ntry

[Lao et al, EMNLP 2011]

PRA: learned path types

CityLocatedInCountry(city, country):

8.04 cityliesonriver, cityliesonriver-1, citylocatedincountry

5.42 hasofficeincity-1, hasofficeincity, citylocatedincountry 4.98 cityalsoknownas, cityalsoknownas, citylocatedincountry 2.85 citycapitalofcountry,citylocatedincountry-1,citylocatedincountry

2.29 agentactsinlocation-1, agentactsinlocation, citylocatedincountry

1.22 statehascapital-1, statelocatedincountry 0.66 citycapitalofcountry . . . 7 of the 2985 learned paths for CityLocatedInCountry

PRA: Challenges

30

PRA: Challenges

• Works great when the KB graph is well connected

30

PRA: Challenges

• Works great when the KB graph is well connected

‣But, sparsity in the KB graph is the main challenge we wanted to solve!

30

Subject-Verb-Object (SVO) Data

Web

Former President Bill Clinton was born in Hope ...

President Obama was born in Honolulu, while ...

31

Subject-Verb-Object (SVO) Data

Web

Former President Bill Clinton was born in Hope ...

President Obama was born in Honolulu, while ...

31

Subject-Verb-Object (SVO) Data

Web

Former President Bill Clinton was born in Hope ...

President Obama was born in Honolulu, while ...

31

Subject-Verb-Object (SVO) Data

Web

Former President Bill Clinton was born in Hope ...

President Obama was born in Honolulu, while ...

SVO“Bill Clinton”, “was born in”, “Hope”“Obama”, “was born in” , “Honolulu”

Extract 600m Subject-Verb-Object (SVO) triples from a parsed web corpus of 230 billion tokens

31

Our Approach: PRA over KB + SVO Graph (Gardner et al., EMNLP 2013)

32

Our Approach: PRA over KB + SVO Graph (Gardner et al., EMNLP 2013)

32

AlexRodriguez(concept)

NY Yankees(concept)

WorldSeries

(concept)

teamPlaysIn

KB Relation Label

Our Approach: PRA over KB + SVO Graph (Gardner et al., EMNLP 2013)

32

AlexRodriguez(concept)

NY Yankees(concept)

WorldSeries

(concept)

teamPlaysIn

KB Relation Label

“plays for”

“bats for”

AlexRodriguez NY Yankees

mention mention

Our Approach: PRA over KB + SVO Graph (Gardner et al., EMNLP 2013)

32

AlexRodriguez(concept)

NY Yankees(concept)

WorldSeries

(concept)

teamPlaysIn

KB Relation Label

“plays for”

“bats for”

AlexRodriguez NY Yankees

mention mention

Lexicalized edges can explode number of paths, feature sparsity => Latent PRA

Latent PRA (Discretized)

33

Latent PRA (Discretized)

33

Step 1: Embed lexicalized edge labels

Latent PRA (Discretized)

33

Step 1: Embed lexicalized edge labels

“plays for”

(A R

od., N

Y Yan

kees

)

“bats for”

(B. Jo

nes,

NY

Mes

)

Latent PRA (Discretized)

33

Step 1: Embed lexicalized edge labels

DimensionalityReduction

“plays for”

(A R

od., N

Y Yan

kees

)

“bats for”

(B. Jo

nes,

NY

Mes

)

Latent PRA (Discretized)

33

Step 1: Embed lexicalized edge labels

DimensionalityReduction

“plays for”

(A R

od., N

Y Yan

kees

)

“bats for”

(B. Jo

nes,

NY

Mes

)

L1 L2 L3

“plays for”

“bats for”

0.9 0.01 -0.3

0.6 0.01 -0.4

LatentDimensions

Latent PRA (Discretized)

33

Step 1: Embed lexicalized edge labels

DimensionalityReduction

“plays for”

(A R

od., N

Y Yan

kees

)

“bats for”

(B. Jo

nes,

NY

Mes

)

L1 L2 L3

“plays for”

“bats for”

