SlideShare a Scribd company logo
A G R E E T O D I S A G R E E
I M P R O V I N G D I S A G R E E M E N T D E T E C T I O N W I T H D U A L G R U S
S U S H A N T H I R AY, V E N K AT E S H D U P PA D A
F I R S T N A M E . L A S T N A M E @ S E E R N E T. I O
S E E R N E T T E C H N O L O G I E S
E S S E M 2 0 1 7
A G R E E M E N T A N D
D I S A G R E E M E N T
• Global: Overall stance
towards the topic
• Local: Between sentences,
posts in forums
Duty Calls 

https://xkcd.com/386/
W H Y ?
• Detect presence of disputes
• Understand ideological stance of participants
• Detect sub-groups
R E L AT E D W O R K
R E L AT E D W O R K : S P E E C H
• Galley et al 2014, Hillard et al 2003, Hahn et al 2006
• Datasets: ICSI, AMI Meeting Corpus
• Features*: sentiments, n-grams, prosodic features





* The models use hand-transcribed or ASR based annotations as well
R E L AT E D W O R K : T E X T
• Yin et al 2012, Abott et al 2011, Misra and Walker 2013,
Mukherjee and Lui 2012, Rosenthal and McKeown
2015
• 2/3/5-way (dis)agreement detection
• Datasets: ABCD, AWTP, IAC, US Message Board,
AAWD, Political Forums
• Features: thread structure, lexical, style, sentiment,
polarity, durational features etc
R E L AT E D D O M A I N S
• Stance Detection: Task of identifying whether the author
of the text is in favor, against or neutral towards a target
• Argument Mining: Umbrella category which primarily
focuses on tasks like:
• automatic extraction of arguments from text
• argument proposition classification
• argumentative parsing
D ATA S E T
D ATA D E F I N I T I O N
Quote Response Pairs:
Consider only those tuples where quote(Q) functions
as a "dialogic parent" to the response(R).
D ATA S E T S
Internet argument corpus Agreement in Wikipedia Talk Pages
Agreement By Create Debators
D ATA S E T S
D ATA S E T
T H R E A D
C O U N T
P O S T
C O U N T
A G R E E D I S A G R E E N O N E
A B C D 9 9 8 1 1 8 5 4 7 9 3 8 1 9 5 6 0 9 9 1 8 6 2 9 3
I A C 1 2 2 0 5 9 4 0 4 2 8 1 2 3 6 4 2 7 6
A W T P 5 0 8 2 2 3 8 1 4 8 6 3 6
D ATA S E T S
D ATA S E T
T H R E A D
C O U N T
P O S T
C O U N T
A G R E E D I S A G R E E N O N E
A B C D 9 9 8 1 1 8 5 4 7 9 3 8 1 9 5 6 0 9 9 1 8 6 2 9 3
I A C 1 2 2 0 5 9 4 0 4 2 8 1 2 3 6 4 2 7 6
A W T P 5 0 8 2 2 3 8 1 4 8 6 3 6
3 0 X
L A R G E R
D ATA
D ATA A N N O TAT I O N : A B C D
The side information is provided by the participant on
the website createdebate.com
• AGREEMENT: Quote and Response support the same
side and the authors are different
• DISAGREEMENT: Quote and Response support
different sides and the authors are different
• NONE: Quote is Root, however the Quote and
Response have the same author
D ATA A N N O TAT I O N : I A C
• Data from 4forums
• Roughly 6000 Q-R pairs annotated for (dis)agreement
on a scale of [-5, 5]
• [-5, -1) disagreement, [-1, 1] none, (1, 5] agreement
• In case of multiple annotators, average annotation
scores are computed after filtering out the none
annotations.
D ATA A N N O TAT I O N : A W T P
• Data from Wikipedia and Livejournal
• Cohen’s κ = 0.73 for 3-way classification: agreement,
disagreement, none
• Cohen’s κ = 0.66 for 5-way classification: agreement-
response, agreement-paraphrase, disagreement-
response and disagreement-paraphrase
D ATA E X P L O R AT I O N
L A B E L P O S T
N O N E
QUOTE: Is Scientology a real religeon? Or is it a fake money making gimmick? 



RESPONSE: All religions are fake, there’s an argument to be made the vast majority are money making
gimmicks. Scien- tology is no more outlandish than any of the more widespread religions.
A G R E E
QUOTE: I am against suicide because you are basically not only harming yourself, but everyone else around
you. Let’s not mention it is a cowards way out. I also have a religious but I CAN explain that reason.
RESPONSE: So true man people only harm the people they love by dying. I am not religious and religiously
and non- religiously suicide is wrong.
D I S A G R E E
QUOTE: The majority of the information learned in school is irrelevant to real world skills. Besides, in a
voluntary setting, most children would go to school via parents demands where school choice would be much
more abundant.
RESPONSE: Children learn math which is relevant, children learn history which is relvant, children learn the
releveant languge to their country, children learn foreign languages which imporoves economic opportunites.
My one friend grew up in Baghdad, Iraq, and they don’t play when it comes to education. He started learning
English in the 3rd grade I think through graduation which helped his economic ooportunities, and he is an
artchitect so the math helped. Please excuse my typos. I have a learning disability.
F E AT U R E E X T R A C T I O N
F E AT U R E S
• Word Vectors: GloVe embeddings of 300 dimensions
• Lexicons [1]
• AFINN : Valence ratings between -5 to 5
• BingLui: Opinion Lexicons
• NRC Affect Intensity: Real valued affect intensity
• NRC Word Emotion Lexicon: 8 sense level associations and 2 sentiment level
associations
• NRC Hashtag Lexicon: Word emotion associations computed on hashtags
• LIWC: Various categorization of words according to thoughts, feelings, motivations



