SlideShare a Scribd company logo
1 of 22
Download to read offline
A Support Framework for Argumentative
Discussions Management in the Web
Elena Cabrio, Serena Villata, Fabien Gandon
Wimmics Team
INRIA, I3S - Sophia Antipolis, France
Supporting community managers using
NLP and argumentation
COMMUNITY
MANAGER
GOAL
Efficient management of
wiki pages by community
managers and animations
of communities
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 2
Supporting community managers using
NLP and argumentation
TEXTUAL
ENTAILMENT
TEXTUAL
ENTAILMENT
How to detect the arguments,
And the relationships
among them?
1
COMMUNITY
MANAGER
GOAL
Efficient management of
wiki pages by community
managers and animations
of communities
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 3
Supporting community managers using
NLP and argumentation
TEXTUAL
ENTAILMENT
TEXTUAL
ENTAILMENT
ARGUMENTATION
THEORY
ARGUMENTATION
THEORY
How to detect the arguments,
And the relationships
among them?
1
How to build the overall
graph of the changes and
discover the winning
arguments?
2
COMMUNITY
MANAGER
GOAL
Efficient management of
wiki pages by community
managers and animations
of communities
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 4
Supporting community managers using
NLP and argumentation
TEXTUAL
ENTAILMENT
TEXTUAL
ENTAILMENT
ARGUMENTATION
THEORY
ARGUMENTATION
THEORY
How to detect the arguments,
And the relationships
among them?
1
How to build the overall
graph of the changes and
discover the winning
arguments?
2
RDF/
SPARQL
RDF/
SPARQL
3
COMMUNITY
MANAGER
How to extract
further insightful
information?
GOAL
Efficient management of
wiki pages by community
managers and animations
of communities
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 5
Outline
1 Related literature
2 Textual Entailment and Argumentation
3 Combined Framework
4 Experimental setting on Wikipedia revisions
5 Conclusions
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 6
Related literature
• Wikipedia revisions in NLP tasks
Zanzotto and Pennacchiotti (2010)
Expanding textual entailment corpora from Wikipedia using co-training
Cabrio et al. (2012)
Extracting context-rich entailment rules from wikipedia revision history
Nelken and Yamangil (2008)
Mining wikipedia revision histories for improving sentence compression
Max and Wisniewski (2010)
Mining naturally-occurring corrections and paraphrases from wikipedia’s revision
history
Dutrey et al. (2011)
Local modifications and paraphrases in wikipedia’s revision history
• Argumentation and NLP
Moens et al. (2007)
Automatic detection of arguments in legal texts
Carenini and Moore (2006)
Generating and evaluating evaluative arguments
Wyner and van Engers (2010)
A framework for enriched, controlled online discussion forums for e-government
policy-making
Heras et al. (2010)
How argumentation can enhance dialogues in social networks
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 7
Related literature
• Wikipedia revisions in NLP tasks
Zanzotto and Pennacchiotti (2010)
Expanding textual entailment corpora from Wikipedia using co-training
Cabrio et al. (2012)
Extracting context-rich entailment rules from wikipedia revision history
Nelken and Yamangil (2008)
Mining wikipedia revision histories for improving sentence compression
Max and Wisniewski (2010)
Mining naturally-occurring corrections and paraphrases from wikipedia’s revision
history
Dutrey et al. (2011)
Local modifications and paraphrases in wikipedia’s revision history
• Argumentation and NLP
Moens et al. (2007)
Automatic detection of arguments in legal texts
Carenini and Moore (2006)
Generating and evaluating evaluative arguments
Wyner and van Engers (2010)
A framework for enriched, controlled online discussion forums for e-government
policy-making
Heras et al. (2010)
How argumentation can enhance dialogues in social networks
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 8
Textual Entailment
• Generic framework for capturing major semantic inference
needs in NLP applications (Dagan and Glickman, 2004).
• Relation between two textual fragments T and H:
T ⇒ H: meaning of H can be inferred from meaning of T, as
interpreted by a typical language user.
T (Wiki11): The land area of the contiguous United States is approximately
1,800 million acres (7,300,000 km2)
H (Wiki10): The land area of the contiguous United States is approximately
1.9 billion acres (770 million hectares)
T (Wiki10): The land area of the contiguous United States is approximately
1.9 billion acres (770 million hectares)
H (Wiki09): The total land area of the contiguous United States is approxima-
tely 1.9 billion acres.
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 9
Textual Entailment
• Generic framework for capturing major semantic inference
needs in NLP applications (Dagan and Glickman, 2004).
• Relation between two textual fragments T and H:
T ⇒ H: meaning of H can be inferred from meaning of T, as
interpreted by a typical language user.
T (Wiki11): The land area of the contiguous United States is approximately
1,800 million acres (7,300,000 km2)
H (Wiki10): The land area of the contiguous United States is approximately
1.9 billion acres (770 million hectares)