0.9 0.01 -0.3

0.6 0.01 -0.4

LatentDimensions

Discretize

Latent PRA (Discretized)

33

Step 1: Embed lexicalized edge labels

“plays for”

“bats for”

+L1 -L3

+L1 -L3

DimensionalityReduction

“plays for”

(A R

od., N

Y Yan

kees

)

“bats for”

(B. Jo

nes,

NY

Mes

)

L1 L2 L3

“plays for”

“bats for”

0.9 0.01 -0.3

0.6 0.01 -0.4

LatentDimensions

Discretize

Latent PRA (Discretized)

34

Latent PRA (Discretized)

34

Step 1I: Use discretized embeddings as edge label

Latent PRA (Discretized)

34

Step 1I: Use discretized embeddings as edge label

“+L1”Alex

Rodriguez NY Yankees

mention mention

“-L3”

Latent PRA (Discretized)

34

Step 1I: Use discretized embeddings as edge label

“+L1”Alex

Rodriguez NY Yankees

mention mention

“-L3”

Example:• “lies on”, “runs through”, “flows through” all get

mapped to same discretized latent dimensions (relevant for cityLiesOnRiver relation)

Latent PRA Experiments

35

Latent PRA Experiments

35

Latent PRA Experiments

35

NELL

MR

R

0

0.225

0.45

0.675

0.9

KB +SVO +Latent (Disc.)

0.90.76

0.64

Latent PRA Experiments

35

NELL

MR

R

0

0.225

0.45

0.675

0.9

KB +SVO +Latent (Disc.)

0.90.76

0.64

Freebase

MR

R

0.6

0.613

0.625

0.638

0.65

KB +SVO +Latent (Disc.)

0.650.64

0.61

Latent PRA Experiments

35

NELL

MR

R

0

0.225

0.45

0.675

0.9

KB +SVO +Latent (Disc.)

0.90.76

0.64

Freebase

MR

R

0.6

0.613

0.625

0.638

0.65

KB +SVO +Latent (Disc.)

0.650.64

0.61

• SVO data helps• Latent features help further

Latent PRA: Summary

36

Latent PRA: Summary

• Makes PRA robust to KB sparsity

36

Latent PRA: Summary

• Makes PRA robust to KB sparsity

• Increases KB coverage, makes lexicalized edge labels possible

36

Latent PRA: Summary

• Makes PRA robust to KB sparsity

• Increases KB coverage, makes lexicalized edge labels possible

• Combines global and local statistics

36

Latent PRA: Summary

• Makes PRA robust to KB sparsity

• Increases KB coverage, makes lexicalized edge labels possible

• Combines global and local statistics

• Brings Ontological and OpenIE together

36

Upcoming EMNLP 2015 papers to overcome sparsity in NELL

Need knowledge to be …

•Available or inferable

•Fresh (temporally scoped) (WSDM ’12, CIKM ‘12)

38

Need knowledge to be …

•Available or inferable

•Fresh (temporally scoped) (WSDM ’12, CIKM ‘12)

38

Source  of  Weak  Supervision: Doc  PublicaBon  Time  ~  Fact  Time

39

Source  of  Weak  Supervision: Doc  PublicaBon  Time  ~  Fact  Time

39

President Clinton

December 23, 1995

Source  of  Weak  Supervision: Doc  PublicaBon  Time  ~  Fact  Time

39

President Clinton

December 23, 1995

AssumpLon:  Fact  is  true  at  the  Lme  of  document  publicaLon

Temporal  Profile  of  Facts

40

Temporal  Profile  of  Facts

Key  Idea:  Temporally  scoping  mulLple  facts    jointly  can  reduce  uncertainty

40

Temporal  Constraint  Examples

41

Temporal  Constraint  Examples

Across  RelaBons

41

Is  CollecBve  Inference  EffecBve?

Is  CollecBve  Inference  EffecBve?

Is  CollecBve  Inference  EffecBve?

CollecBve  Temporal  Scoping

Independent  Temporal  Scoping

Is  CollecBve  Inference  EffecBve?

