SlideShare une entreprise Scribd logo
1  sur  19
Jennifer for
COVID-19:
An NLP-Powered
Chatbot Built for the
People and by the
People to Combat
Misinformation
Yunyao Li, Tyrone Grandison, Patricia
Silveyra, Ali Douraghy, Xinyu Guan, Thomas
Kieselbach, Chengkai Li, Haiqi Zhang
Pandemic + Infodemic = ?
Background
create a platform of evidence-based
information from reliable sources, curated
by scientists, that the public would find
easy to interact with.
Design Consideration Design Choices
Rapid Development Using an existing platform
Ease of Access
Chatbot available on multiple
ways
Ease of Maintenance
Maintainable without
programming by crowd
Quality Assurance
Rigorous process with clear
separation of tasks with
different levels of oversights
Extensibility
Extensible without
programming
Dialog
Manager
Conversation
Agenda
Juji Base System
Conversation Topics
IF
THEN
Extensions
Curator Helper Tester External Data
Source
Question-Answer Pairs
Admin QA Generator
If
relevance(input) > …
then …
Chat UI
Overall Architecture
Juji Base System
• Expressive visual dialog flow design
• Maintainable directly via UI
• Deployable as Web and Facebook bots
• Extensible via QA pairs in spreadsheet
• IR-style QA to match a user question against an
existing question
[Xiao, et al CHI’2020]
Design
Develop
TesteDeployment
Launch
< 24 hours
March 7
March 8
Main Capabilities: QA Pairs
• Crowdsourced: Majority of the efforts
• Auto-Generation: With manually-curated templates + CDC/WHO data
Current focus: statistics on case and death #s.
Example Process: Answer Curation
Deploy
Accurate and open?
Easy to understand?
Empathetic?
Chat Design
Support mixed Initiatives Allow two-way adaptations
1. User  System
2. System  User
Multilingual support
Plans to expand Jennifer to other languages are currently under development.
Sofía (Spanish chatbot)
- QA pairs manually translated
from the Jennifer QA pairs.
- Maintained and manually
curated by a group of bilingual
Spanish-English certified medical
interpreters.
- Uses information from Spanish
language verified sources
Preliminary Results (as of June 18,2020)
• 1056 sessions
• 1,480 questions(excluding questions selected via menus)
• Answered 1,059 of them (response rate = 71%)
• Average engagement duration = 3 min 15 sec
• COVID-19 Question Bank (COQB)
https://www.newvoicesnasem.org/data-downloads
• 3,924 COVID-19-related questions in 944 groups
Lessons Learned
• People are eager to help.
• Process and communication are Important.
• Effective and dedicated management is critical.
• Human-machine conversation requires a
proactive design
Open Challenges
• Scalable Crowdsourced Fact Checking Platform
• Minimize human efforts w/o sacrificing quality
• Zero-Shot Empathetic Natural Language Generation
• Identify resources and compose answers
• Competing Information Sources and Public Trust
• Require than technical solutions
Next Steps
• Formal evaluation
• More automation
• Fact-checking database
 Auto-generation + manual validation
• Automate process management
• Language Expansion
• Partnership
Thank You!
160+
Volunteers
141
institutions
Backup
QA Pairs
• The main capabilities of Jennifer come from the Question-Answer(QA) pairs.
• These are generated by two extension modes: Crowdsourcing and
Automated
• Crowdsourced QA pairs are managed by 4 volunteer groups: Curators,
Helpers, Testers, and Admins.
• To be included in the chatbot, each answer needs to be:
• Easy to understand
• Accurate and Open
• Demonstrate Empathy
Background
• Just as the novel coronavirus continues to infect people around the world,
harmful misinformation about it also continues to spread.
• Due to the pandemic, more people are consuming information available on
the internet, making them more vulnerable to access misleading or fake
information. The WHO has called this a “massive infodemic”.
• While scientists are well placed and willing to help fight COVID-19
misinformation, getting involved often means participating in time-
consuming efforts at the expense of their research time.
• We envisioned using AI to create a platform of evidence-based information
from reliable sources, curated by scientists, that the public would find easy to
interact with.
Design Considerations
• We designed and built "Jennifer" and recruited a global group of
volunteer scientists to help test and scale Jennifer’s performance.
• The goals of this proof-of-principle system is to demonstrate the feasibility to
directly crowd-source the global scientific community’s expertise for public
benefit without the need for intermediaries, thus helping improve public trust
in science.
• Our core design considerations are:
• Rapid Development
• Ease of Access
• Ease of Maintenance
• Quality Assurance
• Extensibility