[1] Open source implementation: https://github.com/SEERNET/EmoInt
S Y S T E M D E S C R I P T I O N
S Y S T E M
D E S C R I P T I O N
• Siamese inspired
architecture
• Using lexical
features as well as
word embeddings
• 3-way classification

Model Architecture
S Y S T E M PA R A M E T E R S
• Sequence length: 64
• Word embedding dimension: 300
• Dropout of 0.5
• Relu layer
• Batch Normalization
E X P E R I M E N T S
E X P E R I M E N T S : F E AT U R E S U S E D
P R E C I S I O N R E C A L L
W E I G H T E D F 1
S C O R E
L E X I C O N S 0 . 7 8 8 0 0 . 7 9 8 0 . 7 8 9
G R U 0 . 7 9 2 0 . 7 9 8 0 . 7 9 4
G R U + L E X I
C O N S
0 . 8 1 2 0 . 8 1 5 0 . 8 0 4
Analyzing impact of varying features on the model performance on ABCD dataset
E X P E R I M E N T S : F E AT U R E S U S E D
P R E C I S I O N R E C A L L
W E I G H T E D F 1
S C O R E
L E X I C O N S 0 . 7 8 8 0 0 . 7 9 8 0 . 7 8 9
G R U 0 . 7 9 2 0 . 7 9 8 0 . 7 9 4
G R U + L E X I
C O N S
0 . 8 1 2 0 . 8 1 5 0 . 8 0 4
Analyzing impact of varying features on the model performance on ABCD dataset
S O TA : 0 . 7 7 6
E X P E R I M E N T S : S E Q U E N C E L E N G T H
S E Q U E N C E
L E N G T H S
P R E C I S I O N R E C A L L
W E I G H T E D F 1
S C O R E
3 2 0 . 8 1 0 0 . 8 1 3 0 . 8 0 6
6 4 0 . 8 1 2 0 . 8 1 5 0 . 8 0 4
1 2 8 0 . 8 0 5 0 . 8 0 8 0 . 7 9 6
Investigating impact of varying maximum sequence length on model performance. Results are
on ABCD dataset
E X P E R I M E N T S : S E Q U E N C E L E N G T H
Distribution of sequence length in Q-R pairs. The graph shows the number of posts v/s sequence length.
E X P E R I M E N T S : T R A N S F E R L E A R N I N G
M O D E L P R E C I S I O N R E C A L L W E I G H T E D F 1 S C O R E
S O TA - - 0 . 5 7 8
D I R E C T 0 . 4 7 3 0 . 3 6 4 0 . 2 8 5
T U N I N G 0 . 5 3 0 0 . 5 7 2 0 . 4 5 0
T R A N S F E R 0 . 5 0 8 0 . 5 5 9 0 . 4 6 5
R E T R A I N L A S T
2 L AY E R S
0 . 5 3 1 0 . 5 7 2 0 . 4 6 0
R E T R A I N L A S T
3 L AY E R S
0 . 5 2 3 0 . 5 7 0 0 . 4 2 8
Tuning Model trained on ABCD for IAC
E X P E R I M E N T S : T R A N S F E R L E A R N I N G
M O D E L P R E C I S I O N R E C A L L W E I G H T E D F 1 S C O R E
S O TA - - 0 . 4 4 4
D I R E C T 0 . 4 3 4 0 . 4 4 5 0 . 3 8 9
T U N I N G 0 . 5 1 5 0 . 4 7 0 0 . 4 6 4
T R A N S F E R 0 . 5 2 5 0 . 4 3 7 0 . 4 4 7
R E T R A I N L A S T
2 L AY E R S
0 . 5 3 4 0 . 4 5 7 0 . 4 4 7
R E T R A I N L A S T
3 L AY E R S
0 . 4 7 7 0 . 5 4 6 0 . 4 8 6
Tuning Model trained on ABCD for AWTP
E X P E R I M E N T S : T R A N S F E R L E A R N I N G
M O D E L P R E C I S I O N R E C A L L W E I G H T E D F 1 S C O R E
S O TA - - 0 . 4 4 4
D I R E C T 0 . 4 3 4 0 . 4 4 5 0 . 3 8 9
T U N I N G 0 . 5 1 5 0 . 4 7 0 0 . 4 6 4
T R A N S F E R 0 . 5 2 5 0 . 4 3 7 0 . 4 4 7
R E T R A I N L A S T
2 L AY E R S
0 . 5 3 4 0 . 4 5 7 0 . 4 4 7
R E T R A I N L A S T
3 L AY E R S
0 . 4 7 7 0 . 5 4 6 0 . 4 8 6
Tuning Model trained on ABCD for AWTP
C O M P E T I T I V E
P E R F O R M A N C E
I S T H E M O D E L
D O M A I N
I N D E P E N D E N T ?
D O M A I N I N D E P E N D E N T ?
• Topics in Train, Development, Test are disjoint.
• Ensures model is topic independent and learns
nuances of (dis)agreement rather than specifics of the
domain.
D O M A I N I N D E P E N D E N T ?
T O P I C N A M E Q U O T E R E S P O N S E
T R A I N Are guns fun
Berno Guns are weapons that can kill people. If
an adult can find a gun to be fun, then a child
can easily find a gun to be fun. We all know
what happens when children get their hands on
guns.
dtrimble Thats like saying we all
know what happens when kids
get their hands on the car keys!
The debate is not about if they
are safe its about weather they
are fun. yes guns are fun
VA L I D AT I O N
18 years old to date
someone over 18
Safiya Thats illegal for a 16 year old to date a 19
year old the law is you have to be 18 to date
someone that's 18 years old or older
Cuaroc Not in Britain.
T E S T
Are lessons learnt from the
past relevant to today's
world of unprecedented
change
sommonsonata Hasn't germany became a
freed country due to the spread of democracy
which you have just stated?
gyliu15 The example that
Germany has become a freed
country because of the spread
of democracy is not valid.
Nevertheless, the lessons learnt
from the past are still relevant
to today's world of
unprecedented change in the
political arena.
D E T E C T I N G ( D I S ) A G R E E M E N T
I S H A R D
H A R D E X A M P L E S
L A B E L Q U O T E R E S P O N S E D E S C R I P T I O N
A G R E E
JessHall01 my parents
do not deserve it, they
treat me like shit and
that’s unecessary. NO
parents should even
romotely lay their hands
on a child. EVER.
kamranw I agree with
you there. NO parent
should hit their child. I
completely feel your
pain if that is the case. I
would be curious to
know how they treat you
like shit though. Not
sure how that is relevent
to minors being sexual
active either.
Although the
participants are on the
same side of the debate,
they are agreeing on
some sentences, which
makes it difficult to give
a single label to the
whole post
D I S A G R E E
joecavalry I tell my kids
to hurry up and eat their
breakfast so that we can
get to school on time.
My little one is so slow
that I tell her she eats
breakslow ;)
Morgie7171 AWWW
thats so cute...............
haha-
hahahahahahahahhaaha
hhha
Due to self labeling,
sometimes off topic chit-
chat on debate forums is
erroneously tagged
H A R D E X A M P L E S
L A B E L Q U O T E R E S P O N S E D E S C R I P T I O N
D I S A G R E E
Of course guns kill
people, but that doesn't
mean that they should
be banned. Knives kill
people, cars kill people,
Big Macs kill people, but
should they be banned
as well?
Do yourself a favor and
ignore anyone who tells
you to be yourself. Bad
idea in your case. Guns
don't kill people, but
people uses guns to kill
people.
Sarcastic responses are
difficult for the model to
figure out.
C O N C L U S I O N
C O N C L U S I O N
• Model doesn’t need to rely on handcrafted features
for exploiting meta-thread structures
• Model pre-trained on large corpora (ABCD) performs
competitively on much smaller hand annotated
datasets
• Model is available as an API at:
developers.deepaffects.com
N E X T S T E P S
• Applying recent developments in computational sarcasm
to improve the model’s ability to detect sarcastic responses
• Use attention based models to identify the specific
contexts the model is using to predict. This gives more
visibility in debugging the model output
• Instead of solely relying on self-labelled datasets, use them
as weak labeled datasets for semi-supervised learning and
combine them with hand-labelled datasets for correcting
mislabels.
Q U E S T I O N S ?