CollecBve  Temporal  Scoping

Independent  Temporal  Scoping

CollecLve  temporal  scoping  improves  performance  compared  to  temporally  scoping  each  fact  

separately

Learning  Temporal  Constraints [Talukdar,  Wijaya,  Mitchell,  CIKM  2012]

43

Learning  Temporal  Constraints [Talukdar,  Wijaya,  Mitchell,  CIKM  2012]

43

Learning  Temporal  Constraints [Talukdar,  Wijaya,  Mitchell,  CIKM  2012]

43

-­‐ Constraints  are  automaLcally  learned  by  GraphOrder,  proposed  graph-­‐based  SSL  algorithm  for  ordering

Learning  Temporal  Constraints [Talukdar,  Wijaya,  Mitchell,  CIKM  2012]

43

-­‐ Constraints  are  automaLcally  learned  by  GraphOrder,  proposed  graph-­‐based  SSL  algorithm  for  ordering

-­‐ Exploits  dependency  parsed  corpus  of  16  billion  tokens

Broader  Interest:  Latent  Conceptual  OrganizaBon  in  Brains  and  Text

44

Text  Data

Broader  Interest:  Latent  Conceptual  OrganizaBon  in  Brains  and  Text

44

Text  Data

Focus of Past Research

Broader  Interest:  Latent  Conceptual  OrganizaBon  in  Brains  and  Text

44

Text  Data

Focus of Past Research

fMRI  Brain  State

Broader  Interest:  Latent  Conceptual  OrganizaBon  in  Brains  and  Text

44

Text  Data

View  1View  2

Latent  Conceptual  OrganizaLon  in  Humans

Focus of Past Research

fMRI  Brain  State

Broader  Interest:  Latent  Conceptual  OrganizaBon  in  Brains  and  Text

44

Text  Data

View  1View  2

Latent  Conceptual  OrganizaLon  in  Humans

Focus of Past Research

fMRI  Brain  State

cat

StarSem  12,    COLING  12,  CoNLL  13,  KDD  14,  SDM  14,  ACL  14,  PLoS  ONE]

Current

cat

Broader  Interest:  Latent  Conceptual  OrganizaBon  in  Brains  and  Text

44

Text  Data

View  1View  2

Latent  Conceptual  OrganizaLon  in  Humans

fMRI  Brain  State

cat

StarSem  12,    COLING  12,  CoNLL  13,  KDD  14,  SDM  14,  ACL  14,  PLoS  ONE]

Current

cat

Future: Jointly model both Text and Brain Data

Results  Highlight

45

Results  Highlight

45

+

Results  Highlight

45

+ =

Leila&Wehbe&

[Fedorenko&et&al.&&2012]&

[Wehbe&et&al.,&2014]&

Author's personal copy

E. Fedorenko et al. / Neuropsychologia 50 (2012) 499– 513 505

Fig. 5. Top: A probabilistic overlap map showing in each voxel how many of the 25 individual subjects show a significant (at p < .05, FDR-corrected) effect for the Sen-tences > Nonwords contrast. Bottom: The main functional parcels derived from the probabilistic overlap map using an image parcellation (watershed) algorithm, as describedin more detail in Fedorenko et al. (2010).

nonword-list a memory probe was presented (a word in the sentences and word-listconditions, and a nonword in the jabberwocky and nonword-list conditions), andparticipants had to decide whether the probe was present in the preceding stimulus.As discussed in Fedorenko et al. (2010), the two versions of the task (passive readingvs. reading with a memory probe at the end) produced similar activation patterns;we therefore collapsed across the two subsets of the subjects in our analyses in thatpaper and we do the same here. Each participant completed between 6 and 8 runs(i.e., between 24 and 32 blocks per condition; see Fedorenko et al., 2010, for detailsof the timing).

In Section 3, we report the results of: (a) region-of-interest-based (ROI-based)MVPA analyses on a set of key language-sensitive regions and (b) whole-brainsearchlight-style analyses (Kriegeskorte et al., 2006).

