The LTI is proud to announce the following PhD Thesis Defense:
A Crowd-Powered Conversational Assistant That Automates Itself Over Time
Ting-Hao Kenneth Huang
11:00am - Tuesday June 12, 2018
GHC 4405
Committee:
Jeffrey P. Bigham, (Chair)
Alexander I. Rudnicky
Niki Kittur
Walter S. Lasecki, (University of Michigan)
Chris Callison-Burch, (University of Pennsylvania)
Evorus: A Crowd-Powered Conversational Assistant Built to Automate Itself Ove...Ting-Hao Huang
Evorus: A Crowd-Powered Conversational Assistant Built to Automate Itself Over Time.
Ting-Hao K. Huang, Joseph Chee Chang, Jeffrey P. Bigham.
In Proceedings of Conference on Human Factors in Computing Systems 2018 (CHI 2018), 2018, Montréal, Canada.
DEF CON 23 - Rich Kelley - harness powershell weaponization made easyFelipe Prado
This document summarizes a presentation about Harness, a tool created by Rich Kelley to make Powershell weaponization easier. Harness allows fully interactive remote Powershell sessions by running payloads on target machines that import modules and return results over the wire. It uses Python and Asyncio on the listener side to seamlessly copy Powershell scripts and commands to targets, with the same capabilities as native Powershell. The tool aims to improve on previous solutions for remote Powershell execution by providing an easy way to gain access, import modules, and run commands on targets from an interactive Powershell console.
The document discusses continuous integration and deployment practices. It begins by describing environments like local, development, test, and production. It then discusses manual deployment processes and the teams involved, including developers, DBAs, sysadmins, and QA. The presentation advocates automating deployments through pipelines that build, run metrics and tests, package, and deploy code. It emphasizes making the code environment-agnostic and managing dependencies. Overall, the document promotes practices for continuous integration and deployment that help software work reliably through faster feedback and deployment.
We hear you!. Collecting and processing user feedback, for real!penpotapp
FOSDEM talk
Clara García
Product designer at Penpot and Kaleidos Open Source. Passionate about the world of usability and defender of a more inclusive digital world. Focused on user-centered design and involved in Open Source projects.
A lot of UX practitioners don't talk to users on a regular basis, at Penpot we might be on the opposite side of the spectrum. We gather a lot of feedback from our users. What for? Fixing (bugs), improving (enhancements), discovering (new needs), prioritizing (asking/frequent queries as an indicator). And the most important thing is what do we do with that feedback and which kind of feedback would we like to receive?
At Penpot, we work as a full support team. We think of our users as a knowledgeable open space they provide us and we all work to learn from the market. Also it’s important to mention that we design Penpot with Penpot, the team members are users too. Plus we manage all our work at Penpot with our sibling Taiga, a powerful agile project management tool which is our sibling company. Obviously we have our own product development vision, but we like to discover what our users think with an open- feedback policy, and feel validation with conducted tests. Our community is the most important and fundamental part in Penpot’s roadmap.
Public speaking - FDP tech leads summit - 2018-04-30Frédéric Harper
This document contains the slides from a presentation given by Frédéric Harper about overcoming the fear of public speaking. Some key points:
- Public speaking involves performing a speech to educate, inspire, or entertain a live audience.
- Harper provides tips for transforming a fear of public speaking into enthusiasm, such as sharing your passion for a topic and helping others by speaking.
- He outlines how to prepare and structure a presentation, including defining the topic, drafting an abstract, practicing, and getting comfortable answering questions.
- Suggestions are given for gaining experience speaking, such as at meetups, conferences, or Toastmasters events. Harper offers to help others overcome their fears of public speaking.
The Puppet Community: Current State and Future Plans - PuppetConf 2014Puppet
The document discusses ways to participate in the Puppet community both online and offline. It outlines how community members can contribute code, documentation, ask questions, and participate in events. The Puppet community recognizes top contributors through awards like Most Valuable Puppeteer. The community aims to be inclusive and help each other through online forums, meetups, conferences and more.
DevOps: Cultural and Tooling Tips Around the WorldDynatrace
To watch this webinar replay, please join us here:
https://info.dynatrace.com/apm_wc_devops_journey_series_tips_around_the_world_na_registration.html
DevOps: Cultural and Tooling Tips Around the World
DevOps! One of the most abused terms in the software industry over the last few years. One of the reasons for this is that the term can mean something totally different, depending on what your role is, and what kind of business you are in. Yet, it is a very real practice with solid benefits that allow companies to build better quality software faster, and with lower cost and risk.
In this 30-minute “secret sauce” session, Andreas Grabner, DevOps Activist at Dynatrace, shares customer learnings and best practices from DevOps adopters around the world. You’ll gain insights from questions like:
• What does DevOps really mean for developers, testers and operators?
• How do companies like Facebook deploy twice a day without big issues?
• How does DevOps work in industries like finance, government, and healthcare where tight regulations exist?
• Is Dev responsible for Ops? Or only if you are working in a Cloud environment?
• What is different and unique as we move from old-fashioned on-prem software to hybrid and Cloud apps?
• Why is talking to people the forgotten DevOps tool?
Evorus: A Crowd-Powered Conversational Assistant Built to Automate Itself Ove...Ting-Hao Huang
Evorus: A Crowd-Powered Conversational Assistant Built to Automate Itself Over Time.
Ting-Hao K. Huang, Joseph Chee Chang, Jeffrey P. Bigham.
In Proceedings of Conference on Human Factors in Computing Systems 2018 (CHI 2018), 2018, Montréal, Canada.