More Related Content

What's hot

Blue Moon - Advertising Plan (Group Project)
Blue Moon - Advertising Plan (Group Project)Blue Moon - Advertising Plan (Group Project)
Blue Moon - Advertising Plan (Group Project)
Sam Cheema
 
Data Visualizations in Digital Products (ProductCamp Boston 2016)
Data Visualizations in Digital Products (ProductCamp Boston 2016)Data Visualizations in Digital Products (ProductCamp Boston 2016)
Data Visualizations in Digital Products (ProductCamp Boston 2016)
ProductCamp Boston
 
Oudejaarskwis 2015
Oudejaarskwis 2015Oudejaarskwis 2015
Oudejaarskwis 2015
Olger Smit
 
Upgrading OpenStack? Avoid these 3 Common Pitfalls
Upgrading OpenStack? Avoid these 3 Common PitfallsUpgrading OpenStack? Avoid these 3 Common Pitfalls
Upgrading OpenStack? Avoid these 3 Common Pitfalls
Platform9
 
6sittingarrangement
6sittingarrangement6sittingarrangement
6sittingarrangement
Saurabh Trivedi
 
iCue - an Intuitive To-Do List Reminder App- Pitch Deck
iCue - an Intuitive To-Do List Reminder App- Pitch DeckiCue - an Intuitive To-Do List Reminder App- Pitch Deck
iCue - an Intuitive To-Do List Reminder App- Pitch Deck
Stephanie Lin
 
SEO: A Crash Course | What is SEO in 2015? An Ethoseo™ Presentation
SEO: A Crash Course | What is SEO in 2015? An Ethoseo™ PresentationSEO: A Crash Course | What is SEO in 2015? An Ethoseo™ Presentation
SEO: A Crash Course | What is SEO in 2015? An Ethoseo™ Presentation
Damien Wright
 
7puzzles
7puzzles7puzzles
7puzzles
Saurabh Trivedi
 
Help Ukraine
Help UkraineHelp Ukraine
Help Ukraine
NastyaTsaruk
 
Fashion Guidelines
Fashion Guidelines Fashion Guidelines
Fashion Guidelines
Saad Lemgaddar
 
American Marketing Association - Strategy Presentation
American Marketing Association - Strategy Presentation American Marketing Association - Strategy Presentation
American Marketing Association - Strategy Presentation
Sam Cheema
 
Ninja Correlation of APT Binaries
Ninja Correlation of APT BinariesNinja Correlation of APT Binaries
Ninja Correlation of APT Binaries
CODE BLUE
 