Contenu connexe

Plus de Yunyao Li

Towards Universal Language Understanding
Towards Universal Language UnderstandingTowards Universal Language Understanding
Towards Universal Language UnderstandingYunyao Li
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language ProcessingYunyao Li
 
Towards Universal Language Understanding (2020 version)
Towards Universal Language Understanding (2020 version)Towards Universal Language Understanding (2020 version)
Towards Universal Language Understanding (2020 version)Yunyao Li
 
Towards Universal Semantic Understanding of Natural Languages
Towards Universal Semantic Understanding of Natural LanguagesTowards Universal Semantic Understanding of Natural Languages
Towards Universal Semantic Understanding of Natural LanguagesYunyao Li
 
An In-depth Analysis of the Effect of Text Normalization in Social Media
An In-depth Analysis of the Effect of Text Normalization in Social MediaAn In-depth Analysis of the Effect of Text Normalization in Social Media
An In-depth Analysis of the Effect of Text Normalization in Social MediaYunyao Li
 
Exploiting Structure in Representation of Named Entities using Active Learning
Exploiting Structure in Representation of Named Entities using Active LearningExploiting Structure in Representation of Named Entities using Active Learning
Exploiting Structure in Representation of Named Entities using Active LearningYunyao Li
 
K-SRL: Instance-based Learning for Semantic Role Labeling
K-SRL: Instance-based Learning for Semantic Role LabelingK-SRL: Instance-based Learning for Semantic Role Labeling
K-SRL: Instance-based Learning for Semantic Role LabelingYunyao Li
 
Coling poster
Coling posterColing poster
Coling posterYunyao Li
 
Natural Language Data Management and Interfaces: Recent Development and Open ...
Natural Language Data Management and Interfaces: Recent Development and Open ...Natural Language Data Management and Interfaces: Recent Development and Open ...
Natural Language Data Management and Interfaces: Recent Development and Open ...Yunyao Li
 
Polyglot: Multilingual Semantic Role Labeling with Unified Labels
Polyglot: Multilingual Semantic Role Labeling with Unified LabelsPolyglot: Multilingual Semantic Role Labeling with Unified Labels
Polyglot: Multilingual Semantic Role Labeling with Unified LabelsYunyao Li
 
Transparent Machine Learning for Information Extraction: State-of-the-Art and...
Transparent Machine Learning for Information Extraction: State-of-the-Art and...Transparent Machine Learning for Information Extraction: State-of-the-Art and...
Transparent Machine Learning for Information Extraction: State-of-the-Art and...Yunyao Li
 
The Power of Declarative Analytics
The Power of Declarative AnalyticsThe Power of Declarative Analytics
The Power of Declarative AnalyticsYunyao Li
 
Enterprise Search in the Big Data Era: Recent Developments and Open Challenges
Enterprise Search in the Big Data Era: Recent Developments and Open ChallengesEnterprise Search in the Big Data Era: Recent Developments and Open Challenges
Enterprise Search in the Big Data Era: Recent Developments and Open ChallengesYunyao Li
 
SystemT: Declarative Information Extraction
SystemT: Declarative Information ExtractionSystemT: Declarative Information Extraction
SystemT: Declarative Information ExtractionYunyao Li
 
Automatic Term Ambiguity Detection
Automatic Term Ambiguity DetectionAutomatic Term Ambiguity Detection
Automatic Term Ambiguity DetectionYunyao Li
 
Information Extraction --- An one hour summary
Information Extraction --- An one hour summaryInformation Extraction --- An one hour summary
Information Extraction --- An one hour summaryYunyao Li
 
Adaptive Parser-Centric Text Normalization
Adaptive Parser-Centric Text NormalizationAdaptive Parser-Centric Text Normalization
Adaptive Parser-Centric Text NormalizationYunyao Li
 
Enterprise information extraction: recent developments and open challenges
Enterprise information extraction: recent developments and open challengesEnterprise information extraction: recent developments and open challenges
Enterprise information extraction: recent developments and open challengesYunyao Li
 
Automatic suggestion of query-rewrite rules for enterprise search
Automatic suggestion of query-rewrite rules for enterprise searchAutomatic suggestion of query-rewrite rules for enterprise search
Automatic suggestion of query-rewrite rules for enterprise searchYunyao Li
 

Plus de Yunyao Li (20)

Towards Universal Language Understanding
Towards Universal Language UnderstandingTowards Universal Language Understanding
Towards Universal Language Understanding
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language Processing
 