DEF CON 23 - Rich Kelley - harness powershell weaponization made easyFelipe Prado
This document summarizes a presentation about Harness, a tool created by Rich Kelley to make Powershell weaponization easier. Harness allows fully interactive remote Powershell sessions by running payloads on target machines that import modules and return results over the wire. It uses Python and Asyncio on the listener side to seamlessly copy Powershell scripts and commands to targets, with the same capabilities as native Powershell. The tool aims to improve on previous solutions for remote Powershell execution by providing an easy way to gain access, import modules, and run commands on targets from an interactive Powershell console.
The document discusses continuous integration and deployment practices. It begins by describing environments like local, development, test, and production. It then discusses manual deployment processes and the teams involved, including developers, DBAs, sysadmins, and QA. The presentation advocates automating deployments through pipelines that build, run metrics and tests, package, and deploy code. It emphasizes making the code environment-agnostic and managing dependencies. Overall, the document promotes practices for continuous integration and deployment that help software work reliably through faster feedback and deployment.
We hear you!. Collecting and processing user feedback, for real!penpotapp
FOSDEM talk
Clara García
Product designer at Penpot and Kaleidos Open Source. Passionate about the world of usability and defender of a more inclusive digital world. Focused on user-centered design and involved in Open Source projects.
A lot of UX practitioners don't talk to users on a regular basis, at Penpot we might be on the opposite side of the spectrum. We gather a lot of feedback from our users. What for? Fixing (bugs), improving (enhancements), discovering (new needs), prioritizing (asking/frequent queries as an indicator). And the most important thing is what do we do with that feedback and which kind of feedback would we like to receive?
At Penpot, we work as a full support team. We think of our users as a knowledgeable open space they provide us and we all work to learn from the market. Also it’s important to mention that we design Penpot with Penpot, the team members are users too. Plus we manage all our work at Penpot with our sibling Taiga, a powerful agile project management tool which is our sibling company. Obviously we have our own product development vision, but we like to discover what our users think with an open- feedback policy, and feel validation with conducted tests. Our community is the most important and fundamental part in Penpot’s roadmap.
Public speaking - FDP tech leads summit - 2018-04-30Frédéric Harper
This document contains the slides from a presentation given by Frédéric Harper about overcoming the fear of public speaking. Some key points:
- Public speaking involves performing a speech to educate, inspire, or entertain a live audience.
- Harper provides tips for transforming a fear of public speaking into enthusiasm, such as sharing your passion for a topic and helping others by speaking.
- He outlines how to prepare and structure a presentation, including defining the topic, drafting an abstract, practicing, and getting comfortable answering questions.
- Suggestions are given for gaining experience speaking, such as at meetups, conferences, or Toastmasters events. Harper offers to help others overcome their fears of public speaking.
The Puppet Community: Current State and Future Plans - PuppetConf 2014Puppet
The document discusses ways to participate in the Puppet community both online and offline. It outlines how community members can contribute code, documentation, ask questions, and participate in events. The Puppet community recognizes top contributors through awards like Most Valuable Puppeteer. The community aims to be inclusive and help each other through online forums, meetups, conferences and more.
DevOps: Cultural and Tooling Tips Around the WorldDynatrace
To watch this webinar replay, please join us here:
https://info.dynatrace.com/apm_wc_devops_journey_series_tips_around_the_world_na_registration.html
DevOps: Cultural and Tooling Tips Around the World
DevOps! One of the most abused terms in the software industry over the last few years. One of the reasons for this is that the term can mean something totally different, depending on what your role is, and what kind of business you are in. Yet, it is a very real practice with solid benefits that allow companies to build better quality software faster, and with lower cost and risk.
In this 30-minute “secret sauce” session, Andreas Grabner, DevOps Activist at Dynatrace, shares customer learnings and best practices from DevOps adopters around the world. You’ll gain insights from questions like:
• What does DevOps really mean for developers, testers and operators?
• How do companies like Facebook deploy twice a day without big issues?
• How does DevOps work in industries like finance, government, and healthcare where tight regulations exist?
• Is Dev responsible for Ops? Or only if you are working in a Cloud environment?
• What is different and unique as we move from old-fashioned on-prem software to hybrid and Cloud apps?
• Why is talking to people the forgotten DevOps tool?
This document presents eight assistive technology strategies that can be easily implemented using existing technology in schools. The strategies are: 1) using high-contrast settings in Windows, 2) utilizing the photo album feature in PowerPoint, 3) creating visual schedules, 4) practicing keyboarding skills, 5) developing social stories, 6) recording audio with Microsoft Word, 7) incorporating graphic organizers, and 8) implementing pacing boards. For each strategy, the document provides links to tutorials, podcasts, blogs and other resources. The overall message is that schools should focus first on low-tech and existing technology to meet student needs in a cost-effective manner.
Running Effective Virtual Meetings: Tools & Techniques for EngagementBeth Kanter
This document provides tools and techniques for running effective virtual meetings. It begins with an agenda for a virtual training session on engagement in virtual meetings. The document then discusses survey results on common types and activities in virtual meetings. It provides tips for the before, during, and after stages of virtual meetings, including design, scheduling, opening and closing exercises, facilitation techniques, and follow up. Interactive exercises and templates are demonstrated for creating meeting norms, introductions, and evaluating meetings. Recipes are given for webinar formats involving presentations and panel discussions. The overall document aims to improve engagement and effectiveness in virtual meetings.
The document outlines an agenda for a podcasting workshop on February 28th, 2008 in Oakland Schools. The agenda includes introductions to podcasting, demonstrations of cell phone and web-based podcasting, and hands-on activities for creating podcasts using Audacity and Voicethread. Participants will learn about types of podcasts, ideas for classroom podcast projects, and resources for publishing podcasts online.
The document outlines an agenda for a podcasting workshop on February 28th, 2008 in Oakland Schools. The agenda includes introductions to podcasting, demonstrations of cell phone and web-based podcasting, and hands-on activities for creating podcasts using Audacity and Voicethread. Participants will learn about types of podcasts, ideas for classroom podcast projects, and resources for publishing podcasts online.