C-Suite Guide to Cybersecurity
C-Suite Guide to CybersecurityC-Suite Guide to Cybersecurity
C-Suite Guide to Cybersecurity
MICHAEL MOSHIRI
 
Ma2002 1.17 rm
Ma2002 1.17 rmMa2002 1.17 rm
Ma2002 1.17 rm
Ramakrishna Paduchuri
 
Regular Expressions for SEO
Regular Expressions for SEORegular Expressions for SEO
Regular Expressions for SEO
Jonathan Moore
 
DATA FLOWS & NATIONAL SECURITY
DATA FLOWS & NATIONAL SECURITYDATA FLOWS & NATIONAL SECURITY
DATA FLOWS & NATIONAL SECURITY
Martina F. Ferracane
 
Quiz Show - Language Trivia
Quiz Show - Language TriviaQuiz Show - Language Trivia
Quiz Show - Language Trivia
Andrew Jeppesen
 
AppTheories_T7
AppTheories_T7AppTheories_T7
AppTheories_T7
Manu Muñoz H
 
Merchandising in the Age of Invisible UI
Merchandising in the Age of Invisible UIMerchandising in the Age of Invisible UI
Merchandising in the Age of Invisible UI
Ara Berberian
 
4 reasons that you cannot engage your team after election
4 reasons that you cannot engage your team after election4 reasons that you cannot engage your team after election
4 reasons that you cannot engage your team after election
Flora Liu
 

What's hot (20)

Blue Moon - Advertising Plan (Group Project)
Blue Moon - Advertising Plan (Group Project)Blue Moon - Advertising Plan (Group Project)
Blue Moon - Advertising Plan (Group Project)
 
Data Visualizations in Digital Products (ProductCamp Boston 2016)
Data Visualizations in Digital Products (ProductCamp Boston 2016)Data Visualizations in Digital Products (ProductCamp Boston 2016)
Data Visualizations in Digital Products (ProductCamp Boston 2016)
 
Oudejaarskwis 2015
Oudejaarskwis 2015Oudejaarskwis 2015
Oudejaarskwis 2015
 
Upgrading OpenStack? Avoid these 3 Common Pitfalls
Upgrading OpenStack? Avoid these 3 Common PitfallsUpgrading OpenStack? Avoid these 3 Common Pitfalls
Upgrading OpenStack? Avoid these 3 Common Pitfalls
 
6sittingarrangement
6sittingarrangement6sittingarrangement
6sittingarrangement
 
iCue - an Intuitive To-Do List Reminder App- Pitch Deck
iCue - an Intuitive To-Do List Reminder App- Pitch DeckiCue - an Intuitive To-Do List Reminder App- Pitch Deck
iCue - an Intuitive To-Do List Reminder App- Pitch Deck
 
SEO: A Crash Course | What is SEO in 2015? An Ethoseo™ Presentation
SEO: A Crash Course | What is SEO in 2015? An Ethoseo™ PresentationSEO: A Crash Course | What is SEO in 2015? An Ethoseo™ Presentation
SEO: A Crash Course | What is SEO in 2015? An Ethoseo™ Presentation
 
7puzzles
7puzzles7puzzles
7puzzles
 
Help Ukraine
Help UkraineHelp Ukraine
Help Ukraine
 
Fashion Guidelines
Fashion Guidelines Fashion Guidelines
Fashion Guidelines
 
American Marketing Association - Strategy Presentation
American Marketing Association - Strategy Presentation American Marketing Association - Strategy Presentation
American Marketing Association - Strategy Presentation
 
Ninja Correlation of APT Binaries
Ninja Correlation of APT BinariesNinja Correlation of APT Binaries
Ninja Correlation of APT Binaries
 
C-Suite Guide to Cybersecurity
C-Suite Guide to CybersecurityC-Suite Guide to Cybersecurity
C-Suite Guide to Cybersecurity
 
Ma2002 1.17 rm
Ma2002 1.17 rmMa2002 1.17 rm
Ma2002 1.17 rm
 
Regular Expressions for SEO
Regular Expressions for SEORegular Expressions for SEO
Regular Expressions for SEO
 
DATA FLOWS & NATIONAL SECURITY
DATA FLOWS & NATIONAL SECURITYDATA FLOWS & NATIONAL SECURITY
DATA FLOWS & NATIONAL SECURITY
 
Quiz Show - Language Trivia
Quiz Show - Language TriviaQuiz Show - Language Trivia
Quiz Show - Language Trivia
 
AppTheories_T7
AppTheories_T7AppTheories_T7
AppTheories_T7
 
Merchandising in the Age of Invisible UI
Merchandising in the Age of Invisible UIMerchandising in the Age of Invisible UI
Merchandising in the Age of Invisible UI
 
4 reasons that you cannot engage your team after election
4 reasons that you cannot engage your team after election4 reasons that you cannot engage your team after election
4 reasons that you cannot engage your team after election
 

Similar to Agree to Disagree

ResearchGate - How do 'Social Networks for Scientists' Affect Libraries?
ResearchGate - How do 'Social Networks for Scientists' Affect Libraries?ResearchGate - How do 'Social Networks for Scientists' Affect Libraries?
ResearchGate - How do 'Social Networks for Scientists' Affect Libraries?
Keita Bando
 
Choosing the right database
Choosing the right databaseChoosing the right database
Choosing the right database
David Simons
 
A Central Role for DOAJ in the Global Ecosystem of Open Access infrastructures
A Central Role for DOAJ in the Global Ecosystem of Open Access infrastructuresA Central Role for DOAJ in the Global Ecosystem of Open Access infrastructures
A Central Role for DOAJ in the Global Ecosystem of Open Access infrastructures
DOAJ (Directory of Open Access Journals)
 