T (Wiki10): The land area of the contiguous United States is approximately
1.9 billion acres (770 million hectares)
H (Wiki09): The total land area of the contiguous United States is approxima-
tely 1.9 billion acres.
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 10
Abstract Argumentation Theory
• Directed graph (Dung, 1995)
Nodes: abstract arguments
Edges: attack relation
argument
A
argument
B
argument
C
argument
A
argument
B
IN OUT IN OUT IN
ATTACK ATTACK ATTACK
• Bipolar argumentation
(Cayrol & Lagasquie-Schiex, 2005),(Boella et al., 2010)
b ca a bc b ca
Supported attack Secondary attack Mediated attack
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 11
Combined Framework
Wikipedia revisions for the article “United States”
T (Wiki12): The land area of the contiguous United States is 2,959,064 square miles (7,663,941 km2).
H (Wiki11): The land area of the contiguous United States is approximately 1,800 million acres
(7,300,000 km2)
T (Wiki11): The land area of the contiguous United States is approximately 1,800 million acres
(7,300,000 km2)
H (Wiki10): The land area of the contiguous United States is approximately 1.9 billion acres )
(770 million hectares)
T (Wiki10): The land area of the contiguous United States is approximately 1.9 billion acres
(770 million hectares)
H (Wiki09): The total land area of the contiguous United States is approximately 1.9 billion acres.
A2
Wiki10
A3
Wiki11
A1
Wiki09
A4
Wiki12
(a)
A2
Wiki10
A3
Wiki11
A1
Wiki09
A4
Wiki12
(b)
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 12
Revisions in RDF using
SIOC-Argumentation extended vocabulary
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 13
Revisions in RDF using
SIOC-Argumentation extended vocabulary
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 14
Extracting further information
from revisions in RDF
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 15
Experimental setting:
preprocessing Wikipedia dumps
• 4 dumps of English Wikipedia (2009, 2010, 2011, 2012)
• 5 most revised pages: United States, World War II, George
Bush, Michael Jackson, Britney Spears
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 16
Experimental setting:
extraction of entailment pairs
• Documents are sentence splitted, and sentences are aligned
• To measure the similarity between the sentences: Position
Independent Word Error Rate (PER) [Tillman et al., 1997]
• Different thresholds are set to cluster pairs into different sets
• Sentences with major editing are selected (0.2<PER<0.6)
• TE pair: revised sentence as T, original sentence as H
Entailment No Entailment
Training Set 114 pairs 114 pairs
Test Set 101 pairs 123 pairs
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 17
Experimental setting: evaluation
• EDITS system (Edit Distance Textual Entailment Suite)
(Kouylekov and Negri, 2010), off-the-shelf system
Basic configuration: word overlap and cosine similarity
algorithms; distance calculated on lemmas; stopword list
• FIRST STEP: TEXTUAL ENTAILMENT
Train Test
EDITS configurations rel Precision Recall Accuracy Precision Recall Accuracy
WordOverlap
yes 0.83 0.82
0.83
0.83 0.82
0.78
no 0.76 0.73 0.79 0.82
CosineSimilarity
yes 0.58 0.89
0.63
0.52 0.87
0.58
no 0.77 0.37 0.76 0.34
• SECOND STEP: TE+ARGUMENTATION THEORY
Test
Configuration Precision Recall F-measure
WordOverlap + AT 0.90 0.92 0.91
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 18
Experimental setting: evaluation
• EDITS system (Edit Distance Textual Entailment Suite)
(Kouylekov and Negri, 2010), off-the-shelf system
Basic configuration: word overlap and cosine similarity
algorithms; distance calculated on lemmas; stopword list
• FIRST STEP: TEXTUAL ENTAILMENT
Train Test
EDITS configurations rel Precision Recall Accuracy Precision Recall Accuracy
WordOverlap
yes 0.83 0.82
0.83
0.83 0.82
0.78
no 0.76 0.73 0.79 0.82
CosineSimilarity
yes 0.58 0.89
0.63
0.52 0.87
0.58
no 0.77 0.37 0.76 0.34
• SECOND STEP: TE+ARGUMENTATION THEORY
Test
Configuration Precision Recall F-measure
WordOverlap + AT 0.90 0.92 0.91
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 19
Experimental setting: evaluation
• EDITS system (Edit Distance Textual Entailment Suite)
(Kouylekov and Negri, 2010), off-the-shelf system
Basic configuration: word overlap and cosine similarity
algorithms; distance calculated on lemmas; stopword list
• FIRST STEP: TEXTUAL ENTAILMENT
Train Test
EDITS configurations rel Precision Recall Accuracy Precision Recall Accuracy
WordOverlap
yes 0.83 0.82
0.83
0.83 0.82
0.78
no 0.76 0.73 0.79 0.82
CosineSimilarity
yes 0.58 0.89
0.63
0.52 0.87
0.58
no 0.77 0.37 0.76 0.34
• SECOND STEP: TE+ARGUMENTATION THEORY
Test
Configuration Precision Recall F-measure
WordOverlap + AT 0.90 0.92 0.91
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 20
1 Connect users to their arguments in online communities
2 Arguments’ evaluation depending on sources’ expertise
3 TE three-way judgement task:
entailment, contradiction, unknown
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 21
Thanks for your attention!
http://bit.ly/WikipediaDatasetXML
http://bit.ly/WikipediaDatasetRDF
http://bit.ly/SIOC_Argumentation
E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 22

