SlideShare ist ein Scribd-Unternehmen logo
1 von 44
A Hybrid Approach to
Mining Conditions
Fernando O. Gallego,
and Rafael Corchuelo
Opinion mining
Attribute Polarity
“lens” Positive
2
Attribute Polarity
“resolution” Neutral
“Flash” Negative
I think that the lens is beyond
excellent for amateurs.
The resolution of this camera is
13Mp. Flash is tacky when
using outdoors.
But wait!
3
The opinion is only
true in a certain
situation
Opinion mining (with conditions)
Attribute Polarity
“lens” Positive (for
amateurs)
4
Attribute Polarity
“resolution” Neutral
“Flash” Negative
(when using
outdoors)
I think that the lens is beyond
excellent for amateurs.
The resolution of this camera is
13Mp. Flash is tacky when
using outdoors.
Roadmap
Introduction
Our proposal
Experimental results
Conclusions
Roadmap
Introduction
Our proposal
Experimental results
Conclusions
Condition mining
7
I think that the lens is beyond
excellent for amateurs.
The resolution of this camera is
13Mp. Flash is tacky when
using outdoors.
for amateurs
when using
outdoors
Current approaches
Machine-learningHandcrafted patterns
Handcrafted patterns
• Mausam et al. (2012)
– OpenIE extraction
– Dependency tree
– Adverbial clauses
• Chikersal et al. (2015)
– Opinion mining
– Basic connectives
– “then”/comma
9
And the problem is…
10
Variability of conditions
11
0/1st/2nd/3rd
conditionals
If you do sth
Even if sby fell down
If sth had passed
Should you help me
When sth happens
May it be accepted
For sby
To sby
During my event
While doing sth After/before sth
If it occurs
Machine learning
• Nakayama et al (2015):
– SVM/CRF Model
– 3k Japanese sentences
– Several lexicons used
12
And the problem is…
13
Roadmap
Introduction
Our proposal
Experimental results
Conclusions
Our solution
Computational linguistics
+
Deep learning
Inputs
Sentence Conditions
I think that the lens is beyond excellent for
amateurs.
[“for amateurs”]
The resolution of this camera is 13Mp. []
Flash is tacky when using outdoors. [“when using outdoors”]
… …
16
Main methods
17
Main methods
18
Train (1/4)
• Create a subset of
training examples for
each sentence
19
S1
S1
S1
S1
ts
ts
ts
ts
Train (2/4)
• Generate condition
candidates for a given
sentence
20
outdoors
tacky
Flash is
usingcop
advcl
nsubj
advmod
when
c1:
c2:
advmod
Flash is tacky when using outdoors
when using outdoors
Train (3/4)
• Score each candidate
21
c1:
c2:
Flash is tacky when using outdoors
when using outdoors
0.8560
1.0000
Train (4/4)
• Train a deep regressor
from training set
22
Regressor’s alternatives
23
MLP
CNN-BiGRUBiGRU
GRU
CNN
Main methods
24
Apply (1/5)
• Generate condition
candidates
25
outdoors
tacky
Flash is
usingcop
advcl
nsubj
advmod
when
c1:
c2:
advmod
Flash is tacky when using outdoors
when using outdoors
Apply (2/5)
• For each condition
candidate it checks
whether it must be
considered or not
26
Apply (3/5)
• The regressor scores
the candidate
27
c1:
c2:
Flash is tacky when using outdoors
when using outdoors
0.8560
1.0000
Apply (4/5)
• If score is equal to or
greater than a given
threshold, it is
considered
28
Apply (5/5)
• It keeps the best non-
overlapped candidates
29
Roadmap
Introduction
Our proposal
Experimental results
Conclusions
Hardware & software configuration
• Intel Xeon E5-2690
• 4 threads at 2.60 Ghz
• 2 GiB of RAM
• Nvidia Tesla K10 GPU
• CentOS Linux 7.3
• Snowball 1.2.1
• Stanford Core NLP 3.8.0
• Python 3.5.4
• Gensim 2.3.0
• Keras 2.0.8 & Theano 1.0
31
Dataset
https://www.kaggle.com/fogallego/reviews-with-conditions
Baselines
Machine-learningHandcrafted patterns
Results
34
Roadmap
Introduction
Our proposal
Experimental results
Conclusions
Well done!
• It overcomes the
problems found in the
literature
• Comprehensive
experimental analysis
• It achieves good results
36
Thanks
Fernando O. Gallego
fogallego@us.es
Condition mining’s main applications
38
Inf. Extraction Opinion mining Recommenders
Detailed example (1/3)
39
who cake
if you be lik- ’s
try
nsubj dobj
someone then john
advmod
xcompadvcl
mark acl:relcl