February OpenNTF Webinar: Introduction to Ansible for NewbiesHoward Greenberg
This talk is for Domino admins and developers who would like to learn Ansible basics. Ansible is an automation engine to automate deployments. HCL provides a set of Ansible playbooks and roles to deploy a complete HCL Connections 7 environment. Come learn what Ansible is and why you should use it in this webinar.
The speaker will be:
Christoph Stoettener, HCL Ambassador
The document discusses contributing to open source projects. It begins by asking participants about their experience with coding and git. It then lists many ways one can contribute such as documentation, bug reports, reviews, development, and translations. The rest of the document outlines an activity where participants are split into groups to collaboratively develop a calculator application implementing various math functions over multiple tasks. It provides guidance on development practices like coding style, testing, and using git. It concludes by discussing the open source development process and encouraging participants to get involved in a project.
Guardian: A Crowd-Powered Spoken Dialog System for Web APIsTing-Hao Huang
Ting-Hao K. Huang, Walter S Lasecki, Jeffrey P Bigham. (2015). Guardian: A Crowd-Powered Spoken Dialog System for Web APIs. Conference on Human Computation & Crowdsourcing (HCOMP 2015), November, 2015, San Diego, USA.
SXSW 2015 Shredding Wireframes: Intro to Rapid PrototypingKyle Outlaw
This 2015 workshop at SXSW covered:
- Current state of UX, limitations of common deliverables (e.g. wireframes)
- POV on prototyping and why it's important in user experience design
- Available tools (Invision, Justinmind, etc)
- Case study: using the Tech Summit app as an example
- What about the spec?
Key Takeaways
- Wireframes are near obsolete
- Why prototype
- Available methods
- Learn about available tools, pros and cons
- Documenting detailed functionality (annotating the prototype)
Basics of contributing to an open source project - from the first Linux Learners Day at LinuxCon 2011
http://events.linuxfoundation.org/events/linuxcon/student-program
State of the Puppet Community: PuppetConf 2014Dawn Foster
Co-Presenter: Kara Sowles
The Puppet Community is one of the things that makes Puppet so special, partly because it is filled with amazing, helpful Puppet users from all over the world. It's a great place to get answers to questions, but the real magic is with the people who are contributing answers, bug reports, help, pull requests, and much more. This session will talk about the many ways that people can contribute to the community.
This session will cover:
* what the community looks like now with some real data from our metrics.
* plans we have for improving the community over the next year (or so).
* how you can contribute to Puppet and our community.
This document discusses seven tools for highly effective librarians: telephone, discussion lists, smart phones, Doodle polling sites, IM/chat reference, Jing software, and mobile optimized tools. It provides examples for each tool and how librarians can use them, such as using telephone to gather information, discussion lists in specific subject areas, and embedding quick videos in chat reference using Jing. The document also includes bonus tools for collaboration, communication, and management.
This document discusses seven tools for highly effective librarians: telephone, discussion lists, smart phones, Doodle polling sites, IM/chat reference, Jing software, and mobile optimized tools. It provides examples for each tool and how librarians can use them, such as using telephone to gather information, discussion lists in specific subject areas, and embedding quick videos in chat reference using Jing. The document also includes bonus tools for collaboration, communication, and management.
Talk for the startup of the official local Python Community, "Python Bari".
The talk is composed of three sections:
- Python meetup format
- Python history, today, and the future
- Useful best practices and resources
This document discusses how various Web 2.0 tools can be used to hone students' social and language skills. It outlines both synchronous tools like chat programs that allow for real-time interaction, as well asynchronous tools like blogs and wikis. Specific tools mentioned include blogs, wikis, Twitter, discussion forums, movie makers, and virtual worlds. The goals of using these tools are to familiarize students with technology, allow them to practice English in authentic contexts, and expand their cultural understanding through global communication. The teacher's role is to select appropriate tools to guide students in using the language and skills practice.
This document provides an agenda and information for a Hacktoberfest info session. The agenda includes introductions to open source software, Hacktoberfest, contributor guidelines, prizes, and a hands-on session on Git and GitHub basics. Key topics covered are an overview of open source software and its advantages, what Hacktoberfest is and participant eligibility, contribution guidelines, prizes for completing 4 valid pull requests, and an introduction to version control systems and the GitHub workflow.
ConveRSE framework at work (hands on RecSys Summer School)Fedelucio Narducci
The document describes ConveRSE, a domain-independent framework for building conversational recommender systems (CoRS). ConveRSE uses natural language interactions to acquire user preferences, provide recommendations, and explanations. It includes components for intent recognition, entity recognition, sentiment analysis, and a recommendation service. The framework's architecture is modular and allows building CoRS applications through a dialog manager that coordinates the other components. The document also outlines a hands-on session where attendees can implement a simplified version of ConveRSE.
Digital Odyssey 2014 : Code, the Most Important Language in the World
Friday June 6th, 2014
9:00 am - 5:00 pm
Oakham House, Ryerson University
55 Gould St
Toronto, ON M5B 1E9
Open Source software projects and communities
Panel Speakers: Randy Metcalfe, Kirsta Stapelfeldt,
This document discusses engaging communities through technology. It outlines three main groups - students, faculty, and a learning design community. For students, it notes how their access, use, and creation of media has changed with technology. It discusses efforts to systematically engage faculty through initiatives and support. It also describes an informal learning design community that meets regularly both online and in person to enhance teaching and learning.
A 10-Month-Long Deployment Study of On-Demand Recruiting for Low-Latency Crow...Ting-Hao Huang
A 10-Month-Long Deployment Study of On-Demand Recruiting for Low-Latency Crowdsourcing
Ting-Hao K. Huang, Jeffrey P. Bigham.
In Proceedings of The fifth AAAI Conference on Human Computation and Crowdsourcing (HCOMP 2017), 2017, Quebec City, Canada.