Choosing the Right Database
Choosing the Right DatabaseChoosing the Right Database
Choosing the Right Database
David Simons
 
The Ethics of Everybody Else
The Ethics of Everybody ElseThe Ethics of Everybody Else
The Ethics of Everybody Else
Tyler Schnoebelen
 
Disruptive Testing
Disruptive TestingDisruptive Testing
Disruptive Testing
Anne-Marie Charrett
 
The Ethics of Everybody Else | Wrangle Conference 2017
The Ethics of Everybody Else | Wrangle Conference 2017The Ethics of Everybody Else | Wrangle Conference 2017
The Ethics of Everybody Else | Wrangle Conference 2017
Cloudera, Inc.
 
Data Modelling at Scale
Data Modelling at ScaleData Modelling at Scale
Data Modelling at Scale
David Simons
 
Criteria for open access publishing and indexing in DOAJ
Criteria for open access publishing and indexing in DOAJCriteria for open access publishing and indexing in DOAJ
Criteria for open access publishing and indexing in DOAJ
Clara Armengou
 
From Content Strategy to Drupal Site Building - Connecting the dots
From Content Strategy to Drupal Site Building - Connecting the dotsFrom Content Strategy to Drupal Site Building - Connecting the dots
From Content Strategy to Drupal Site Building - Connecting the dots
Ronald Ashri
 
From Content Strategy to Drupal Site Building - Connecting the Dots
From Content Strategy to Drupal Site Building - Connecting the DotsFrom Content Strategy to Drupal Site Building - Connecting the Dots
From Content Strategy to Drupal Site Building - Connecting the Dots
Ronald Ashri
 
TDD Using the SOLID Principles
TDD Using the SOLID PrinciplesTDD Using the SOLID Principles
TDD Using the SOLID PrinciplesJenna Pederson
 
California Science Center (USC CSCI 588)
California Science Center (USC CSCI 588)California Science Center (USC CSCI 588)
California Science Center (USC CSCI 588)
Sunny Chiu
 
Graph theory in Practise
Graph theory in PractiseGraph theory in Practise
Graph theory in Practise
David Simons
 
Creative Reflection: The Critical Practice of Stepping Back
Creative Reflection: The Critical Practice of Stepping BackCreative Reflection: The Critical Practice of Stepping Back
Creative Reflection: The Critical Practice of Stepping Back
char booth
 
STC-PMC November 2016 Presentation - Mobile First Content
STC-PMC November 2016 Presentation - Mobile First ContentSTC-PMC November 2016 Presentation - Mobile First Content
STC-PMC November 2016 Presentation - Mobile First Content
STC-Philadelphia Metro Chapter
 
Empower b1+ intermediate_students_book
Empower b1+ intermediate_students_bookEmpower b1+ intermediate_students_book
Empower b1+ intermediate_students_book
Htay Lwin Oo
 
Designing Pedagogical Interventions to Support Student Use of Learning Analytics
Designing Pedagogical Interventions to Support Student Use of Learning AnalyticsDesigning Pedagogical Interventions to Support Student Use of Learning Analytics
Designing Pedagogical Interventions to Support Student Use of Learning Analyticsalywise
 
Conférence - Du bon usage d'une charte graphique
Conférence - Du bon usage d'une charte graphiqueConférence - Du bon usage d'une charte graphique
Conférence - Du bon usage d'une charte graphique
David Endico
 
eHarmony @ Phoenix Con 2016
eHarmony @ Phoenix Con 2016eHarmony @ Phoenix Con 2016
eHarmony @ Phoenix Con 2016
Vijaykumar Vangapandu
 

Similar to Agree to Disagree (20)

ResearchGate - How do 'Social Networks for Scientists' Affect Libraries?
ResearchGate - How do 'Social Networks for Scientists' Affect Libraries?ResearchGate - How do 'Social Networks for Scientists' Affect Libraries?
ResearchGate - How do 'Social Networks for Scientists' Affect Libraries?
 
Choosing the right database
Choosing the right databaseChoosing the right database
Choosing the right database
 
A Central Role for DOAJ in the Global Ecosystem of Open Access infrastructures
A Central Role for DOAJ in the Global Ecosystem of Open Access infrastructuresA Central Role for DOAJ in the Global Ecosystem of Open Access infrastructures
A Central Role for DOAJ in the Global Ecosystem of Open Access infrastructures
 
Choosing the Right Database
Choosing the Right DatabaseChoosing the Right Database
Choosing the Right Database
 
The Ethics of Everybody Else
The Ethics of Everybody ElseThe Ethics of Everybody Else
The Ethics of Everybody Else
 
Disruptive Testing
Disruptive TestingDisruptive Testing
Disruptive Testing
 
The Ethics of Everybody Else | Wrangle Conference 2017
The Ethics of Everybody Else | Wrangle Conference 2017The Ethics of Everybody Else | Wrangle Conference 2017
The Ethics of Everybody Else | Wrangle Conference 2017
 
Data Modelling at Scale
Data Modelling at ScaleData Modelling at Scale
Data Modelling at Scale
 
Criteria for open access publishing and indexing in DOAJ
Criteria for open access publishing and indexing in DOAJCriteria for open access publishing and indexing in DOAJ
Criteria for open access publishing and indexing in DOAJ
 
From Content Strategy to Drupal Site Building - Connecting the dots
From Content Strategy to Drupal Site Building - Connecting the dotsFrom Content Strategy to Drupal Site Building - Connecting the dots
From Content Strategy to Drupal Site Building - Connecting the dots
 