copnsubj
case
If you are someone who likes cakes then try John’s
Detailed example (2/3)
40
’s
case
john
xcomp
try
-
then
advmod
cake
dobj
lik-
acl:relcl
who
nsubj
someone
advcl
be
cop
you
nsubj
if
mark
c1 :
c2:
c3:
c4:
cake
dobj
lik-
acl:relcl
who
nsubj
someone
advcl
be
cop
you
nsubj
if
mark
cake
dobj
lik-
acl:relcl
who
nsubj
’s
case
john
xcomp
who cake
if you be lik- ’s
try
nsubj dobj
someone then john
advmod
xcompadvcl
mark acl:relcl
copnsubj
case
Detailed example (3/3)
41
Our Neural Networks
CNN:
Convolution
Input ld
Output .9l1.2d
Activation relu
Kernel 3
Drop-out 0.2000
Convolution
Input .9l1.2d
Output .6l.3d
Activation relu
Kernel 17
Drop-out 0.2000
Pooling
Input .6l.3d
Output .6l1
Functor max
Pool global
Dense
Input .6l1
Output .3l1
Activation linear
Drop-out 0.2000
Dense
Input .3l1
Output 11
Activation tanh
Drop-out 0.0000
MLP: GRU:
Dense
Input ld
Output l.5d
Activation tanh
Drop-out 0.2000
Dense
Input l.5d
Output 11
Activation linear
Drop-out 0.0000
GRU
Input ld
Output l1
Activation tanh
Drop-out 0.1500
Dense
Input l1
Output .3l1
Activation linear
Drop-out 0.2000
Dense
Input .3l1
Output 11
Activation tanh
Drop-out 0.0000
BiGRU:
BiGRU
Input ld
Output 2l1
Activation tanh
Drop-out 0.1500
Dense
Input 2l1
Output .3l1
Activation linear
Drop-out 0.2000
CNN-BiGRU:
Convolution
Input ld
Output .9l.3d
Activation relu
Kernel 3
Drop-out 0.0000
Pooling
Input .9l.3d
Output .9l.3d
Functor max
Pool 2
BiGRU
Input .9l.3d
Output 4l1
Activation tanh
Drop-out 0.1500
Dense
Input .4l1
Output .3l1
Activation linear
Drop-out 0.2000
Dense
Input 3l1
Output 11
Activation tanh
Drop-out 0.0000
Dense
Input .3l1
Output 11
Activation tanh
Drop-out 0.0000
Detailed results
Lang Proposal
q = 0.2500 q = 0.5000 q = 0.7500
P R F1 P R F1 P R F1
en
MB 0.6270 0.6144 0.6206 0.6270 0.6144 0.6206 0.6270 0.6144 0.6206
CB 0.7979 0.4642 0.5870 0.7979 0.4642 0.5870 0.7979 0.4642 0.5870
Averages 0.7125 0.5393 0.6038 0.7125 0.5393 0.6038 0.7125 0.5393 0.6038
MLP 0.4741 0.7799 0.5897 0.5612 0.5271 0.5436 0.5739 0.4582 0.5096
GRU 0.9999 0.4421 0.6131 0.9999 0.4421 0.6131 0.9999 0.4421 0.6131
BiGRU 0.5448 0.5262 0.5353 0.8999 0.4421 0.5929 0.9999 0.4421 0.6131
CNN 0.5908 0.7546 0.6628 0.6211 0.6278 0.6244 0.6571 0.5432 0.5948
CNN-BiGRU 0.5586 0.8052 0.6596 0.6318 0.6529 0.6422 0.7327 0.4914 0.5883
Averages 0.6336 0.6616 0.6121 0.7428 0.5384 0.6033 0.7927 0.4754 0.5838
es
MB 0.6699 0.5285 0.5909 0.6699 0.5285 0.5909 0.6699 0.5285 0.5909
CB 0.7953 0.4399 0.5665 0.7953 0.4399 0.5665 0.7953 0.4399 0.5665
Averages 0.7326 0.4842 0.5787 0.7326 0.4842 0.5787 0.7326 0.4842 0.5787
MLP 0.4232 0.8295 0.5604 0.5382 0.5678 0.5526 0.5771 0.4465 0.5034
GRU 0.5246 0.7483 0.6168 0.7089 0.4304 0.5356 0.9999 0.4153 0.5869
BiGRU 0.5321 0.7451 0.6209 0.6335 0.4692 0.5391 0.9999 0.4153 0.5869
CNN 0.5997 0.7519 0.6672 0.6606 0.6521 0.6563 0.7065 0.5467 0.6164
CNN-BiGRU 0.5227 0.8221 0.6390 0.6195 0.6968 0.6559 0.6843 0.5369 0.6017
Averages 0.5205 0.7794 0.6209 0.6321 0.5633 0.5879 0.7935 0.4721 0.5790
43
Statistical analysis
q = 0.2500 q = 0.5000
Proposal Ranking Comparison z p-value Proposal Ranking Comparison z p-value
CNN 1.0000 CNN x CNN - - CNN-BiGRU 1.4000 CNN-BiGRU x CNN-BiGRU - -
CNN-BiGRU 2.0000 CNN x CNN-BiGRU 1.4142 0.1573 CNN 1.6000 CNN-BiGRU x CNN 0.2828 0.7773
BiGRU 3.5000 CNN x BiGRU 3.5355 0.0008 MLP 3.1000 CNN-BiGRU x MLP 2.4042 0.0324
MLP 4.1000 CNN x MLP 4.3841 0.0000 BiGRU 4.2000 CNN-BiGRU x BiGRU 3.9598 0.0002
GRU 4.4000 CNN x GRU 4.8083 0.0000 GRU 4.7000 CNN-BiGRU x GRU 4.6669 0.0000
(a) (b)
q = 0.7500
Proposal Ranking Comparison z p-value Proposal Ranking Comparison z p-value
CNN 1.3000 CNN x CNN - - CNN0.25 1.4000 CNN0.25 x CNN0.25 - -
CNN-BiGRU 1.7000 CNN x CNN-BiGRU 0.5657 0.5716 CNN-BiGRU0.50 1.8000 CNN0.25 x CNN-BiGRU0.50 0.5657 0.5716
MLP 3.0000 CNN x MLP 2.4042 0.0324 MB 3.4000 CNN0.25 xMB 2.8284 0.0094
GRU 4.5000 CNN x GRU 4.5255 0.0000 CNN0.75 3.7000 CNN0.25 xCNN0.75 3.2527 0.0034
BiGRU 4.5000 CNN x BiGRU 4.5255 0.0000 CB 4.7000 CNN0.25 x CB 4.6669 0.0000
(c) (d)
44