The document discusses crowd-powered conversational agents and experiments comparing different methods for aggregating responses from multiple workers. It finds that for simple queries, taking the first response provides the best speed while taking the first matching response and ESP provides the best quality. For more complex queries, ESP + first matching response with 5-8 workers and 15-20 seconds performs best, achieving around 80% F1 score. More workers generally provides better results but slower response times.
More Related Content
Similar to A Crowd-Powered Conversational Assistant That Automates Itself Over Time
This document presents eight assistive technology strategies that can be easily implemented using existing technology in schools. The strategies are: 1) using high-contrast settings in Windows, 2) utilizing the photo album feature in PowerPoint, 3) creating visual schedules, 4) practicing keyboarding skills, 5) developing social stories, 6) recording audio with Microsoft Word, 7) incorporating graphic organizers, and 8) implementing pacing boards. For each strategy, the document provides links to tutorials, podcasts, blogs and other resources. The overall message is that schools should focus first on low-tech and existing technology to meet student needs in a cost-effective manner.
Running Effective Virtual Meetings: Tools & Techniques for EngagementBeth Kanter
This document provides tools and techniques for running effective virtual meetings. It begins with an agenda for a virtual training session on engagement in virtual meetings. The document then discusses survey results on common types and activities in virtual meetings. It provides tips for the before, during, and after stages of virtual meetings, including design, scheduling, opening and closing exercises, facilitation techniques, and follow up. Interactive exercises and templates are demonstrated for creating meeting norms, introductions, and evaluating meetings. Recipes are given for webinar formats involving presentations and panel discussions. The overall document aims to improve engagement and effectiveness in virtual meetings.
The document outlines an agenda for a podcasting workshop on February 28th, 2008 in Oakland Schools. The agenda includes introductions to podcasting, demonstrations of cell phone and web-based podcasting, and hands-on activities for creating podcasts using Audacity and Voicethread. Participants will learn about types of podcasts, ideas for classroom podcast projects, and resources for publishing podcasts online.
The document outlines an agenda for a podcasting workshop on February 28th, 2008 in Oakland Schools. The agenda includes introductions to podcasting, demonstrations of cell phone and web-based podcasting, and hands-on activities for creating podcasts using Audacity and Voicethread. Participants will learn about types of podcasts, ideas for classroom podcast projects, and resources for publishing podcasts online.
February OpenNTF Webinar: Introduction to Ansible for NewbiesHoward Greenberg
This talk is for Domino admins and developers who would like to learn Ansible basics. Ansible is an automation engine to automate deployments. HCL provides a set of Ansible playbooks and roles to deploy a complete HCL Connections 7 environment. Come learn what Ansible is and why you should use it in this webinar.
The speaker will be:
Christoph Stoettener, HCL Ambassador
The document discusses contributing to open source projects. It begins by asking participants about their experience with coding and git. It then lists many ways one can contribute such as documentation, bug reports, reviews, development, and translations. The rest of the document outlines an activity where participants are split into groups to collaboratively develop a calculator application implementing various math functions over multiple tasks. It provides guidance on development practices like coding style, testing, and using git. It concludes by discussing the open source development process and encouraging participants to get involved in a project.
Guardian: A Crowd-Powered Spoken Dialog System for Web APIsTing-Hao Huang
Ting-Hao K. Huang, Walter S Lasecki, Jeffrey P Bigham. (2015). Guardian: A Crowd-Powered Spoken Dialog System for Web APIs. Conference on Human Computation & Crowdsourcing (HCOMP 2015), November, 2015, San Diego, USA.
SXSW 2015 Shredding Wireframes: Intro to Rapid PrototypingKyle Outlaw
This 2015 workshop at SXSW covered:
- Current state of UX, limitations of common deliverables (e.g. wireframes)
- POV on prototyping and why it's important in user experience design
- Available tools (Invision, Justinmind, etc)
- Case study: using the Tech Summit app as an example
- What about the spec?
Key Takeaways
- Wireframes are near obsolete
- Why prototype
- Available methods
- Learn about available tools, pros and cons
- Documenting detailed functionality (annotating the prototype)
Basics of contributing to an open source project - from the first Linux Learners Day at LinuxCon 2011
http://events.linuxfoundation.org/events/linuxcon/student-program
State of the Puppet Community: PuppetConf 2014Dawn Foster
Co-Presenter: Kara Sowles
The Puppet Community is one of the things that makes Puppet so special, partly because it is filled with amazing, helpful Puppet users from all over the world. It's a great place to get answers to questions, but the real magic is with the people who are contributing answers, bug reports, help, pull requests, and much more. This session will talk about the many ways that people can contribute to the community.
This session will cover:
* what the community looks like now with some real data from our metrics.
* plans we have for improving the community over the next year (or so).
* how you can contribute to Puppet and our community.
This document discusses seven tools for highly effective librarians: telephone, discussion lists, smart phones, Doodle polling sites, IM/chat reference, Jing software, and mobile optimized tools. It provides examples for each tool and how librarians can use them, such as using telephone to gather information, discussion lists in specific subject areas, and embedding quick videos in chat reference using Jing. The document also includes bonus tools for collaboration, communication, and management.
This document discusses seven tools for highly effective librarians: telephone, discussion lists, smart phones, Doodle polling sites, IM/chat reference, Jing software, and mobile optimized tools. It provides examples for each tool and how librarians can use them, such as using telephone to gather information, discussion lists in specific subject areas, and embedding quick videos in chat reference using Jing. The document also includes bonus tools for collaboration, communication, and management.
Talk for the startup of the official local Python Community, "Python Bari".