2.1. ROI-based analyses

We chose to use as ROIs for our MVPA analyses the thirteen group-level func-tional parcels6 (Fig. 5, bottom) that were derived from the probabilistic overlapmap for the Sentences > Nonword-lists activations7 (Fig. 5, top), as described inFedorenko et al. (2010). These group-based ROIs represent the locations whereindividual activations tend to be found most consistently across subjects. So, forany given subject, a parcel will include some voxels that respond reliably morestrongly to Sentences than Nonwords, and some voxels that do not show this prop-erty. We chose to use these group-level parcels instead of subject-specific functionalROIs in these analyses for two reasons. First, it has been previously demonstrated

6 These parcels were created in order to systematize and automate the proce-dure for defining subject-specific functional ROIs (fROIs): in particular, for any givenregion, an individual subject’s fROI is defined by intersecting the relevant parcel withthe subject’s thresholded activation map. In other words, these functional parcelsserve as spatial constraints on the selection of subject-specific voxels, akin to usingborders of anatomical regions (see Julian, Fedorenko, & Kanwisher, submitted, foran extension of this method to ventral visual regions).

7 Although these group-level functional parcels were created from the 25 subjectswhose data we examine here, non-independence issues (Vul & Kanwisher, 2009) donot arise in examining the discriminability between word lists and jabberwockysentences because the data from those conditions were not used in creating theparcels. Some non-independence is present when we examine the discriminabilityamong all four conditions (Section 3.1). This non-independence should be taken intoconsideration when interpreting the results from the ROI-based analyses. However,the fact that the results of the whole-brain searchlight analyses, which do not suf-fer from such non-independence problems, look similar to those of the ROI-basedanalyses largely alleviates the concerns.

(Haxby et al., 2001; Kriegeskorte et al., 2006) that even voxels that do not show aparticular functional signature relevant to the to-be-discriminated conditions cancontribute to classification accuracy. For example, Haxby et al. (2001) showed thatremoving voxels from the ventral visual regions that respond most strongly to somevisual category does not strongly affect the ability to discriminate that categoryfrom other categories. Consequently, voxels in the vicinity of language-sensitiveregions in each individual subject may contain information about various aspectsof linguistic knowledge even though they do not show the functional signature oflanguage-sensitive voxels. And second, because we wanted to examine neural activ-ity patterns across all four conditions, we could not use any of the conditions fordefining subject-specific fROIs. (However, in addition to these whole-parcel-basedanalyses, we did conduct one analysis where we looked at the ability of subject-specific functional ROIs (fROIs), defined by the Sentences > Nonword-lists contrast,to discriminate between word lists and jabberwocky sentences. The results of thisanalysis are reported in Appendix A.)

For each condition we divided the data into odd-numbered and even-numberedruns (each subject performed between 6 and 8 runs total). Then, for each subjectand for each ROI, and across the two independent halves of the data, we computedthe within- vs. between-condition spatial correlations for each pair of conditions (asschematically shown in Fig. 4 above), considering all the voxels within the parcel.For example, to see how well the pattern of activity for the Sentences condition isdiscriminated from the pattern of activity for the Word-lists condition, we computed(i) a within-condition correlation value for the Sentences condition by comparing thepattern of activity for the Sentences condition in the odd vs. even runs (all the r valuesare Fisher-transformed); (ii) a within-condition correlation value for the Word-listscondition by comparing the pattern of activity for the Word-lists condition in theodd vs. even runs; and (iii) a between-condition correlation value by comparing thepattern of activation for the Sentences condition in the odd/even runs and for theWord-lists condition in the even/odd runs (these two values are averaged to createone between-condition value). Finally, for each ROI we performed an F-test on thewithin vs. between-condition correlation values across subjects to see whether thewithin-condition values are reliably higher than the between-condition values. Ifso, this would suggest that the distinction between the two conditions in questionis represented in the relevant ROI.