Weitere ähnliche Inhalte

Ähnlich wie A Hybrid Approach to Mining Conditions

Instruction Manual | EOTech Vudu X 2-12x40 | Optics Trade
Instruction Manual | EOTech Vudu X 2-12x40 | Optics TradeInstruction Manual | EOTech Vudu X 2-12x40 | Optics Trade
Instruction Manual | EOTech Vudu X 2-12x40 | Optics TradeOptics-Trade
 
Multi-Direction Pedestrian Wind Comfort Analysis
Multi-Direction Pedestrian Wind Comfort AnalysisMulti-Direction Pedestrian Wind Comfort Analysis
Multi-Direction Pedestrian Wind Comfort AnalysisSimScale
 
Yahoo! presentation
Yahoo! presentationYahoo! presentation
Yahoo! presentationYawen Li
 
Gfm3211econtrolloopstability1572623823828
Gfm3211econtrolloopstability1572623823828Gfm3211econtrolloopstability1572623823828
Gfm3211econtrolloopstability1572623823828Hoopeer Hoopeer
 
Instruction Manual | Sig Sauer Tango6 Riflescopes | Optics Trade
 Instruction Manual | Sig Sauer Tango6 Riflescopes | Optics Trade Instruction Manual | Sig Sauer Tango6 Riflescopes | Optics Trade
Instruction Manual | Sig Sauer Tango6 Riflescopes | Optics TradeOptics-Trade
 
Predictive Performance Monitoring of Material Handling Systems Using the Perf...
Predictive Performance Monitoring of Material Handling Systems Using the Perf...Predictive Performance Monitoring of Material Handling Systems Using the Perf...
Predictive Performance Monitoring of Material Handling Systems Using the Perf...Vadim Denisov
 
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W1 Process Capability
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W1 Process CapabilityJavier Garcia - Verdugo Sanchez - Six Sigma Training - W1 Process Capability
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W1 Process CapabilityJ. García - Verdugo
 
Pushover analysis-sacs
Pushover analysis-sacsPushover analysis-sacs
Pushover analysis-sacsHoàng Bkaero
 
Instruction Manual | EOTech Vudu X 1-6x24 | Optics Trade
Instruction Manual | EOTech Vudu X 1-6x24 | Optics TradeInstruction Manual | EOTech Vudu X 1-6x24 | Optics Trade
Instruction Manual | EOTech Vudu X 1-6x24 | Optics TradeOptics-Trade
 
1.28 Inch Screen 240x240 Round LCD Display For Smart Watch Wearable Device
1.28 Inch Screen 240x240 Round LCD Display For Smart Watch Wearable Device1.28 Inch Screen 240x240 Round LCD Display For Smart Watch Wearable Device
1.28 Inch Screen 240x240 Round LCD Display For Smart Watch Wearable DeviceShawn Lee
 