The talk is composed of three sections:
- Python meetup format
- Python history, today, and the future
- Useful best practices and resources
This document discusses how various Web 2.0 tools can be used to hone students' social and language skills. It outlines both synchronous tools like chat programs that allow for real-time interaction, as well asynchronous tools like blogs and wikis. Specific tools mentioned include blogs, wikis, Twitter, discussion forums, movie makers, and virtual worlds. The goals of using these tools are to familiarize students with technology, allow them to practice English in authentic contexts, and expand their cultural understanding through global communication. The teacher's role is to select appropriate tools to guide students in using the language and skills practice.
This document provides an agenda and information for a Hacktoberfest info session. The agenda includes introductions to open source software, Hacktoberfest, contributor guidelines, prizes, and a hands-on session on Git and GitHub basics. Key topics covered are an overview of open source software and its advantages, what Hacktoberfest is and participant eligibility, contribution guidelines, prizes for completing 4 valid pull requests, and an introduction to version control systems and the GitHub workflow.
ConveRSE framework at work (hands on RecSys Summer School)Fedelucio Narducci
The document describes ConveRSE, a domain-independent framework for building conversational recommender systems (CoRS). ConveRSE uses natural language interactions to acquire user preferences, provide recommendations, and explanations. It includes components for intent recognition, entity recognition, sentiment analysis, and a recommendation service. The framework's architecture is modular and allows building CoRS applications through a dialog manager that coordinates the other components. The document also outlines a hands-on session where attendees can implement a simplified version of ConveRSE.
Digital Odyssey 2014 : Code, the Most Important Language in the World
Friday June 6th, 2014
9:00 am - 5:00 pm
Oakham House, Ryerson University
55 Gould St
Toronto, ON M5B 1E9
Open Source software projects and communities
Panel Speakers: Randy Metcalfe, Kirsta Stapelfeldt,
This document discusses engaging communities through technology. It outlines three main groups - students, faculty, and a learning design community. For students, it notes how their access, use, and creation of media has changed with technology. It discusses efforts to systematically engage faculty through initiatives and support. It also describes an informal learning design community that meets regularly both online and in person to enhance teaching and learning.
Similar to A Crowd-Powered Conversational Assistant That Automates Itself Over Time (20)
A 10-Month-Long Deployment Study of On-Demand Recruiting for Low-Latency Crow...Ting-Hao Huang
A 10-Month-Long Deployment Study of On-Demand Recruiting for Low-Latency Crowdsourcing
Ting-Hao K. Huang, Jeffrey P. Bigham.
In Proceedings of The fifth AAAI Conference on Human Computation and Crowdsourcing (HCOMP 2017), 2017, Quebec City, Canada.
The document discusses crowd-powered conversational agents and experiments comparing different methods for aggregating responses from multiple workers. It finds that for simple queries, taking the first response provides the best speed while taking the first matching response and ESP provides the best quality. For more complex queries, ESP + first matching response with 5-8 workers and 15-20 seconds performs best, achieving around 80% F1 score. More workers generally provides better results but slower response times.
A Crowd-Powered Conversational Assistant That Automates Itself Over TimeTing-Hao Huang
A Crowd-Powered Conversational Assistant That Automates Itself Over Time
Ting-Hao (Kenneth) Huang
11:30am – Wednesday, January 11th
GHC 6501
Committee:
Jeffrey P. Bigham, CMU (Chair)
Alexander I. Rudnicky, CMU
Niki Kittur, CMU
Walter S. Lasecki, University of Michigan
Chris Callison-Burch, University of Pennsylvania
Abstract:
Interaction in rich natural language enables people to exchange thoughts efficiently and come to a shared understanding quickly. Modern personal intelligent assistants such as Apple's Siri and Amazon's Echo all utilize conversational interfaces as their primary communication channels, and illustrate a future that in which getting help from a computer is as easy as asking a friend. However, despite decades of research, modern conversational assistants are still limited in domain, expressiveness, and robustness. In this thesis, we take an alternative approach that blends real-time human computation with artificial intelligence to reliably engage in conversations. Instead of bootstrapping automation from the bottom up with only automatic components, we start with our crowd-powered conversational assistant, Chorus, and create a framework that enables Chorus to automate itself over time. Each of Chorus' response is proposed and voted on by a group of crowd workers in real-time. Toward realizing the goal of full automation, we (i) augmented Chorus' capability by connecting it with sensors and effectors on smartphones so that users can safely control them via conversation, and (ii) deployed Chorus to the public as a Google Hangouts chatbot to collect a large corpus of conversations to help speed automation. The deployed Chorus also provides a working system to experiment automated approaches. In the future, we will (iii) create a framework that enables Chorus to automate itself over time by automatically obtaining response candidates from multiple dialog systems and selecting appropriate responses based on the current conversation. Over time, the automated systems will take over more responsibility in Chorus, not only helping us to deploy robust conversational assistants before we know how to automate everything, but also allowing us to drive down costs and gradually reduce reliance on the crowd.
For a copy of the thesis proposal, please go to:
https://www.cs.cmu.edu/~tinghaoh/pdf/2017_thesis_proposal.pdf
"Is there anything else I can help you with?": Challenges in Deploying an On-...Ting-Hao Huang
"Is there anything else I can help you with?": Challenges in Deploying an On-Demand Crowd-Powered Conversational Agent
Ting-Hao K. Huang, Walter S. Lasecki, Amos Azaria, Jeffrey P. Bigham.
In Proceedings of Conference on Human Computation & Crowdsourcing (HCOMP 2016), 2016, Austin, TX, USA.
We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. The first release of this dataset, SIND1 v.1, includes 81,743 unique photos in 20,211 sequences, aligned to both descriptive (caption) and story language. We establish several strong baselines for the storytelling task, and motivate an automatic metric to benchmark progress. Modelling concrete description as well as figurative and social language, as provided in this dataset and the storytelling task, has the potential to move artificial intelligence from basic understandings of typical visual scenes towards more and more human-like understanding of grounded event structure and subjective expression.