More Related Content

Similar to Supporting Argumentative Discussions Management in the Web

Deep Neural Methods for Retrieval
Deep Neural Methods for RetrievalDeep Neural Methods for Retrieval
Deep Neural Methods for RetrievalBhaskar Mitra
 
Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Bhaskar Mitra
 
CHI2007 talk on Conflicts in Wikipedia
CHI2007 talk on Conflicts in WikipediaCHI2007 talk on Conflicts in Wikipedia
CHI2007 talk on Conflicts in WikipediaEd Chi
 
Design and Multilingual Users on Twitter and Wikipedia
Design and Multilingual Users on Twitter and WikipediaDesign and Multilingual Users on Twitter and Wikipedia
Design and Multilingual Users on Twitter and WikipediaScott A. Hale
 
Change Management in the Traditional and Semantic Web
Change Management in the Traditional and Semantic WebChange Management in the Traditional and Semantic Web
Change Management in the Traditional and Semantic WebINRIA-OAK
 
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD Cloud
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD CloudAnalyzing the Evolution of Vocabulary Terms and Their Impact on the LOD Cloud
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD CloudMOVING Project
 

Similar to Supporting Argumentative Discussions Management in the Web (10)

Deep Neural Methods for Retrieval
Deep Neural Methods for RetrievalDeep Neural Methods for Retrieval
Deep Neural Methods for Retrieval
 
Topical_Facets
Topical_FacetsTopical_Facets
Topical_Facets
 
Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)
 