Chopper Wheel.ppt
Chopper Wheel.pptChopper Wheel.ppt
Chopper Wheel.pptlokma3
 
Image-to-Image Translation
Image-to-Image TranslationImage-to-Image Translation
Image-to-Image TranslationJunho Kim
 
CMU Trecvid sed11
CMU Trecvid sed11CMU Trecvid sed11
CMU Trecvid sed11Lu Jiang
 
Failure Mode Effects & Analysis
Failure Mode Effects & AnalysisFailure Mode Effects & Analysis
Failure Mode Effects & AnalysisMuhammad Rezvani
 
Scalable NDT Instruments for the Inspection of Variable Geometry Components
Scalable NDT Instruments for the Inspection of Variable Geometry ComponentsScalable NDT Instruments for the Inspection of Variable Geometry Components
Scalable NDT Instruments for the Inspection of Variable Geometry ComponentsOlympus IMS
 
Test & Measurement 2016 Product Catalog Chroma
Test & Measurement 2016 Product Catalog ChromaTest & Measurement 2016 Product Catalog Chroma
Test & Measurement 2016 Product Catalog Chromasea_cvn
 

Ähnlich wie A Hybrid Approach to Mining Conditions (20)

Instruction Manual | EOTech Vudu X 2-12x40 | Optics Trade
Instruction Manual | EOTech Vudu X 2-12x40 | Optics TradeInstruction Manual | EOTech Vudu X 2-12x40 | Optics Trade
Instruction Manual | EOTech Vudu X 2-12x40 | Optics Trade
 
Multi-Direction Pedestrian Wind Comfort Analysis
Multi-Direction Pedestrian Wind Comfort AnalysisMulti-Direction Pedestrian Wind Comfort Analysis
Multi-Direction Pedestrian Wind Comfort Analysis
 
Yahoo! presentation
Yahoo! presentationYahoo! presentation
Yahoo! presentation
 
Gfm3211econtrolloopstability1572623823828
Gfm3211econtrolloopstability1572623823828Gfm3211econtrolloopstability1572623823828
Gfm3211econtrolloopstability1572623823828
 
Instruction Manual | Sig Sauer Tango6 Riflescopes | Optics Trade
 Instruction Manual | Sig Sauer Tango6 Riflescopes | Optics Trade Instruction Manual | Sig Sauer Tango6 Riflescopes | Optics Trade
Instruction Manual | Sig Sauer Tango6 Riflescopes | Optics Trade
 
Predictive Performance Monitoring of Material Handling Systems Using the Perf...
Predictive Performance Monitoring of Material Handling Systems Using the Perf...Predictive Performance Monitoring of Material Handling Systems Using the Perf...
Predictive Performance Monitoring of Material Handling Systems Using the Perf...
 
Unit Commitment
Unit CommitmentUnit Commitment
Unit Commitment
 
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W1 Process Capability
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W1 Process CapabilityJavier Garcia - Verdugo Sanchez - Six Sigma Training - W1 Process Capability
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W1 Process Capability
 
Pushover analysis-sacs
Pushover analysis-sacsPushover analysis-sacs
Pushover analysis-sacs
 
Instruction Manual | EOTech Vudu X 1-6x24 | Optics Trade
Instruction Manual | EOTech Vudu X 1-6x24 | Optics TradeInstruction Manual | EOTech Vudu X 1-6x24 | Optics Trade
Instruction Manual | EOTech Vudu X 1-6x24 | Optics Trade
 
Extrusion software
Extrusion softwareExtrusion software
Extrusion software
 
Tree building 2
Tree building 2Tree building 2
Tree building 2
 
1.28 Inch Screen 240x240 Round LCD Display For Smart Watch Wearable Device
1.28 Inch Screen 240x240 Round LCD Display For Smart Watch Wearable Device1.28 Inch Screen 240x240 Round LCD Display For Smart Watch Wearable Device
1.28 Inch Screen 240x240 Round LCD Display For Smart Watch Wearable Device
 
Applying QbD to Biotech Process Validation
Applying QbD to Biotech Process ValidationApplying QbD to Biotech Process Validation
Applying QbD to Biotech Process Validation
 
Chopper Wheel.ppt
Chopper Wheel.pptChopper Wheel.ppt
Chopper Wheel.ppt
 
Image-to-Image Translation
Image-to-Image TranslationImage-to-Image Translation
Image-to-Image Translation
 
CMU Trecvid sed11
CMU Trecvid sed11CMU Trecvid sed11
CMU Trecvid sed11
 
Failure Mode Effects & Analysis
Failure Mode Effects & AnalysisFailure Mode Effects & Analysis
Failure Mode Effects & Analysis
 