Social Metaphor Detection via Topical AnalysisTing-Hao Huang
Ting-Hao (Kenneth) Huang. (2013). Social Metaphor Detection via Topical Analysis. IJCNLP 2013 Workshop on Natural Language Processing for Social Media (SocialNLP), pages 14–22, Nagoya, Japan, 14 October 2013.
Your One-Stop Shop for Python Success: Top 10 US Python Development Providersakankshawande
Simplify your search for a reliable Python development partner! This list presents the top 10 trusted US providers offering comprehensive Python development services, ensuring your project's success from conception to completion.
HCL Notes and Domino License Cost Reduction in the World of DLAUpanagenda
Webinar Recording: https://www.panagenda.com/webinars/hcl-notes-and-domino-license-cost-reduction-in-the-world-of-dlau/
The introduction of DLAU and the CCB & CCX licensing model caused quite a stir in the HCL community. As a Notes and Domino customer, you may have faced challenges with unexpected user counts and license costs. You probably have questions on how this new licensing approach works and how to benefit from it. Most importantly, you likely have budget constraints and want to save money where possible. Don’t worry, we can help with all of this!
We’ll show you how to fix common misconfigurations that cause higher-than-expected user counts, and how to identify accounts which you can deactivate to save money. There are also frequent patterns that can cause unnecessary cost, like using a person document instead of a mail-in for shared mailboxes. We’ll provide examples and solutions for those as well. And naturally we’ll explain the new licensing model.
Join HCL Ambassador Marc Thomas in this webinar with a special guest appearance from Franz Walder. It will give you the tools and know-how to stay on top of what is going on with Domino licensing. You will be able lower your cost through an optimized configuration and keep it low going forward.
These topics will be covered
- Reducing license cost by finding and fixing misconfigurations and superfluous accounts
- How do CCB and CCX licenses really work?
- Understanding the DLAU tool and how to best utilize it
- Tips for common problem areas, like team mailboxes, functional/test users, etc
- Practical examples and best practices to implement right away
Skybuffer SAM4U tool for SAP license adoptionTatiana Kojar
Manage and optimize your license adoption and consumption with SAM4U, an SAP free customer software asset management tool.
SAM4U, an SAP complimentary software asset management tool for customers, delivers a detailed and well-structured overview of license inventory and usage with a user-friendly interface. We offer a hosted, cost-effective, and performance-optimized SAM4U setup in the Skybuffer Cloud environment. You retain ownership of the system and data, while we manage the ABAP 7.58 infrastructure, ensuring fixed Total Cost of Ownership (TCO) and exceptional services through the SAP Fiori interface.
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...alexjohnson7307
Predictive maintenance is a proactive approach that anticipates equipment failures before they happen. At the forefront of this innovative strategy is Artificial Intelligence (AI), which brings unprecedented precision and efficiency. AI in predictive maintenance is transforming industries by reducing downtime, minimizing costs, and enhancing productivity.
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUpanagenda
Webinar Recording: https://www.panagenda.com/webinars/hcl-notes-und-domino-lizenzkostenreduzierung-in-der-welt-von-dlau/
DLAU und die Lizenzen nach dem CCB- und CCX-Modell sind für viele in der HCL-Community seit letztem Jahr ein heißes Thema. Als Notes- oder Domino-Kunde haben Sie vielleicht mit unerwartet hohen Benutzerzahlen und Lizenzgebühren zu kämpfen. Sie fragen sich vielleicht, wie diese neue Art der Lizenzierung funktioniert und welchen Nutzen sie Ihnen bringt. Vor allem wollen Sie sicherlich Ihr Budget einhalten und Kosten sparen, wo immer möglich. Das verstehen wir und wir möchten Ihnen dabei helfen!
Wir erklären Ihnen, wie Sie häufige Konfigurationsprobleme lösen können, die dazu führen können, dass mehr Benutzer gezählt werden als nötig, und wie Sie überflüssige oder ungenutzte Konten identifizieren und entfernen können, um Geld zu sparen. Es gibt auch einige Ansätze, die zu unnötigen Ausgaben führen können, z. B. wenn ein Personendokument anstelle eines Mail-Ins für geteilte Mailboxen verwendet wird. Wir zeigen Ihnen solche Fälle und deren Lösungen. Und natürlich erklären wir Ihnen das neue Lizenzmodell.
Nehmen Sie an diesem Webinar teil, bei dem HCL-Ambassador Marc Thomas und Gastredner Franz Walder Ihnen diese neue Welt näherbringen. Es vermittelt Ihnen die Tools und das Know-how, um den Überblick zu bewahren. Sie werden in der Lage sein, Ihre Kosten durch eine optimierte Domino-Konfiguration zu reduzieren und auch in Zukunft gering zu halten.
Diese Themen werden behandelt
- Reduzierung der Lizenzkosten durch Auffinden und Beheben von Fehlkonfigurationen und überflüssigen Konten
- Wie funktionieren CCB- und CCX-Lizenzen wirklich?
- Verstehen des DLAU-Tools und wie man es am besten nutzt
- Tipps für häufige Problembereiche, wie z. B. Team-Postfächer, Funktions-/Testbenutzer usw.
- Praxisbeispiele und Best Practices zum sofortigen Umsetzen
Ivanti’s Patch Tuesday breakdown goes beyond patching your applications and brings you the intelligence and guidance needed to prioritize where to focus your attention first. Catch early analysis on our Ivanti blog, then join industry expert Chris Goettl for the Patch Tuesday Webinar Event. There we’ll do a deep dive into each of the bulletins and give guidance on the risks associated with the newly-identified vulnerabilities.