From Content Strategy to Drupal Site Building - Connecting the Dots
From Content Strategy to Drupal Site Building - Connecting the DotsFrom Content Strategy to Drupal Site Building - Connecting the Dots
From Content Strategy to Drupal Site Building - Connecting the Dots
 
TDD Using the SOLID Principles
TDD Using the SOLID PrinciplesTDD Using the SOLID Principles
TDD Using the SOLID Principles
 
California Science Center (USC CSCI 588)
California Science Center (USC CSCI 588)California Science Center (USC CSCI 588)
California Science Center (USC CSCI 588)
 
Graph theory in Practise
Graph theory in PractiseGraph theory in Practise
Graph theory in Practise
 
Creative Reflection: The Critical Practice of Stepping Back
Creative Reflection: The Critical Practice of Stepping BackCreative Reflection: The Critical Practice of Stepping Back
Creative Reflection: The Critical Practice of Stepping Back
 
STC-PMC November 2016 Presentation - Mobile First Content
STC-PMC November 2016 Presentation - Mobile First ContentSTC-PMC November 2016 Presentation - Mobile First Content
STC-PMC November 2016 Presentation - Mobile First Content
 
Empower b1+ intermediate_students_book
Empower b1+ intermediate_students_bookEmpower b1+ intermediate_students_book
Empower b1+ intermediate_students_book
 
Designing Pedagogical Interventions to Support Student Use of Learning Analytics
Designing Pedagogical Interventions to Support Student Use of Learning AnalyticsDesigning Pedagogical Interventions to Support Student Use of Learning Analytics
Designing Pedagogical Interventions to Support Student Use of Learning Analytics
 
Conférence - Du bon usage d'une charte graphique
Conférence - Du bon usage d'une charte graphiqueConférence - Du bon usage d'une charte graphique
Conférence - Du bon usage d'une charte graphique
 
eHarmony @ Phoenix Con 2016
eHarmony @ Phoenix Con 2016eHarmony @ Phoenix Con 2016
eHarmony @ Phoenix Con 2016
 

Recently uploaded

SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
Peter Spielvogel
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
RinaMondal9
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Ramesh Iyer
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
DianaGray10
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
Alan Dix
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Product School
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Nexer Digital
 
Quantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIsQuantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIs
Vlad Stirbu
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
Alison B. Lowndes
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
Dorra BARTAGUIZ
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Thierry Lestable
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
Assure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyesAssure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.
ViralQR
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 

Recently uploaded (20)

SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
 
Quantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIsQuantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIs
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
Assure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyesAssure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyes
 
Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 

Agree to Disagree

  • 1. A G R E E T O D I S A G R E E I M P R O V I N G D I S A G R E E M E N T D E T E C T I O N W I T H D U A L G R U S S U S H A N T H I R AY, V E N K AT E S H D U P PA D A F I R S T N A M E . L A S T N A M E @ S E E R N E T. I O S E E R N E T T E C H N O L O G I E S E S S E M 2 0 1 7
  • 2. A G R E E M E N T A N D D I S A G R E E M E N T • Global: Overall stance towards the topic • Local: Between sentences, posts in forums Duty Calls 
 https://xkcd.com/386/
  • 3. W H Y ? • Detect presence of disputes • Understand ideological stance of participants • Detect sub-groups
  • 4. R E L AT E D W O R K
  • 5. R E L AT E D W O R K : S P E E C H • Galley et al 2014, Hillard et al 2003, Hahn et al 2006 • Datasets: ICSI, AMI Meeting Corpus • Features*: sentiments, n-grams, prosodic features
 
 
 * The models use hand-transcribed or ASR based annotations as well
  • 6. R E L AT E D W O R K : T E X T • Yin et al 2012, Abott et al 2011, Misra and Walker 2013, Mukherjee and Lui 2012, Rosenthal and McKeown 2015 • 2/3/5-way (dis)agreement detection • Datasets: ABCD, AWTP, IAC, US Message Board, AAWD, Political Forums • Features: thread structure, lexical, style, sentiment, polarity, durational features etc
  • 7. R E L AT E D D O M A I N S • Stance Detection: Task of identifying whether the author of the text is in favor, against or neutral towards a target • Argument Mining: Umbrella category which primarily focuses on tasks like: • automatic extraction of arguments from text • argument proposition classification • argumentative parsing
  • 8. D ATA S E T
  • 9. D ATA D E F I N I T I O N Quote Response Pairs: Consider only those tuples where quote(Q) functions as a "dialogic parent" to the response(R).
  • 10. D ATA S E T S Internet argument corpus Agreement in Wikipedia Talk Pages Agreement By Create Debators
  • 11. D ATA S E T S D ATA S E T T H R E A D C O U N T P O S T C O U N T A G R E E D I S A G R E E N O N E A B C D 9 9 8 1 1 8 5 4 7 9 3 8 1 9 5 6 0 9 9 1 8 6 2 9 3 I A C 1 2 2 0 5 9 4 0 4 2 8 1 2 3 6 4 2 7 6 A W T P 5 0 8 2 2 3 8 1 4 8 6 3 6
  • 12. D ATA S E T S D ATA S E T T H R E A D C O U N T P O S T C O U N T A G R E E D I S A G R E E N O N E A B C D 9 9 8 1 1 8 5 4 7 9 3 8 1 9 5 6 0 9 9 1 8 6 2 9 3 I A C 1 2 2 0 5 9 4 0 4 2 8 1 2 3 6 4 2 7 6 A W T P 5 0 8 2 2 3 8 1 4 8 6 3 6 3 0 X L A R G E R D ATA
  • 13. D ATA A N N O TAT I O N : A B C D The side information is provided by the participant on the website createdebate.com • AGREEMENT: Quote and Response support the same side and the authors are different • DISAGREEMENT: Quote and Response support different sides and the authors are different • NONE: Quote is Root, however the Quote and Response have the same author
  • 14. D ATA A N N O TAT I O N : I A C • Data from 4forums • Roughly 6000 Q-R pairs annotated for (dis)agreement on a scale of [-5, 5] • [-5, -1) disagreement, [-1, 1] none, (1, 5] agreement • In case of multiple annotators, average annotation scores are computed after filtering out the none annotations.
  • 15. D ATA A N N O TAT I O N : A W T P • Data from Wikipedia and Livejournal • Cohen’s κ = 0.73 for 3-way classification: agreement, disagreement, none • Cohen’s κ = 0.66 for 5-way classification: agreement- response, agreement-paraphrase, disagreement- response and disagreement-paraphrase
  • 16. D ATA E X P L O R AT I O N L A B E L P O S T N O N E QUOTE: Is Scientology a real religeon? Or is it a fake money making gimmick? 
 