We deviated from Haxby’s analysis strategies in one way. In particular, Haxbyapplied centering to his data by subtracting the mean level of activation of a voxelfrom the activation level for each of the conditions. This is equivalent to consideringthe activation from each condition with respect to a baseline activation level com-puted as the average activation across all conditions, instead of using an independentfixation baseline as we used in our analyses. The centering procedure potentiallyincreases sensitivity of the MVPAs by removing one source of variance from acrossthe voxels and leaving only between-condition differences in play. However, cen-tering also introduces between-condition dependencies in the estimation of thewithin-condition similarity measures, which complicates their interpretation.

a"

b"

Seman(cs"Characters" Syntax"

Dialog" Mo(on"Visual"

[Wehbe et al., PLOS ONE 2014]

Leila&Wehbe&

[Fedorenko&et&al.&&2012]&

[Wehbe&et&al.,&2014]&

Author's personal copy

E. Fedorenko et al. / Neuropsychologia 50 (2012) 499– 513 505

Fig. 5. Top: A probabilistic overlap map showing in each voxel how many of the 25 individual subjects show a significant (at p < .05, FDR-corrected) effect for the Sen-tences > Nonwords contrast. Bottom: The main functional parcels derived from the probabilistic overlap map using an image parcellation (watershed) algorithm, as describedin more detail in Fedorenko et al. (2010).

nonword-list a memory probe was presented (a word in the sentences and word-listconditions, and a nonword in the jabberwocky and nonword-list conditions), andparticipants had to decide whether the probe was present in the preceding stimulus.As discussed in Fedorenko et al. (2010), the two versions of the task (passive readingvs. reading with a memory probe at the end) produced similar activation patterns;we therefore collapsed across the two subsets of the subjects in our analyses in thatpaper and we do the same here. Each participant completed between 6 and 8 runs(i.e., between 24 and 32 blocks per condition; see Fedorenko et al., 2010, for detailsof the timing).

In Section 3, we report the results of: (a) region-of-interest-based (ROI-based)MVPA analyses on a set of key language-sensitive regions and (b) whole-brainsearchlight-style analyses (Kriegeskorte et al., 2006).

2.1. ROI-based analyses

We chose to use as ROIs for our MVPA analyses the thirteen group-level func-tional parcels6 (Fig. 5, bottom) that were derived from the probabilistic overlapmap for the Sentences > Nonword-lists activations7 (Fig. 5, top), as described inFedorenko et al. (2010). These group-based ROIs represent the locations whereindividual activations tend to be found most consistently across subjects. So, forany given subject, a parcel will include some voxels that respond reliably morestrongly to Sentences than Nonwords, and some voxels that do not show this prop-erty. We chose to use these group-level parcels instead of subject-specific functionalROIs in these analyses for two reasons. First, it has been previously demonstrated

6 These parcels were created in order to systematize and automate the proce-dure for defining subject-specific functional ROIs (fROIs): in particular, for any givenregion, an individual subject’s fROI is defined by intersecting the relevant parcel withthe subject’s thresholded activation map. In other words, these functional parcelsserve as spatial constraints on the selection of subject-specific voxels, akin to usingborders of anatomical regions (see Julian, Fedorenko, & Kanwisher, submitted, foran extension of this method to ventral visual regions).

7 Although these group-level functional parcels were created from the 25 subjectswhose data we examine here, non-independence issues (Vul & Kanwisher, 2009) donot arise in examining the discriminability between word lists and jabberwockysentences because the data from those conditions were not used in creating theparcels. Some non-independence is present when we examine the discriminabilityamong all four conditions (Section 3.1). This non-independence should be taken intoconsideration when interpreting the results from the ROI-based analyses. However,the fact that the results of the whole-brain searchlight analyses, which do not suf-fer from such non-independence problems, look similar to those of the ROI-basedanalyses largely alleviates the concerns.