Taking AI to the Next Level in Manufacturing.pdfssuserfac0301
Read Taking AI to the Next Level in Manufacturing to gain insights on AI adoption in the manufacturing industry, such as:
1. How quickly AI is being implemented in manufacturing.
2. Which barriers stand in the way of AI adoption.
3. How data quality and governance form the backbone of AI.
4. Organizational processes and structures that may inhibit effective AI adoption.
6. Ideas and approaches to help build your organization's AI strategy.
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...Alex Pruden
Folding is a recent technique for building efficient recursive SNARKs. Several elegant folding protocols have been proposed, such as Nova, Supernova, Hypernova, Protostar, and others. However, all of them rely on an additively homomorphic commitment scheme based on discrete log, and are therefore not post-quantum secure. In this work we present LatticeFold, the first lattice-based folding protocol based on the Module SIS problem. This folding protocol naturally leads to an efficient recursive lattice-based SNARK and an efficient PCD scheme. LatticeFold supports folding low-degree relations, such as R1CS, as well as high-degree relations, such as CCS. The key challenge is to construct a secure folding protocol that works with the Ajtai commitment scheme. The difficulty, is ensuring that extracted witnesses are low norm through many rounds of folding. We present a novel technique using the sumcheck protocol to ensure that extracted witnesses are always low norm no matter how many rounds of folding are used. Our evaluation of the final proof system suggests that it is as performant as Hypernova, while providing post-quantum security.
Paper Link: https://eprint.iacr.org/2024/257
Fueling AI with Great Data with Airbyte WebinarZilliz
This talk will focus on how to collect data from a variety of sources, leveraging this data for RAG and other GenAI use cases, and finally charting your course to productionalization.
This presentation provides valuable insights into effective cost-saving techniques on AWS. Learn how to optimize your AWS resources by rightsizing, increasing elasticity, picking the right storage class, and choosing the best pricing model. Additionally, discover essential governance mechanisms to ensure continuous cost efficiency. Whether you are new to AWS or an experienced user, this presentation provides clear and practical tips to help you reduce your cloud costs and get the most out of your budget.
Best 20 SEO Techniques To Improve Website Visibility In SERPPixlogix Infotech
Boost your website's visibility with proven SEO techniques! Our latest blog dives into essential strategies to enhance your online presence, increase traffic, and rank higher on search engines. From keyword optimization to quality content creation, learn how to make your site stand out in the crowded digital landscape. Discover actionable tips and expert insights to elevate your SEO game.
Digital Banking in the Cloud: How Citizens Bank Unlocked Their MainframePrecisely
Inconsistent user experience and siloed data, high costs, and changing customer expectations – Citizens Bank was experiencing these challenges while it was attempting to deliver a superior digital banking experience for its clients. Its core banking applications run on the mainframe and Citizens was using legacy utilities to get the critical mainframe data to feed customer-facing channels, like call centers, web, and mobile. Ultimately, this led to higher operating costs (MIPS), delayed response times, and longer time to market.
Ever-changing customer expectations demand more modern digital experiences, and the bank needed to find a solution that could provide real-time data to its customer channels with low latency and operating costs. Join this session to learn how Citizens is leveraging Precisely to replicate mainframe data to its customer channels and deliver on their “modern digital bank” experiences.
5th LF Energy Power Grid Model Meet-up SlidesDanBrown980551
5th Power Grid Model Meet-up
It is with great pleasure that we extend to you an invitation to the 5th Power Grid Model Meet-up, scheduled for 6th June 2024. This event will adopt a hybrid format, allowing participants to join us either through an online Mircosoft Teams session or in person at TU/e located at Den Dolech 2, Eindhoven, Netherlands. The meet-up will be hosted by Eindhoven University of Technology (TU/e), a research university specializing in engineering science & technology.
Power Grid Model
The global energy transition is placing new and unprecedented demands on Distribution System Operators (DSOs). Alongside upgrades to grid capacity, processes such as digitization, capacity optimization, and congestion management are becoming vital for delivering reliable services.
Power Grid Model is an open source project from Linux Foundation Energy and provides a calculation engine that is increasingly essential for DSOs. It offers a standards-based foundation enabling real-time power systems analysis, simulations of electrical power grids, and sophisticated what-if analysis. In addition, it enables in-depth studies and analysis of the electrical power grid’s behavior and performance. This comprehensive model incorporates essential factors such as power generation capacity, electrical losses, voltage levels, power flows, and system stability.
Power Grid Model is currently being applied in a wide variety of use cases, including grid planning, expansion, reliability, and congestion studies. It can also help in analyzing the impact of renewable energy integration, assessing the effects of disturbances or faults, and developing strategies for grid control and optimization.
What to expect
For the upcoming meetup we are organizing, we have an exciting lineup of activities planned:
-Insightful presentations covering two practical applications of the Power Grid Model.
-An update on the latest advancements in Power Grid -Model technology during the first and second quarters of 2024.
-An interactive brainstorming session to discuss and propose new feature requests.
-An opportunity to connect with fellow Power Grid Model enthusiasts and users.
Digital Marketing Trends in 2024 | Guide for Staying AheadWask
https://www.wask.co/ebooks/digital-marketing-trends-in-2024
Feeling lost in the digital marketing whirlwind of 2024? Technology is changing, consumer habits are evolving, and staying ahead of the curve feels like a never-ending pursuit. This e-book is your compass. Dive into actionable insights to handle the complexities of modern marketing. From hyper-personalization to the power of user-generated content, learn how to build long-term relationships with your audience and unlock the secrets to success in the ever-shifting digital landscape.
Programming Foundation Models with DSPy - Meetup SlidesZilliz
Prompting language models is hard, while programming language models is easy. In this talk, I will discuss the state-of-the-art framework DSPy for programming foundation models with its powerful optimizers and runtime constraint system.
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slackshyamraj55
Discover the seamless integration of RPA (Robotic Process Automation), COMPOSER, and APM with AWS IDP enhanced with Slack notifications. Explore how these technologies converge to streamline workflows, optimize performance, and ensure secure access, all while leveraging the power of AWS IDP and real-time communication via Slack notifications.