 RESPONSE: All religions are fake, there’s an argument to be made the vast majority are money making gimmicks. Scien- tology is no more outlandish than any of the more widespread religions. A G R E E QUOTE: I am against suicide because you are basically not only harming yourself, but everyone else around you. Let’s not mention it is a cowards way out. I also have a religious but I CAN explain that reason. RESPONSE: So true man people only harm the people they love by dying. I am not religious and religiously and non- religiously suicide is wrong. D I S A G R E E QUOTE: The majority of the information learned in school is irrelevant to real world skills. Besides, in a voluntary setting, most children would go to school via parents demands where school choice would be much more abundant. RESPONSE: Children learn math which is relevant, children learn history which is relvant, children learn the releveant languge to their country, children learn foreign languages which imporoves economic opportunites. My one friend grew up in Baghdad, Iraq, and they don’t play when it comes to education. He started learning English in the 3rd grade I think through graduation which helped his economic ooportunities, and he is an artchitect so the math helped. Please excuse my typos. I have a learning disability.
  • 17. F E AT U R E E X T R A C T I O N
  • 18. F E AT U R E S • Word Vectors: GloVe embeddings of 300 dimensions • Lexicons [1] • AFINN : Valence ratings between -5 to 5 • BingLui: Opinion Lexicons • NRC Affect Intensity: Real valued affect intensity • NRC Word Emotion Lexicon: 8 sense level associations and 2 sentiment level associations • NRC Hashtag Lexicon: Word emotion associations computed on hashtags • LIWC: Various categorization of words according to thoughts, feelings, motivations
 
