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
From Big Text to Big Knowledge Partha Talukdar Machine And Language - - PowerPoint PPT Presentation
From Big Text to Big Knowledge Partha Talukdar Machine And Language Learning (MALL) Lab SERC & CSA, Indian Institute of Science Matt Gardner Bryan Kisiel Tom Mitchell Derry Wijaya Carnegie Mellon University IISc Overview Indian
Derry Wijaya Tom Mitchell Partha Talukdar Machine And Language Learning (MALL) Lab SERC & CSA, Indian Institute of Science Matt Gardner Bryan Kisiel
Carnegie Mellon University
Indian Institute of Science (IISc), Bangalore
Integrated PhD, MTech
6
CSA : RESEARCH AREAS
MACHINE LEARNING, AI, PATTERN RECOGNITION, DATA MINING, ANALYTICS, NLP
Shirish Shevade, Shalabh Bhatnagar, Susheela Devi, Shivani Agarwal, Ambedkar, Partha Talukdar
GAME THEORY AND MECHANISM DESIGN
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,
CODING, ALGORITHMIC ALGEBRA
PVK, D. Patil, Bhavana
AUTOMATA THEORY, FORMAL METHODS, LOGICS
Deepak D’Souza, Aditya Kanade, K.V. Raghavan,
COMPILERS, SOFTWARE ENGINEERING
Aditya Kanade, Murali Krishna, Uday Kumar, D. D’Souza,
ARCHITECTURE, OS, STORAGE, NETWORKS, DISTRIBUTED COMPUTING
Matthew Jacob, R. Govindarajan,
Uday Kumar, Murali Krishna, Arpita, Bhavana
DATABASE SYSTEMS
Jayant Haritsa, R.C. Hansdah, Partha Talukdar
CRYPTOLOGY, SECURITY
Sanjit Chatterjee, Arpita, Bhavana,
R.C. Hansdah
VISUALIZATION, GRAPHICS,
Vijay Natarajan Satish Govindarajan
6
CSA : RESEARCH AREAS
MACHINE LEARNING, AI, PATTERN RECOGNITION, DATA MINING, ANALYTICS, NLP
Shirish Shevade, Shalabh Bhatnagar, Susheela Devi, Shivani Agarwal, Ambedkar, Partha Talukdar
GAME THEORY AND MECHANISM DESIGN
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,
CODING, ALGORITHMIC ALGEBRA
PVK, D. Patil, Bhavana
AUTOMATA THEORY, FORMAL METHODS, LOGICS
Deepak D’Souza, Aditya Kanade, K.V. Raghavan,
COMPILERS, SOFTWARE ENGINEERING
Aditya Kanade, Murali Krishna, Uday Kumar, D. D’Souza,
ARCHITECTURE, OS, STORAGE, NETWORKS, DISTRIBUTED COMPUTING
Matthew Jacob, R. Govindarajan,
Uday Kumar, Murali Krishna, Arpita, Bhavana
DATABASE SYSTEMS
Jayant Haritsa, R.C. Hansdah, Partha Talukdar
CRYPTOLOGY, SECURITY
Sanjit Chatterjee, Arpita, Bhavana,
R.C. Hansdah
THEORY
VISUALIZATION, GRAPHICS,
Vijay Natarajan Satish Govindarajan
6
CSA : RESEARCH AREAS
MACHINE LEARNING, AI, PATTERN RECOGNITION, DATA MINING, ANALYTICS, NLP
Shirish Shevade, Shalabh Bhatnagar, Susheela Devi, Shivani Agarwal, Ambedkar, Partha Talukdar
GAME THEORY AND MECHANISM DESIGN
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,
CODING, ALGORITHMIC ALGEBRA
PVK, D. Patil, Bhavana
AUTOMATA THEORY, FORMAL METHODS, LOGICS
Deepak D’Souza, Aditya Kanade, K.V. Raghavan,
COMPILERS, SOFTWARE ENGINEERING
Aditya Kanade, Murali Krishna, Uday Kumar, D. D’Souza,
ARCHITECTURE, OS, STORAGE, NETWORKS, DISTRIBUTED COMPUTING
Matthew Jacob, R. Govindarajan,
Uday Kumar, Murali Krishna, Arpita, Bhavana
DATABASE SYSTEMS
Jayant Haritsa, R.C. Hansdah, Partha Talukdar
CRYPTOLOGY, SECURITY
Sanjit Chatterjee, Arpita, Bhavana,
R.C. Hansdah
THEORY COMPUTER SYSTEMS
VISUALIZATION, GRAPHICS,
Vijay Natarajan Satish Govindarajan
6
CSA : RESEARCH AREAS
MACHINE LEARNING, AI, PATTERN RECOGNITION, DATA MINING, ANALYTICS, NLP
Shirish Shevade, Shalabh Bhatnagar, Susheela Devi, Shivani Agarwal, Ambedkar, Partha Talukdar
GAME THEORY AND MECHANISM DESIGN
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,
CODING, ALGORITHMIC ALGEBRA
PVK, D. Patil, Bhavana
AUTOMATA THEORY, FORMAL METHODS, LOGICS
Deepak D’Souza, Aditya Kanade, K.V. Raghavan,
COMPILERS, SOFTWARE ENGINEERING
Aditya Kanade, Murali Krishna, Uday Kumar, D. D’Souza,
ARCHITECTURE, OS, STORAGE, NETWORKS, DISTRIBUTED COMPUTING
Matthew Jacob, R. Govindarajan,
Uday Kumar, Murali Krishna, Arpita, Bhavana
DATABASE SYSTEMS
Jayant Haritsa, R.C. Hansdah, Partha Talukdar
CRYPTOLOGY, SECURITY
Sanjit Chatterjee, Arpita, Bhavana,
R.C. Hansdah
THEORY COMPUTER SYSTEMS INTELLIGENT SYSTEMS
VISUALIZATION, GRAPHICS,
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)
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
ECE, EE)
presence
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
13
Background knowledge is key to Intelligent Decision Making