CHI2007 talk on Conflicts in Wikipedia
CHI2007 talk on Conflicts in WikipediaCHI2007 talk on Conflicts in Wikipedia
CHI2007 talk on Conflicts in Wikipedia
 
Design and Multilingual Users on Twitter and Wikipedia
Design and Multilingual Users on Twitter and WikipediaDesign and Multilingual Users on Twitter and Wikipedia
Design and Multilingual Users on Twitter and Wikipedia
 
Implementation of Semantic Network Dictionary System for Global Observation ...
Implementation of Semantic Network Dictionary System for Global Observation ...Implementation of Semantic Network Dictionary System for Global Observation ...
Implementation of Semantic Network Dictionary System for Global Observation ...
 
Implementation of semantic network dictionary system
Implementation of semantic network dictionary system Implementation of semantic network dictionary system
Implementation of semantic network dictionary system
 
Change Management in the Traditional and Semantic Web
Change Management in the Traditional and Semantic WebChange Management in the Traditional and Semantic Web
Change Management in the Traditional and Semantic Web
 
Developing an Ontology for Irrigation Information Resources
Developing an Ontology for Irrigation Information Resources Developing an Ontology for Irrigation Information Resources
Developing an Ontology for Irrigation Information Resources
 
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD Cloud
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD CloudAnalyzing the Evolution of Vocabulary Terms and Their Impact on the LOD Cloud
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD Cloud
 

Recently uploaded

Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsAndrey Dotsenko
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Neo4j
 
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDGMarianaLemus7
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxnull - The Open Security Community
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 

Recently uploaded (20)

Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024
 
The transition to renewables in India.pdf
The transition to renewables in India.pdfThe transition to renewables in India.pdf
The transition to renewables in India.pdf
 
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDG
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 