Scalable NDT Instruments for the Inspection of Variable Geometry Components
Scalable NDT Instruments for the Inspection of Variable Geometry ComponentsScalable NDT Instruments for the Inspection of Variable Geometry Components
Scalable NDT Instruments for the Inspection of Variable Geometry Components
 
Test & Measurement 2016 Product Catalog Chroma
Test & Measurement 2016 Product Catalog ChromaTest & Measurement 2016 Product Catalog Chroma
Test & Measurement 2016 Product Catalog Chroma
 

Kürzlich hochgeladen

4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptxmary850239
 
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxiammrhaywood
 
Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Celine George
 
How to do quick user assign in kanban in Odoo 17 ERP
How to do quick user assign in kanban in Odoo 17 ERPHow to do quick user assign in kanban in Odoo 17 ERP
How to do quick user assign in kanban in Odoo 17 ERPCeline George
 
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITYISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITYKayeClaireEstoconing
 
4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptx4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptxmary850239
 
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptx
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptxMULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptx
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptxAnupkumar Sharma
 
Integumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.pptIntegumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.pptshraddhaparab530
 
THEORIES OF ORGANIZATION-PUBLIC ADMINISTRATION
THEORIES OF ORGANIZATION-PUBLIC ADMINISTRATIONTHEORIES OF ORGANIZATION-PUBLIC ADMINISTRATION
THEORIES OF ORGANIZATION-PUBLIC ADMINISTRATIONHumphrey A Beña
 
Music 9 - 4th quarter - Vocal Music of the Romantic Period.pptx
Music 9 - 4th quarter - Vocal Music of the Romantic Period.pptxMusic 9 - 4th quarter - Vocal Music of the Romantic Period.pptx
Music 9 - 4th quarter - Vocal Music of the Romantic Period.pptxleah joy valeriano
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parentsnavabharathschool99
 
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17Celine George
 
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptxQ4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptxlancelewisportillo
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Mark Reed
 
How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17Celine George
 
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxBarangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxCarlos105
 
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTS
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTSGRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTS
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTSJoshuaGantuangco2
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfPatidar M
 
ICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdfICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdfVanessa Camilleri
 

Kürzlich hochgeladen (20)

4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx
 
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
 
Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17
 
How to do quick user assign in kanban in Odoo 17 ERP
How to do quick user assign in kanban in Odoo 17 ERPHow to do quick user assign in kanban in Odoo 17 ERP
How to do quick user assign in kanban in Odoo 17 ERP
 
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITYISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
 
4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptx4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptx
 
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptx
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptxMULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptx
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptx
 
Integumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.pptIntegumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.ppt
 
THEORIES OF ORGANIZATION-PUBLIC ADMINISTRATION
THEORIES OF ORGANIZATION-PUBLIC ADMINISTRATIONTHEORIES OF ORGANIZATION-PUBLIC ADMINISTRATION
THEORIES OF ORGANIZATION-PUBLIC ADMINISTRATION
 
Music 9 - 4th quarter - Vocal Music of the Romantic Period.pptx
Music 9 - 4th quarter - Vocal Music of the Romantic Period.pptxMusic 9 - 4th quarter - Vocal Music of the Romantic Period.pptx
Music 9 - 4th quarter - Vocal Music of the Romantic Period.pptx
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parents
 
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
 
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptxQ4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)
 
How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17
 
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxBarangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
 
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptxYOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
 
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTS
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTSGRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTS
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTS
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdf
 
ICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdfICS2208 Lecture6 Notes for SL spaces.pdf
ICS2208 Lecture6 Notes for SL spaces.pdf
 