(Haxby et al., 2001; Kriegeskorte et al., 2006) that even voxels that do not show aparticular functional signature relevant to the to-be-discriminated conditions cancontribute to classification accuracy. For example, Haxby et al. (2001) showed thatremoving voxels from the ventral visual regions that respond most strongly to somevisual category does not strongly affect the ability to discriminate that categoryfrom other categories. Consequently, voxels in the vicinity of language-sensitiveregions in each individual subject may contain information about various aspectsof linguistic knowledge even though they do not show the functional signature oflanguage-sensitive voxels. And second, because we wanted to examine neural activ-ity patterns across all four conditions, we could not use any of the conditions fordefining subject-specific fROIs. (However, in addition to these whole-parcel-basedanalyses, we did conduct one analysis where we looked at the ability of subject-specific functional ROIs (fROIs), defined by the Sentences > Nonword-lists contrast,to discriminate between word lists and jabberwocky sentences. The results of thisanalysis are reported in Appendix A.)

For each condition we divided the data into odd-numbered and even-numberedruns (each subject performed between 6 and 8 runs total). Then, for each subjectand for each ROI, and across the two independent halves of the data, we computedthe within- vs. between-condition spatial correlations for each pair of conditions (asschematically shown in Fig. 4 above), considering all the voxels within the parcel.For example, to see how well the pattern of activity for the Sentences condition isdiscriminated from the pattern of activity for the Word-lists condition, we computed(i) a within-condition correlation value for the Sentences condition by comparing thepattern of activity for the Sentences condition in the odd vs. even runs (all the r valuesare Fisher-transformed); (ii) a within-condition correlation value for the Word-listscondition by comparing the pattern of activity for the Word-lists condition in theodd vs. even runs; and (iii) a between-condition correlation value by comparing thepattern of activation for the Sentences condition in the odd/even runs and for theWord-lists condition in the even/odd runs (these two values are averaged to createone between-condition value). Finally, for each ROI we performed an F-test on thewithin vs. between-condition correlation values across subjects to see whether thewithin-condition values are reliably higher than the between-condition values. Ifso, this would suggest that the distinction between the two conditions in questionis represented in the relevant ROI.

We deviated from Haxby’s analysis strategies in one way. In particular, Haxbyapplied centering to his data by subtracting the mean level of activation of a voxelfrom the activation level for each of the conditions. This is equivalent to consideringthe activation from each condition with respect to a baseline activation level com-puted as the average activation across all conditions, instead of using an independentfixation baseline as we used in our analyses. The centering procedure potentiallyincreases sensitivity of the MVPAs by removing one source of variance from acrossthe voxels and leaving only between-condition differences in play. However, cen-tering also introduces between-condition dependencies in the estimation of thewithin-condition similarity measures, which complicates their interpretation.

a"

b"

Seman(cs"Characters" Syntax"

Dialog" Mo(on"Visual"

[Wehbe et al., PLOS ONE 2014]

From  Strings  to  Things  and  Beyond

From  Strings  to  Things  and  Beyond

Construct

From  Strings  to  Things  and  Beyond

Construct

New Data

Maintain

From  Strings  to  Things  and  Beyond

Construct

New Data

Maintain Apply

From  Strings  to  Things  and  Beyond

Construct

New Data

Maintain Apply

Ongoing  Research  at  MALL  Lab• Continuous KB evaluation

• Temporal Micro Reading

• Representation Learning

• Large-scale Learning

• Goal-directed KB expansion

48

Prakhar Pjha (IISc)

Arabinda Moni (IISc)

Yogesh D. (BTech, IIT BHU)

Chandrahas (IISc)

Uday Saini (BTech, IIT Ropar)

Madhav N. (IISc)

3 PhD, 3 Masters, 4 Project Assistants, 1 Intern

External  CollaboraBon  &  Support

49

Final  Thoughts

50

Final  Thoughts

50

Final  Thoughts

50

Final  Thoughts

50

Unprecedented  opportunity  to  bring  world  knowledge  into  AI  systems  -­‐-­‐  focus  of  my  research

Big Text Big Knowledge

Thank  You! [email protected] www.talukdar.net

Machine    Learning

Big  Data  Processing

Natural  Language  Processing

Decisions