 [1] Open source implementation: https://github.com/SEERNET/EmoInt
  • 19. S Y S T E M D E S C R I P T I O N
  • 20. S Y S T E M D E S C R I P T I O N • Siamese inspired architecture • Using lexical features as well as word embeddings • 3-way classification
 Model Architecture
  • 21. S Y S T E M PA R A M E T E R S • Sequence length: 64 • Word embedding dimension: 300 • Dropout of 0.5 • Relu layer • Batch Normalization
  • 22. E X P E R I M E N T S
  • 23. E X P E R I M E N T S : F E AT U R E S U S E D P R E C I S I O N R E C A L L W E I G H T E D F 1 S C O R E L E X I C O N S 0 . 7 8 8 0 0 . 7 9 8 0 . 7 8 9 G R U 0 . 7 9 2 0 . 7 9 8 0 . 7 9 4 G R U + L E X I C O N S 0 . 8 1 2 0 . 8 1 5 0 . 8 0 4 Analyzing impact of varying features on the model performance on ABCD dataset
  • 24. E X P E R I M E N T S : F E AT U R E S U S E D P R E C I S I O N R E C A L L W E I G H T E D F 1 S C O R E L E X I C O N S 0 . 7 8 8 0 0 . 7 9 8 0 . 7 8 9 G R U 0 . 7 9 2 0 . 7 9 8 0 . 7 9 4 G R U + L E X I C O N S 0 . 8 1 2 0 . 8 1 5 0 . 8 0 4 Analyzing impact of varying features on the model performance on ABCD dataset S O TA : 0 . 7 7 6
  • 25. E X P E R I M E N T S : S E Q U E N C E L E N G T H S E Q U E N C E L E N G T H S P R E C I S I O N R E C A L L W E I G H T E D F 1 S C O R E 3 2 0 . 8 1 0 0 . 8 1 3 0 . 8 0 6 6 4 0 . 8 1 2 0 . 8 1 5 0 . 8 0 4 1 2 8 0 . 8 0 5 0 . 8 0 8 0 . 7 9 6 Investigating impact of varying maximum sequence length on model performance. Results are on ABCD dataset
  • 26. E X P E R I M E N T S : S E Q U E N C E L E N G T H Distribution of sequence length in Q-R pairs. The graph shows the number of posts v/s sequence length.
  • 27. E X P E R I M E N T S : T R A N S F E R L E A R N I N G M O D E L P R E C I S I O N R E C A L L W E I G H T E D F 1 S C O R E S O TA - - 0 . 5 7 8 D I R E C T 0 . 4 7 3 0 . 3 6 4 0 . 2 8 5 T U N I N G 0 . 5 3 0 0 . 5 7 2 0 . 4 5 0 T R A N S F E R 0 . 5 0 8 0 . 5 5 9 0 . 4 6 5 R E T R A I N L A S T 2 L AY E R S 0 . 5 3 1 0 . 5 7 2 0 . 4 6 0 R E T R A I N L A S T 3 L AY E R S 0 . 5 2 3 0 . 5 7 0 0 . 4 2 8 Tuning Model trained on ABCD for IAC
  • 28. E X P E R I M E N T S : T R A N S F E R L E A R N I N G M O D E L P R E C I S I O N R E C A L L W E I G H T E D F 1 S C O R E S O TA - - 0 . 4 4 4 D I R E C T 0 . 4 3 4 0 . 4 4 5 0 . 3 8 9 T U N I N G 0 . 5 1 5 0 . 4 7 0 0 . 4 6 4 T R A N S F E R 0 . 5 2 5 0 . 4 3 7 0 . 4 4 7 R E T R A I N L A S T 2 L AY E R S 0 . 5 3 4 0 . 4 5 7 0 . 4 4 7 R E T R A I N L A S T 3 L AY E R S 0 . 4 7 7 0 . 5 4 6 0 . 4 8 6 Tuning Model trained on ABCD for AWTP
  • 29. E X P E R I M E N T S : T R A N S F E R L E A R N I N G M O D E L P R E C I S I O N R E C A L L W E I G H T E D F 1 S C O R E S O TA - - 0 . 4 4 4 D I R E C T 0 . 4 3 4 0 . 4 4 5 0 . 3 8 9 T U N I N G 0 . 5 1 5 0 . 4 7 0 0 . 4 6 4 T R A N S F E R 0 . 5 2 5 0 . 4 3 7 0 . 4 4 7 R E T R A I N L A S T 2 L AY E R S 0 . 5 3 4 0 . 4 5 7 0 . 4 4 7 R E T R A I N L A S T 3 L AY E R S 0 . 4 7 7 0 . 5 4 6 0 . 4 8 6 Tuning Model trained on ABCD for AWTP C O M P E T I T I V E P E R F O R M A N C E
  • 30. I S T H E M O D E L D O M A I N I N D E P E N D E N T ?
  • 31. D O M A I N I N D E P E N D E N T ? • Topics in Train, Development, Test are disjoint. • Ensures model is topic independent and learns nuances of (dis)agreement rather than specifics of the domain.
  • 32. D O M A I N I N D E P E N D E N T ? T O P I C N A M E Q U O T E R E S P O N S E T R A I N Are guns fun Berno Guns are weapons that can kill people. If an adult can find a gun to be fun, then a child can easily find a gun to be fun. We all know what happens when children get their hands on guns. dtrimble Thats like saying we all know what happens when kids get their hands on the car keys! The debate is not about if they are safe its about weather they are fun. yes guns are fun VA L I D AT I O N 18 years old to date someone over 18 Safiya Thats illegal for a 16 year old to date a 19 year old the law is you have to be 18 to date someone that's 18 years old or older Cuaroc Not in Britain. T E S T Are lessons learnt from the past relevant to today's world of unprecedented change sommonsonata Hasn't germany became a freed country due to the spread of democracy which you have just stated? gyliu15 The example that Germany has become a freed country because of the spread of democracy is not valid. Nevertheless, the lessons learnt from the past are still relevant to today's world of unprecedented change in the political arena.
  • 33. D E T E C T I N G ( D I S ) A G R E E M E N T I S H A R D
  • 34. H A R D E X A M P L E S L A B E L Q U O T E R E S P O N S E D E S C R I P T I O N A G R E E JessHall01 my parents do not deserve it, they treat me like shit and that’s unecessary. NO parents should even romotely lay their hands on a child. EVER. kamranw I agree with you there. NO parent should hit their child. I completely feel your pain if that is the case. I would be curious to know how they treat you like shit though. Not sure how that is relevent to minors being sexual active either. Although the participants are on the same side of the debate, they are agreeing on some sentences, which makes it difficult to give a single label to the whole post D I S A G R E E joecavalry I tell my kids to hurry up and eat their breakfast so that we can get to school on time. My little one is so slow that I tell her she eats breakslow ;) Morgie7171 AWWW thats so cute............... haha- hahahahahahahahhaaha hhha Due to self labeling, sometimes off topic chit- chat on debate forums is erroneously tagged
  • 35. H A R D E X A M P L E S L A B E L Q U O T E R E S P O N S E D E S C R I P T I O N D I S A G R E E Of course guns kill people, but that doesn't mean that they should be banned. Knives kill people, cars kill people, Big Macs kill people, but should they be banned as well? Do yourself a favor and ignore anyone who tells you to be yourself. Bad idea in your case. Guns don't kill people, but people uses guns to kill people. Sarcastic responses are difficult for the model to figure out.
  • 36. C O N C L U S I O N
  • 37. C O N C L U S I O N • Model doesn’t need to rely on handcrafted features for exploiting meta-thread structures • Model pre-trained on large corpora (ABCD) performs competitively on much smaller hand annotated datasets • Model is available as an API at: developers.deepaffects.com
  • 38. N E X T S T E P S
  • 39. • Applying recent developments in computational sarcasm to improve the model’s ability to detect sarcastic responses • Use attention based models to identify the specific contexts the model is using to predict. This gives more visibility in debugging the model output • Instead of solely relying on self-labelled datasets, use them as weak labeled datasets for semi-supervised learning and combine them with hand-labelled datasets for correcting mislabels.
  • 40. Q U E S T I O N S ?