A Hybrid Approach to Mining Conditions

  • 1. A Hybrid Approach to Mining Conditions Fernando O. Gallego, and Rafael Corchuelo
  • 2. Opinion mining Attribute Polarity “lens” Positive 2 Attribute Polarity “resolution” Neutral “Flash” Negative I think that the lens is beyond excellent for amateurs. The resolution of this camera is 13Mp. Flash is tacky when using outdoors.
  • 3. But wait! 3 The opinion is only true in a certain situation
  • 4. Opinion mining (with conditions) Attribute Polarity “lens” Positive (for amateurs) 4 Attribute Polarity “resolution” Neutral “Flash” Negative (when using outdoors) I think that the lens is beyond excellent for amateurs. The resolution of this camera is 13Mp. Flash is tacky when using outdoors.
  • 7. Condition mining 7 I think that the lens is beyond excellent for amateurs. The resolution of this camera is 13Mp. Flash is tacky when using outdoors. for amateurs when using outdoors
  • 9. Handcrafted patterns • Mausam et al. (2012) – OpenIE extraction – Dependency tree – Adverbial clauses • Chikersal et al. (2015) – Opinion mining – Basic connectives – “then”/comma 9
  • 10. And the problem is… 10
  • 11. Variability of conditions 11 0/1st/2nd/3rd conditionals If you do sth Even if sby fell down If sth had passed Should you help me When sth happens May it be accepted For sby To sby During my event While doing sth After/before sth If it occurs
  • 12. Machine learning • Nakayama et al (2015): – SVM/CRF Model – 3k Japanese sentences – Several lexicons used 12
  • 13. And the problem is… 13
  • 16. Inputs Sentence Conditions I think that the lens is beyond excellent for amateurs. [“for amateurs”] The resolution of this camera is 13Mp. [] Flash is tacky when using outdoors. [“when using outdoors”] … … 16
  • 19. Train (1/4) • Create a subset of training examples for each sentence 19 S1 S1 S1 S1 ts ts ts ts
  • 20. Train (2/4) • Generate condition candidates for a given sentence 20 outdoors tacky Flash is usingcop advcl nsubj advmod when c1: c2: advmod Flash is tacky when using outdoors when using outdoors
  • 21. Train (3/4) • Score each candidate 21 c1: c2: Flash is tacky when using outdoors when using outdoors 0.8560 1.0000
  • 22. Train (4/4) • Train a deep regressor from training set 22
  • 25. Apply (1/5) • Generate condition candidates 25 outdoors tacky Flash is usingcop advcl nsubj advmod when c1: c2: advmod Flash is tacky when using outdoors when using outdoors
  • 26. Apply (2/5) • For each condition candidate it checks whether it must be considered or not 26
  • 27. Apply (3/5) • The regressor scores the candidate 27 c1: c2: Flash is tacky when using outdoors when using outdoors 0.8560 1.0000
  • 28. Apply (4/5) • If score is equal to or greater than a given threshold, it is considered 28
  • 29. Apply (5/5) • It keeps the best non- overlapped candidates 29
  • 31. Hardware & software configuration • Intel Xeon E5-2690 • 4 threads at 2.60 Ghz • 2 GiB of RAM • Nvidia Tesla K10 GPU • CentOS Linux 7.3 • Snowball 1.2.1 • Stanford Core NLP 3.8.0 • Python 3.5.4 • Gensim 2.3.0 • Keras 2.0.8 & Theano 1.0 31
  • 36. Well done! • It overcomes the problems found in the literature • Comprehensive experimental analysis • It achieves good results 36
  • 38. Condition mining’s main applications 38 Inf. Extraction Opinion mining Recommenders
  • 39. Detailed example (1/3) 39 who cake if you be lik- ’s try nsubj dobj someone then john advmod xcompadvcl mark acl:relcl copnsubj case If you are someone who likes cakes then try John’s
  • 40. Detailed example (2/3) 40 ’s case john xcomp try - then advmod cake dobj lik- acl:relcl who nsubj someone advcl be cop you nsubj if mark c1 : c2: c3: c4: cake dobj lik- acl:relcl who nsubj someone advcl be cop you nsubj if mark cake dobj lik- acl:relcl who nsubj ’s case john xcomp who cake if you be lik- ’s try nsubj dobj someone then john advmod xcompadvcl mark acl:relcl copnsubj case