Towards Universal Language Understanding (2020 version)
Towards Universal Language Understanding (2020 version)Towards Universal Language Understanding (2020 version)
Towards Universal Language Understanding (2020 version)
 
Towards Universal Semantic Understanding of Natural Languages
Towards Universal Semantic Understanding of Natural LanguagesTowards Universal Semantic Understanding of Natural Languages
Towards Universal Semantic Understanding of Natural Languages
 
An In-depth Analysis of the Effect of Text Normalization in Social Media
An In-depth Analysis of the Effect of Text Normalization in Social MediaAn In-depth Analysis of the Effect of Text Normalization in Social Media
An In-depth Analysis of the Effect of Text Normalization in Social Media
 
Exploiting Structure in Representation of Named Entities using Active Learning
Exploiting Structure in Representation of Named Entities using Active LearningExploiting Structure in Representation of Named Entities using Active Learning
Exploiting Structure in Representation of Named Entities using Active Learning
 
K-SRL: Instance-based Learning for Semantic Role Labeling
K-SRL: Instance-based Learning for Semantic Role LabelingK-SRL: Instance-based Learning for Semantic Role Labeling
K-SRL: Instance-based Learning for Semantic Role Labeling
 
Coling poster
Coling posterColing poster
Coling poster
 
Coling demo
Coling demoColing demo
Coling demo
 
Natural Language Data Management and Interfaces: Recent Development and Open ...
Natural Language Data Management and Interfaces: Recent Development and Open ...Natural Language Data Management and Interfaces: Recent Development and Open ...
Natural Language Data Management and Interfaces: Recent Development and Open ...
 
Polyglot: Multilingual Semantic Role Labeling with Unified Labels
Polyglot: Multilingual Semantic Role Labeling with Unified LabelsPolyglot: Multilingual Semantic Role Labeling with Unified Labels
Polyglot: Multilingual Semantic Role Labeling with Unified Labels
 
Transparent Machine Learning for Information Extraction: State-of-the-Art and...
Transparent Machine Learning for Information Extraction: State-of-the-Art and...Transparent Machine Learning for Information Extraction: State-of-the-Art and...
Transparent Machine Learning for Information Extraction: State-of-the-Art and...
 
The Power of Declarative Analytics
The Power of Declarative AnalyticsThe Power of Declarative Analytics
The Power of Declarative Analytics
 
Enterprise Search in the Big Data Era: Recent Developments and Open Challenges
Enterprise Search in the Big Data Era: Recent Developments and Open ChallengesEnterprise Search in the Big Data Era: Recent Developments and Open Challenges
Enterprise Search in the Big Data Era: Recent Developments and Open Challenges
 
SystemT: Declarative Information Extraction
SystemT: Declarative Information ExtractionSystemT: Declarative Information Extraction
SystemT: Declarative Information Extraction
 
Automatic Term Ambiguity Detection
Automatic Term Ambiguity DetectionAutomatic Term Ambiguity Detection
Automatic Term Ambiguity Detection
 
Information Extraction --- An one hour summary
Information Extraction --- An one hour summaryInformation Extraction --- An one hour summary
Information Extraction --- An one hour summary
 
Adaptive Parser-Centric Text Normalization
Adaptive Parser-Centric Text NormalizationAdaptive Parser-Centric Text Normalization
Adaptive Parser-Centric Text Normalization
 
Enterprise information extraction: recent developments and open challenges
Enterprise information extraction: recent developments and open challengesEnterprise information extraction: recent developments and open challenges
Enterprise information extraction: recent developments and open challenges
 
Automatic suggestion of query-rewrite rules for enterprise search
Automatic suggestion of query-rewrite rules for enterprise searchAutomatic suggestion of query-rewrite rules for enterprise search
Automatic suggestion of query-rewrite rules for enterprise search
 

Dernier

Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessPixlogix Infotech
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 

Dernier (20)

Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 

Jennifer for COVID-19: An NLP-Powered Chatbot Built for the People and by the People to Combat Misinformation