13
Background knowledge is key to Intelligent Decision Making
13
Background knowledge is key to Intelligent Decision Making
?
13
Background knowledge is key to Intelligent Decision Making
?
13
Background knowledge is key to Intelligent Decision Making
inventedCharacter
14
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
alone ¡(a ¡117% ¡growth) ¡ ¡
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
alone ¡(a ¡117% ¡growth) ¡ ¡
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
alone ¡(a ¡117% ¡growth) ¡ ¡
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
alone ¡(a ¡117% ¡growth) ¡ ¡
Need ¡to ¡harvest ¡knowledge ¡from ¡ unstructured ¡text ¡data
15
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
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
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
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
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
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
16
16 Improved Web Search Experience, facilitated by Harvested Knowledge
16 Improved Web Search Experience, facilitated by Harvested Knowledge No Structured Information
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.” ¡
New ¡paradigm ¡for ¡Machine ¡Learning:
17
New ¡paradigm ¡for ¡Machine ¡Learning:
Persistent ¡soSware ¡individual
17
New ¡paradigm ¡for ¡Machine ¡Learning:
Persistent ¡soSware ¡individual Learns ¡many ¡funcLons ¡/ ¡knowledge ¡types
17
New ¡paradigm ¡for ¡Machine ¡Learning:
Persistent ¡soSware ¡individual Learns ¡many ¡funcLons ¡/ ¡knowledge ¡types Learns ¡easier ¡things ¡first, ¡then ¡more ¡difficult
17
New ¡paradigm ¡for ¡Machine ¡Learning:
Persistent ¡soSware ¡individual Learns ¡many ¡funcLons ¡/ ¡knowledge ¡types Learns ¡easier ¡things ¡first, ¡then ¡more ¡difficult The ¡more ¡it ¡learns, ¡the ¡more ¡it ¡can ¡learn ¡next
17
New ¡paradigm ¡for ¡Machine ¡Learning:
Persistent ¡soSware ¡individual Learns ¡many ¡funcLons ¡/ ¡knowledge ¡types Learns ¡easier ¡things ¡first, ¡then ¡more ¡difficult The ¡more ¡it ¡learns, ¡the ¡more ¡it ¡can ¡learn ¡next Learns ¡from ¡experience, ¡and ¡from ¡advice
17
18
Inputs:
18
Inputs:
18
Inputs:
18
Inputs:
18
Inputs:
18
Inputs:
18
Inputs:
The ¡task:
18
Inputs:
The ¡task:
18
Inputs:
The ¡task:
18
Inputs:
The ¡task:
18
Inputs:
The ¡task:
18
19
Running ¡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
Running ¡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
20
Globe and Mail Stanley Cup hockey NHL Toronto CFRB Hockey Team play hasClass won Toronto Maple Leafs home town city paper league Sundin Milson writer radio Air Canada Centre team stadium Canada city stadium politician country Miller airport member Toskala Pearson Skydome Connaught Sunnybrook hospital city company skates helmet uses equipment won Red Wings Detroit hometown GM city company competes with Toyota plays in league Prius Corrola created Hino acquired automobile economic sector city stadium climbing football uses equipment
20
Globe and Mail Stanley Cup hockey NHL Toronto CFRB Hockey Team play hasClass won Toronto Maple Leafs home town city paper league Sundin Milson writer radio Air Canada Centre team stadium Canada city stadium politician country Miller airport member Toskala Pearson Skydome Connaught Sunnybrook hospital city company skates helmet uses equipment won Red Wings Detroit hometown GM city company competes with Toyota plays in league Prius Corrola created Hino acquired automobile economic sector city stadium climbing football uses equipment
NELL ¡KB: ¡hIp://rtw.ml.cmu.edu ¡ TwiIer: ¡@cmunell
20
Globe and Mail Stanley Cup hockey NHL Toronto CFRB Hockey Team play hasClass won Toronto Maple Leafs home town city paper league Sundin Milson writer radio Air Canada Centre team stadium Canada city stadium politician country Miller airport member Toskala Pearson Skydome Connaught Sunnybrook hospital city company skates helmet uses equipment won Red Wings Detroit hometown GM city company competes with Toyota plays in league Prius Corrola created Hino acquired automobile economic sector city stadium climbing football uses equipment
NELL ¡KB: ¡hIp://rtw.ml.cmu.edu ¡ TwiIer: ¡@cmunell
Which relation?