  • 42. Our Neural Networks CNN: Convolution Input ld Output .9l1.2d Activation relu Kernel 3 Drop-out 0.2000 Convolution Input .9l1.2d Output .6l.3d Activation relu Kernel 17 Drop-out 0.2000 Pooling Input .6l.3d Output .6l1 Functor max Pool global Dense Input .6l1 Output .3l1 Activation linear Drop-out 0.2000 Dense Input .3l1 Output 11 Activation tanh Drop-out 0.0000 MLP: GRU: Dense Input ld Output l.5d Activation tanh Drop-out 0.2000 Dense Input l.5d Output 11 Activation linear Drop-out 0.0000 GRU Input ld Output l1 Activation tanh Drop-out 0.1500 Dense Input l1 Output .3l1 Activation linear Drop-out 0.2000 Dense Input .3l1 Output 11 Activation tanh Drop-out 0.0000 BiGRU: BiGRU Input ld Output 2l1 Activation tanh Drop-out 0.1500 Dense Input 2l1 Output .3l1 Activation linear Drop-out 0.2000 CNN-BiGRU: Convolution Input ld Output .9l.3d Activation relu Kernel 3 Drop-out 0.0000 Pooling Input .9l.3d Output .9l.3d Functor max Pool 2 BiGRU Input .9l.3d Output 4l1 Activation tanh Drop-out 0.1500 Dense Input .4l1 Output .3l1 Activation linear Drop-out 0.2000 Dense Input 3l1 Output 11 Activation tanh Drop-out 0.0000 Dense Input .3l1 Output 11 Activation tanh Drop-out 0.0000
  • 43. Detailed results Lang Proposal q = 0.2500 q = 0.5000 q = 0.7500 P R F1 P R F1 P R F1 en MB 0.6270 0.6144 0.6206 0.6270 0.6144 0.6206 0.6270 0.6144 0.6206 CB 0.7979 0.4642 0.5870 0.7979 0.4642 0.5870 0.7979 0.4642 0.5870 Averages 0.7125 0.5393 0.6038 0.7125 0.5393 0.6038 0.7125 0.5393 0.6038 MLP 0.4741 0.7799 0.5897 0.5612 0.5271 0.5436 0.5739 0.4582 0.5096 GRU 0.9999 0.4421 0.6131 0.9999 0.4421 0.6131 0.9999 0.4421 0.6131 BiGRU 0.5448 0.5262 0.5353 0.8999 0.4421 0.5929 0.9999 0.4421 0.6131 CNN 0.5908 0.7546 0.6628 0.6211 0.6278 0.6244 0.6571 0.5432 0.5948 CNN-BiGRU 0.5586 0.8052 0.6596 0.6318 0.6529 0.6422 0.7327 0.4914 0.5883 Averages 0.6336 0.6616 0.6121 0.7428 0.5384 0.6033 0.7927 0.4754 0.5838 es MB 0.6699 0.5285 0.5909 0.6699 0.5285 0.5909 0.6699 0.5285 0.5909 CB 0.7953 0.4399 0.5665 0.7953 0.4399 0.5665 0.7953 0.4399 0.5665 Averages 0.7326 0.4842 0.5787 0.7326 0.4842 0.5787 0.7326 0.4842 0.5787 MLP 0.4232 0.8295 0.5604 0.5382 0.5678 0.5526 0.5771 0.4465 0.5034 GRU 0.5246 0.7483 0.6168 0.7089 0.4304 0.5356 0.9999 0.4153 0.5869 BiGRU 0.5321 0.7451 0.6209 0.6335 0.4692 0.5391 0.9999 0.4153 0.5869 CNN 0.5997 0.7519 0.6672 0.6606 0.6521 0.6563 0.7065 0.5467 0.6164 CNN-BiGRU 0.5227 0.8221 0.6390 0.6195 0.6968 0.6559 0.6843 0.5369 0.6017 Averages 0.5205 0.7794 0.6209 0.6321 0.5633 0.5879 0.7935 0.4721 0.5790 43
  • 44. Statistical analysis q = 0.2500 q = 0.5000 Proposal Ranking Comparison z p-value Proposal Ranking Comparison z p-value CNN 1.0000 CNN x CNN - - CNN-BiGRU 1.4000 CNN-BiGRU x CNN-BiGRU - - CNN-BiGRU 2.0000 CNN x CNN-BiGRU 1.4142 0.1573 CNN 1.6000 CNN-BiGRU x CNN 0.2828 0.7773 BiGRU 3.5000 CNN x BiGRU 3.5355 0.0008 MLP 3.1000 CNN-BiGRU x MLP 2.4042 0.0324 MLP 4.1000 CNN x MLP 4.3841 0.0000 BiGRU 4.2000 CNN-BiGRU x BiGRU 3.9598 0.0002 GRU 4.4000 CNN x GRU 4.8083 0.0000 GRU 4.7000 CNN-BiGRU x GRU 4.6669 0.0000 (a) (b) q = 0.7500 Proposal Ranking Comparison z p-value Proposal Ranking Comparison z p-value CNN 1.3000 CNN x CNN - - CNN0.25 1.4000 CNN0.25 x CNN0.25 - - CNN-BiGRU 1.7000 CNN x CNN-BiGRU 0.5657 0.5716 CNN-BiGRU0.50 1.8000 CNN0.25 x CNN-BiGRU0.50 0.5657 0.5716 MLP 3.0000 CNN x MLP 2.4042 0.0324 MB 3.4000 CNN0.25 xMB 2.8284 0.0094 GRU 4.5000 CNN x GRU 4.5255 0.0000 CNN0.75 3.7000 CNN0.25 xCNN0.75 3.2527 0.0034 BiGRU 4.5000 CNN x BiGRU 4.5255 0.0000 CB 4.7000 CNN0.25 x CB 4.6669 0.0000 (c) (d) 44