Supporting Argumentative Discussions Management in the Web

  • 1. A Support Framework for Argumentative Discussions Management in the Web Elena Cabrio, Serena Villata, Fabien Gandon Wimmics Team INRIA, I3S - Sophia Antipolis, France
  • 2. Supporting community managers using NLP and argumentation COMMUNITY MANAGER GOAL Efficient management of wiki pages by community managers and animations of communities E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 2
  • 3. Supporting community managers using NLP and argumentation TEXTUAL ENTAILMENT TEXTUAL ENTAILMENT How to detect the arguments, And the relationships among them? 1 COMMUNITY MANAGER GOAL Efficient management of wiki pages by community managers and animations of communities E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 3
  • 4. Supporting community managers using NLP and argumentation TEXTUAL ENTAILMENT TEXTUAL ENTAILMENT ARGUMENTATION THEORY ARGUMENTATION THEORY How to detect the arguments, And the relationships among them? 1 How to build the overall graph of the changes and discover the winning arguments? 2 COMMUNITY MANAGER GOAL Efficient management of wiki pages by community managers and animations of communities E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 4
  • 5. Supporting community managers using NLP and argumentation TEXTUAL ENTAILMENT TEXTUAL ENTAILMENT ARGUMENTATION THEORY ARGUMENTATION THEORY How to detect the arguments, And the relationships among them? 1 How to build the overall graph of the changes and discover the winning arguments? 2 RDF/ SPARQL RDF/ SPARQL 3 COMMUNITY MANAGER How to extract further insightful information? GOAL Efficient management of wiki pages by community managers and animations of communities E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 5
  • 6. Outline 1 Related literature 2 Textual Entailment and Argumentation 3 Combined Framework 4 Experimental setting on Wikipedia revisions 5 Conclusions E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 6
  • 7. Related literature • Wikipedia revisions in NLP tasks Zanzotto and Pennacchiotti (2010) Expanding textual entailment corpora from Wikipedia using co-training Cabrio et al. (2012) Extracting context-rich entailment rules from wikipedia revision history Nelken and Yamangil (2008) Mining wikipedia revision histories for improving sentence compression Max and Wisniewski (2010) Mining naturally-occurring corrections and paraphrases from wikipedia’s revision history Dutrey et al. (2011) Local modifications and paraphrases in wikipedia’s revision history • Argumentation and NLP Moens et al. (2007) Automatic detection of arguments in legal texts Carenini and Moore (2006) Generating and evaluating evaluative arguments Wyner and van Engers (2010) A framework for enriched, controlled online discussion forums for e-government policy-making Heras et al. (2010) How argumentation can enhance dialogues in social networks E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 7
  • 8. Related literature • Wikipedia revisions in NLP tasks Zanzotto and Pennacchiotti (2010) Expanding textual entailment corpora from Wikipedia using co-training Cabrio et al. (2012) Extracting context-rich entailment rules from wikipedia revision history Nelken and Yamangil (2008) Mining wikipedia revision histories for improving sentence compression Max and Wisniewski (2010) Mining naturally-occurring corrections and paraphrases from wikipedia’s revision history Dutrey et al. (2011) Local modifications and paraphrases in wikipedia’s revision history • Argumentation and NLP Moens et al. (2007) Automatic detection of arguments in legal texts Carenini and Moore (2006) Generating and evaluating evaluative arguments Wyner and van Engers (2010) A framework for enriched, controlled online discussion forums for e-government policy-making Heras et al. (2010) How argumentation can enhance dialogues in social networks E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 8
  • 9. Textual Entailment • Generic framework for capturing major semantic inference needs in NLP applications (Dagan and Glickman, 2004). • Relation between two textual fragments T and H: T ⇒ H: meaning of H can be inferred from meaning of T, as interpreted by a typical language user. T (Wiki11): The land area of the contiguous United States is approximately 1,800 million acres (7,300,000 km2) H (Wiki10): The land area of the contiguous United States is approximately 1.9 billion acres (770 million hectares) T (Wiki10): The land area of the contiguous United States is approximately 1.9 billion acres (770 million hectares) H (Wiki09): The total land area of the contiguous United States is approxima- tely 1.9 billion acres. E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 9
  • 10. Textual Entailment • Generic framework for capturing major semantic inference needs in NLP applications (Dagan and Glickman, 2004). • Relation between two textual fragments T and H: T ⇒ H: meaning of H can be inferred from meaning of T, as interpreted by a typical language user. T (Wiki11): The land area of the contiguous United States is approximately 1,800 million acres (7,300,000 km2) H (Wiki10): The land area of the contiguous United States is approximately 1.9 billion acres (770 million hectares) T (Wiki10): The land area of the contiguous United States is approximately 1.9 billion acres (770 million hectares) H (Wiki09): The total land area of the contiguous United States is approxima- tely 1.9 billion acres. E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 10