20
Globe and Mail Stanley Cup hockey NHL Toronto CFRB Hockey Team play hasClass won Toronto Maple Leafs home town city paper league Sundin Milson writer radio Air Canada Centre team stadium Canada city stadium politician country Miller airport member Toskala Pearson Skydome Connaught Sunnybrook hospital city company skates helmet uses equipment won Red Wings Detroit hometown GM city company competes with Toyota plays in league Prius Corrola created Hino acquired automobile economic sector city stadium climbing football uses equipment
NELL ¡KB: ¡hIp://rtw.ml.cmu.edu ¡ TwiIer: ¡@cmunell
When?: Temporal Scoping Which relation?
21
AAAI 2015
24
25
25
25
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
CityInState CityInState-1 C i t y I n S t a t e
Philadelphia Harisburg
…(14)
U.S. Feature Value Logistic Regresssion Weight CityLocatedInCountry(Pittsburgh) = U.S. p=0.58
CityLocatedInCountry
Delta PPG AtLocation-1
AtLocation
Atlanta Dallas Tokyo Japan CityLocatedInCountry(Pittsburgh) = ?
C i t y L
a t e d I n C
n t r y
[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
30
well connected
30
well connected
main challenge we wanted to solve!
30
Web
Former President Bill Clinton was born in Hope ... President Obama was born in Honolulu, while ...
31
Web
Former President Bill Clinton was born in Hope ... President Obama was born in Honolulu, while ...
31
Web
Former President Bill Clinton was born in Hope ... President Obama was born in Honolulu, while ...
31
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
32
32
Alex Rodriguez (concept) NY Yankees (concept) World Series (concept) teamPlaysIn
KB Relation Label
32
Alex Rodriguez (concept) NY Yankees (concept) World Series (concept) teamPlaysIn
KB Relation Label
“plays for” “bats for” Alex Rodriguez NY Yankees mention mention
32
Alex Rodriguez (concept) NY Yankees (concept) World Series (concept) teamPlaysIn
KB Relation Label
“plays for” “bats for” Alex Rodriguez NY Yankees mention mention
Lexicalized edges can explode number of paths, feature sparsity => Latent PRA
33
33
Step 1: Embed lexicalized edge labels
33
Step 1: Embed lexicalized edge labels
“plays for”
( A R
. , N Y Y a n k e e s )
“bats for”
( B . J
e s , N Y M e s )
33
Step 1: Embed lexicalized edge labels
Dimensionality Reduction “plays for”
( A R
. , N Y Y a n k e e s )
“bats for”
( B . J
e s , N Y M e s )
33
Step 1: Embed lexicalized edge labels
Dimensionality Reduction “plays for”
( A R
. , N Y Y a n k e e s )
“bats for”
( B . J
e s , N Y M e s )
L1 L2 L3
“plays for” “bats for”
0.9 0.01 -0.3 0.6 0.01 -0.4
Latent Dimensions
33
Step 1: Embed lexicalized edge labels
Dimensionality Reduction “plays for”
( A R
. , N Y Y a n k e e s )
“bats for”
( B . J
e s , N Y M e s )
L1 L2 L3
“plays for” “bats for”
0.9 0.01 -0.3 0.6 0.01 -0.4
Latent Dimensions Discretize
33
Step 1: Embed lexicalized edge labels
“plays for” “bats for”
+L1 -L3 +L1 -L3
Dimensionality Reduction “plays for”
( A R
. , N Y Y a n k e e s )
“bats for”
( B . J
e s , N Y M e s )
L1 L2 L3
“plays for” “bats for”
0.9 0.01 -0.3 0.6 0.01 -0.4
Latent Dimensions Discretize
34
34
Step 1I: Use discretized embeddings as edge label
34
Step 1I: Use discretized embeddings as edge label
“+L1” Alex Rodriguez NY Yankees mention mention “-L3”
34
Step 1I: Use discretized embeddings as edge label
“+L1” Alex Rodriguez NY Yankees mention mention “-L3”
Example:
mapped to same discretized latent dimensions (relevant for cityLiesOnRiver relation)
35
35
35
NELL
MRR 0.225 0.45 0.675 0.9 KB +SVO +Latent (Disc.)