Hinweis der Redaktion

  1. Thanks for attending my presentation. My name is Fernando O. Gallego and I co-authored this paper with Rafael Corchuelo, both from the University of Seville. -- Copyright (C) 2018 The Distributed Group The use of these slides is hereby constrained to the conditions of the TDG Licence, a copy of which you may download from http://www.tdg-seville.info/License.html
  2. First of all, let’s introduce an example to understand the problem. Opinion mining is a set of natural language processing tasks whose main goal is to determine whether an opinion of a document or an aspect is positive, negative, or neutral.
  3. But wait! There is a problem that you likely didn’t notice.
  4. There are some clauses in the sentence, which are known as conditions, that changes the sense of the opinion. For instance, the positive opinion about “lens” is only true if you consider amateur photographers. Alike, the negative opinion regarding “Flash” is only true if the user uses the camera outdoors.
  5. This is the roadmap of my presentation: I’ll start with a broad introduction to the problem, then I’ll report on our proposal, then on some experimental results, and, finally, I’ll present some conclusions.
  6. Let’s start with the introduction
  7. Simply put, condition mining is a task whose goal is to identify conditions from a piece of text.
  8. Currently, there are two approaches in the literature, namely: handcrafted patterns and machine learning.
  9. Handcrafted or user-defined patterns clearly describe how to identify a condition in a text by means of connectives, pos-tags, dependency tags, or another clue words. There are two proposals in this way: Mausam, who studied the problem in the field of entity-relation extraction and uses adverbial clauses from the dependency tree; and Chikersal, who studied the problem in the field of opinion mining and uses basic connectives and tokens “then”/comma.
  10. Unfortunately, the previous proposals are not appealing because of the human effort when handcrafting such patterns.
  11. Furthermore, the results typically fall short regarding recall because of the variability of the conditions.
  12. The only existing machine-learning proposal was introduced by Nakayama et al, who worked in the field of opinion mining in Japanese. They devised a model that is based on several features from opinion expressions, which requires to provide some specific-purpose dictionaries, taxonomies, and heuristics. They used Conditional Random Fields and Support Vector Machines to learn classifiers of syntactic units of the sentences.
  13. Unfortunately, their proposal was only evaluated on a small dataset with 3,155 sentences regarding hotels and the best F1 score attained was 0.58. As a conclusion, this proposal is not generally applicable and its effectiveness is poor
  14. Then, we’ll describe our proposal
  15. Our solution is a hybrid approach that combines computational linguistics and deep learning. It does not have any of the problems found in the related work.
  16. Our inputs are a set of sentences with its corresponding sets of labelling. Those sets identify the conditions for each sentence.
  17. These are our proposal’s main methods.
  18. Method “train” returns a regressor that computes a score that assesses how likely a candidate condition is an actual condition.
  19. The procedure is repeated for every input sentence to compute a subset of training examples.
  20. The procedure starts by generating a set of condition candidates from the sentence’s dependency tree. The heuristic used is quite simple, we consider every non-leaf node in the dependency tree and compute all of the sequences of tokens that originate from that node.
  21. For each candidate, we computed a score that represents how likely it is a condition.
  22. And finally, we train a deep regressor using well-known Deep learning networks.
  23. We have experimented with a dozens neural network alternatives but the best ones are those that we present in our paper, namely: Multilayer Perceptron, Gated Recurrent Unit Network, Bidirectional Gated Recurrent Unit Network, Convolutional Neural Network, and a hybrid neural network composed of both Convolutional layers and Bidirectional Gated Recurrent Unit layers.
  24. Method “apply” returns the conditions found in a sentence by means of that regressor.
  25. We first need to compute the set of candidate conditions of the sentence. This method is the same as one used in main method train.
  26. The procedure is repeated for every candidate to check whether it must be considered or not
  27. Given a candidate, we need to score it. In this case, we use the regressor that we trained before.
  28. If the score is equal to or greater than a given threshold, it is added to the result set.
  29. Finally, we remove the conditions that overlap others with a higher score.
  30. Now, let me show you our experimental results.
  31. This is our hardware and software configuration. As you can see, it’s a pretty regular configuration with recent versions of software components.
  32. We used a dataset with almost 4 million sentences in English and Spanish. In addiction, we just increased the amount of sentences by means of new languages like French or Italian, and we uploaded it to Kaggle platform.
  33. We used the Handcrafted patterns proposals as baselines. But the Machine Learning proposal wasn’t considered because it is not clear if it can be customised to deal with languages other than Japanese and its best F1 was 0.58; neither could we find an implementation or the dataset.
  34. In this slide we present our results in terms of F1 score. Our best alternatives are, namely: CNN and CNN-BiGRU, which beats the related work proposals. We performed statistical analysis to determine which alternative is the winner.
  35. It’s time for conclusions
  36. Our conclusions are that we’ve present a proposal that overcomes the problems found in the literature. Our experimental analysis covers a variety of alternatives and it achieves promising results.
  37. Thanks for attending this presentation
  38. Corregir el símbolo del threshold.
  39. Corregir el símbolo del threshold.