  • 11. Abstract Argumentation Theory • Directed graph (Dung, 1995) Nodes: abstract arguments Edges: attack relation argument A argument B argument C argument A argument B IN OUT IN OUT IN ATTACK ATTACK ATTACK • Bipolar argumentation (Cayrol & Lagasquie-Schiex, 2005),(Boella et al., 2010) b ca a bc b ca Supported attack Secondary attack Mediated attack E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 11
  • 12. Combined Framework Wikipedia revisions for the article “United States” T (Wiki12): The land area of the contiguous United States is 2,959,064 square miles (7,663,941 km2). H (Wiki11): The land area of the contiguous United States is approximately 1,800 million acres (7,300,000 km2) T (Wiki11): The land area of the contiguous United States is approximately 1,800 million acres (7,300,000 km2) H (Wiki10): The land area of the contiguous United States is approximately 1.9 billion acres ) (770 million hectares) T (Wiki10): The land area of the contiguous United States is approximately 1.9 billion acres (770 million hectares) H (Wiki09): The total land area of the contiguous United States is approximately 1.9 billion acres. A2 Wiki10 A3 Wiki11 A1 Wiki09 A4 Wiki12 (a) A2 Wiki10 A3 Wiki11 A1 Wiki09 A4 Wiki12 (b) E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 12
  • 13. Revisions in RDF using SIOC-Argumentation extended vocabulary E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 13
  • 14. Revisions in RDF using SIOC-Argumentation extended vocabulary E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 14
  • 15. Extracting further information from revisions in RDF E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 15
  • 16. Experimental setting: preprocessing Wikipedia dumps • 4 dumps of English Wikipedia (2009, 2010, 2011, 2012) • 5 most revised pages: United States, World War II, George Bush, Michael Jackson, Britney Spears E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 16
  • 17. Experimental setting: extraction of entailment pairs • Documents are sentence splitted, and sentences are aligned • To measure the similarity between the sentences: Position Independent Word Error Rate (PER) [Tillman et al., 1997] • Different thresholds are set to cluster pairs into different sets • Sentences with major editing are selected (0.2<PER<0.6) • TE pair: revised sentence as T, original sentence as H Entailment No Entailment Training Set 114 pairs 114 pairs Test Set 101 pairs 123 pairs E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 17
  • 18. Experimental setting: evaluation • EDITS system (Edit Distance Textual Entailment Suite) (Kouylekov and Negri, 2010), off-the-shelf system Basic configuration: word overlap and cosine similarity algorithms; distance calculated on lemmas; stopword list • FIRST STEP: TEXTUAL ENTAILMENT Train Test EDITS configurations rel Precision Recall Accuracy Precision Recall Accuracy WordOverlap yes 0.83 0.82 0.83 0.83 0.82 0.78 no 0.76 0.73 0.79 0.82 CosineSimilarity yes 0.58 0.89 0.63 0.52 0.87 0.58 no 0.77 0.37 0.76 0.34 • SECOND STEP: TE+ARGUMENTATION THEORY Test Configuration Precision Recall F-measure WordOverlap + AT 0.90 0.92 0.91 E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 18
  • 19. Experimental setting: evaluation • EDITS system (Edit Distance Textual Entailment Suite) (Kouylekov and Negri, 2010), off-the-shelf system Basic configuration: word overlap and cosine similarity algorithms; distance calculated on lemmas; stopword list • FIRST STEP: TEXTUAL ENTAILMENT Train Test EDITS configurations rel Precision Recall Accuracy Precision Recall Accuracy WordOverlap yes 0.83 0.82 0.83 0.83 0.82 0.78 no 0.76 0.73 0.79 0.82 CosineSimilarity yes 0.58 0.89 0.63 0.52 0.87 0.58 no 0.77 0.37 0.76 0.34 • SECOND STEP: TE+ARGUMENTATION THEORY Test Configuration Precision Recall F-measure WordOverlap + AT 0.90 0.92 0.91 E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 19
  • 20. Experimental setting: evaluation • EDITS system (Edit Distance Textual Entailment Suite) (Kouylekov and Negri, 2010), off-the-shelf system Basic configuration: word overlap and cosine similarity algorithms; distance calculated on lemmas; stopword list • FIRST STEP: TEXTUAL ENTAILMENT Train Test EDITS configurations rel Precision Recall Accuracy Precision Recall Accuracy WordOverlap yes 0.83 0.82 0.83 0.83 0.82 0.78 no 0.76 0.73 0.79 0.82 CosineSimilarity yes 0.58 0.89 0.63 0.52 0.87 0.58 no 0.77 0.37 0.76 0.34 • SECOND STEP: TE+ARGUMENTATION THEORY Test Configuration Precision Recall F-measure WordOverlap + AT 0.90 0.92 0.91 E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 20
  • 21. 1 Connect users to their arguments in online communities 2 Arguments’ evaluation depending on sources’ expertise 3 TE three-way judgement task: entailment, contradiction, unknown E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 21
  • 22. Thanks for your attention! http://bit.ly/WikipediaDatasetXML http://bit.ly/WikipediaDatasetRDF http://bit.ly/SIOC_Argumentation E. Cabrio, S. Villata, F. Gandon, Argumentative Discussions Management in the Web. 22