  • 1. Jennifer for COVID-19: An NLP-Powered Chatbot Built for the People and by the People to Combat Misinformation Yunyao Li, Tyrone Grandison, Patricia Silveyra, Ali Douraghy, Xinyu Guan, Thomas Kieselbach, Chengkai Li, Haiqi Zhang
  • 3. Background create a platform of evidence-based information from reliable sources, curated by scientists, that the public would find easy to interact with.
  • 4. Design Consideration Design Choices Rapid Development Using an existing platform Ease of Access Chatbot available on multiple ways Ease of Maintenance Maintainable without programming by crowd Quality Assurance Rigorous process with clear separation of tasks with different levels of oversights Extensibility Extensible without programming
  • 5. Dialog Manager Conversation Agenda Juji Base System Conversation Topics IF THEN Extensions Curator Helper Tester External Data Source Question-Answer Pairs Admin QA Generator If relevance(input) > … then … Chat UI Overall Architecture
  • 6. Juji Base System • Expressive visual dialog flow design • Maintainable directly via UI • Deployable as Web and Facebook bots • Extensible via QA pairs in spreadsheet • IR-style QA to match a user question against an existing question [Xiao, et al CHI’2020] Design Develop TesteDeployment Launch < 24 hours March 7 March 8
  • 7. Main Capabilities: QA Pairs • Crowdsourced: Majority of the efforts • Auto-Generation: With manually-curated templates + CDC/WHO data Current focus: statistics on case and death #s.
  • 8. Example Process: Answer Curation Deploy Accurate and open? Easy to understand? Empathetic?
  • 9. Chat Design Support mixed Initiatives Allow two-way adaptations 1. User  System 2. System  User
  • 10. Multilingual support Plans to expand Jennifer to other languages are currently under development. Sofía (Spanish chatbot) - QA pairs manually translated from the Jennifer QA pairs. - Maintained and manually curated by a group of bilingual Spanish-English certified medical interpreters. - Uses information from Spanish language verified sources
  • 11. Preliminary Results (as of June 18,2020) • 1056 sessions • 1,480 questions(excluding questions selected via menus) • Answered 1,059 of them (response rate = 71%) • Average engagement duration = 3 min 15 sec • COVID-19 Question Bank (COQB) https://www.newvoicesnasem.org/data-downloads • 3,924 COVID-19-related questions in 944 groups
  • 12. Lessons Learned • People are eager to help. • Process and communication are Important. • Effective and dedicated management is critical. • Human-machine conversation requires a proactive design
  • 13. Open Challenges • Scalable Crowdsourced Fact Checking Platform • Minimize human efforts w/o sacrificing quality • Zero-Shot Empathetic Natural Language Generation • Identify resources and compose answers • Competing Information Sources and Public Trust • Require than technical solutions
  • 14. Next Steps • Formal evaluation • More automation • Fact-checking database  Auto-generation + manual validation • Automate process management • Language Expansion • Partnership
  • 17. QA Pairs • The main capabilities of Jennifer come from the Question-Answer(QA) pairs. • These are generated by two extension modes: Crowdsourcing and Automated • Crowdsourced QA pairs are managed by 4 volunteer groups: Curators, Helpers, Testers, and Admins. • To be included in the chatbot, each answer needs to be: • Easy to understand • Accurate and Open • Demonstrate Empathy
  • 18. Background • Just as the novel coronavirus continues to infect people around the world, harmful misinformation about it also continues to spread. • Due to the pandemic, more people are consuming information available on the internet, making them more vulnerable to access misleading or fake information. The WHO has called this a “massive infodemic”. • While scientists are well placed and willing to help fight COVID-19 misinformation, getting involved often means participating in time- consuming efforts at the expense of their research time. • We envisioned using AI to create a platform of evidence-based information from reliable sources, curated by scientists, that the public would find easy to interact with.
  • 19. Design Considerations • We designed and built "Jennifer" and recruited a global group of volunteer scientists to help test and scale Jennifer’s performance. • The goals of this proof-of-principle system is to demonstrate the feasibility to directly crowd-source the global scientific community’s expertise for public benefit without the need for intermediaries, thus helping improve public trust in science. • Our core design considerations are: • Rapid Development • Ease of Access • Ease of Maintenance • Quality Assurance • Extensibility

Notes de l'éditeur

  1. Just as the novel coronavirus continues to infect people around the world, harmful misinformation about it also continues to spread.  Due to the pandemic, more people are consuming information available on the internet, making them more vulnerable to access misleading or fake information.  The WHO has called this a “massive infodemic”. Based on earlier study during Zika outbreak, misleading posts spread faster and were more popular than accurate posts on the large social-media site
  2. While scientists are well placed and willing to help fight COVID-19 misinformation, getting involved often means participating  in time-consuming efforts at the expense of their research time.  In our op-ed at Scientific American on how US must respond to the pandemic, we envisioned using AI to create a platform of evidence-based information from reliable sources, curated by scientists, that the public would find easy to interact with. This would ”dramatically help disseminate accurate information.
  3. The main capabilities of Jennifer come from the Question-Answer(QA) pairs.