0.9 0.76 0.64
35
NELL
MRR 0.225 0.45 0.675 0.9 KB +SVO +Latent (Disc.)
0.9 0.76 0.64 Freebase
MRR 0.6 0.613 0.625 0.638 0.65 KB +SVO +Latent (Disc.)
0.65 0.64 0.61
35
NELL
MRR 0.225 0.45 0.675 0.9 KB +SVO +Latent (Disc.)
0.9 0.76 0.64 Freebase
MRR 0.6 0.613 0.625 0.638 0.65 KB +SVO +Latent (Disc.)
0.65 0.64 0.61
36
36
lexicalized edge labels possible
36
lexicalized edge labels possible
36
lexicalized edge labels possible
together
36
Upcoming EMNLP 2015 papers to overcome sparsity in NELL
38
38
39
39
President Clinton
December 23, 1995
39
President Clinton
December 23, 1995
AssumpLon: ¡Fact ¡is ¡true ¡at ¡the ¡Lme ¡
40
Key ¡Idea: ¡Temporally ¡scoping ¡mulLple ¡facts ¡ ¡ jointly ¡can ¡reduce ¡uncertainty
40
41
Across ¡RelaBons
41
CollecBve ¡Temporal ¡ Scoping Independent ¡Temporal ¡ Scoping
CollecBve ¡Temporal ¡ Scoping Independent ¡Temporal ¡ Scoping
CollecLve ¡temporal ¡scoping ¡improves ¡performance ¡ compared ¡to ¡temporally ¡scoping ¡each ¡fact ¡ separately
[Talukdar, ¡Wijaya, ¡Mitchell, ¡CIKM ¡2012]
43
[Talukdar, ¡Wijaya, ¡Mitchell, ¡CIKM ¡2012]
43
[Talukdar, ¡Wijaya, ¡Mitchell, ¡CIKM ¡2012]
43
automaLcally ¡learned ¡ by ¡GraphOrder, ¡ proposed ¡graph-‑based ¡ SSL ¡algorithm ¡for ¡
[Talukdar, ¡Wijaya, ¡Mitchell, ¡CIKM ¡2012]
43
automaLcally ¡learned ¡ by ¡GraphOrder, ¡ proposed ¡graph-‑based ¡ SSL ¡algorithm ¡for ¡
parsed ¡corpus ¡of ¡16 ¡ billion ¡tokens
44
Text ¡ Data
44
Text ¡ Data
Focus of Past Research
44
Text ¡ Data
Focus of Past Research
fMRI ¡ Brain ¡ State
44
Text ¡ Data
View ¡1 View ¡2 Latent ¡Conceptual ¡ OrganizaLon ¡in ¡Humans
Focus of Past Research
fMRI ¡ Brain ¡ State
44
Text ¡ Data
View ¡1 View ¡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
44
Text ¡ Data
View ¡1 View ¡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
45
45
45
Leila&Wehbe&
[Fedorenko&et&al.& &2012]& [Wehbe&et&al.,&2014]&
Althoughb"
Seman(cs" Characters" Syntax" Dialog" Mo(on" Visual"
[Wehbe et al., PLOS ONE 2014]
Leila&Wehbe&
[Fedorenko&et&al.& &2012]& [Wehbe&et&al.,&2014]&
Althoughb"
Seman(cs" Characters" Syntax" Dialog" Mo(on" Visual"
[Wehbe et al., PLOS ONE 2014]
Construct
Construct
New Data
Maintain
Construct
New Data
Maintain Apply
Construct
New Data
Maintain Apply
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
49
50
50
50
50
Unprecedented ¡opportunity ¡to ¡bring ¡world ¡ knowledge ¡into ¡AI ¡systems ¡-‑-‑ ¡focus ¡of ¡my ¡research
ppt@serc.iisc.in www.talukdar.net
Machine ¡ ¡ Learning Big ¡Data ¡ Processing Natural ¡ Language ¡ Processing Decisions