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
A Crowd-Powered Conversational Assistant That Automates Itself Over Time
1. Live Note/QA: http://tinyurl.com/KenDefense
1 / 85
[ Question / Feedback: http://tinyurl.com/KenDefense ]
Ting-Hao (Kenneth) Huang, Carnegie Mellon University
A Crowd-Powered Conversational Assistant That
Automates Itself Over Time
9. Live Note/QA: http://tinyurl.com/KenDefense
9 / 85
What just
happened?
• Open Conversation
• Multi-turn interaction
• Multiple domains
• Personalized
• Coherent dialog
• Mix of task-oriented
and social conversation
12. Live Note/QA: http://tinyurl.com/KenDefense
12 / 85
Existing Approaches to
Open Conversation
• Combining multiple automated dialog systems
• DialPort (Zhao, et al., 2016)
• End-to-end framework for dialogue systems
• Serban, et al. 2016; Li, et al. 2017
• Adapting a model to many other domains
• Walker, et al., 2007; Sun, et al., 2016
• Chit-chat systems (social bot)
• Hold social conversations (Banchs, et al., 2012)
• Still a very hard problem…
13. Live Note/QA: http://tinyurl.com/KenDefense
13 / 85
Existing Approaches to
Open Conversation
• Combining multiple task-oriented dialog systems
• DialPort (Zhao, et al., 2016)
• End-to-end framework for dialogue systems
• Serban, et al. 2016; Li, et al. 2017
• Adapting a model to many other domains
• Walker, et al., 2007; Sun, et al., 2016
• Chit-chat systems (social bot)
• Hold social conversations (Banchs, et al., 2012)
• Still a very hard problem…
MIT Technology Review
Feb 27, 2018
19. Live Note/QA: http://tinyurl.com/KenDefense
19 / 85
Thesis Statement
By allowing new chatbots to be easily integrated, reusing prior
crowd answers, and gradually reducing the crowd's role in
choosing high-quality responses,
a deployed crowd-powered dialog system can be automated
over time to support real-world open conversations.
20. Live Note/QA: http://tinyurl.com/KenDefense
20 / 85
Thesis Statement
By allowing new chatbots to be easily integrated, reusing prior
crowd answers, and gradually reducing the crowd's role in
choosing high-quality responses,
a deployed crowd-powered dialog system can be automated
over time to support real-world open conversations.
Chorus Deployment
[ HCOMP’16, HCOMP’17 ]
21. Live Note/QA: http://tinyurl.com/KenDefense
21 / 85
Thesis Statement
By allowing new chatbots to be easily integrated, reusing prior
crowd answers, and gradually reducing the crowd's role in
choosing high-quality responses,
a deployed crowd-powered dialog system can be automated
over time to support real-world open conversations.
Chorus Deployment Evorus
[ HCOMP’16, HCOMP’17 ] [ CHI’18 , UIST Poster’17 ]
22. Live Note/QA: http://tinyurl.com/KenDefense
22 / 85
Thesis Statement
By allowing new chatbots to be easily integrated, reusing prior
crowd answers, and gradually reducing the crowd's role in
choosing high-quality responses,
a deployed crowd-powered dialog system can be automated
over time to support real-world open conversations.
Chorus Deployment Evorus
Guardian
[ HCOMP’15, CI’17 ]
[ HCOMP’16, HCOMP’17 ] [ CHI’18 , UIST Poster’17 ]
30. Live Note/QA: http://tinyurl.com/KenDefense
30 / 85
female, computer science
PhD student in Texas
we're going to visit her this
weekend from Pittsburgh
She's in Austin
Does she have any
favorite TV shows,
movies, or video games?
U
Sure! What types of
things does your friend
like?
U
Can you suggest some
birthday present for one
of my friend?
30
Gift
Suggestion
31. Live Note/QA: http://tinyurl.com/KenDefense
31 / 85
female, computer science
PhD student in Texas
we're going to visit her this
weekend from Pittsburgh
She's in Austin
Does she have any
favorite TV shows,
movies, or video games?
U
Sure! What types of
things does your friend
like?
U
Can you suggest some
birthday present for one
of my friend?
31
Gift
Suggestion
32. Live Note/QA: http://tinyurl.com/KenDefense
32 / 85
female, computer science
PhD student in Texas
we're going to visit her this
weekend from Pittsburgh
She's in Austin
Does she have any
favorite TV shows,
movies, or video games?
U
Sure! What types of
things does your friend
like?
U
Can you suggest some
birthday present for one
of my friend?
32
Gift
Suggestion
33. Live Note/QA: http://tinyurl.com/KenDefense
33 / 85
Pittsburgh
with which company
are you flying?
U
Let me check
UHow many suitcases can I
take on a flight from the US
to Israel?
Can I ask you from where
are you planning to board
the flight?
and which air services
are you using?
Travel
Planning
Full transcript:
Huang, et al. HCOMP 2016.
34. Live Note/QA: http://tinyurl.com/KenDefense
34 / 85
What Did We Learn?
• Challenges Identified
• Malicious workers & users
• Identifying the end of a conversation
• When workers’ consensus is not enough…
• Basic Statistics
• Avg session duration = 10.63 min (SD=8.38)
• Avg #message per session = 25.87 (SD= 27.27)
Foundation for future automation!
35. Live Note/QA: http://tinyurl.com/KenDefense
35 / 85
Open Conversation
Personal
Assistants
AI-Powered
Dialog Systems
Automated
Crowd-Powered
Dialog Systems
Chorus Deployment
[ HCOMP’16, HCOMP’17 ]
36. Live Note/QA: http://tinyurl.com/KenDefense
36 / 85
Open Conversation
Personal
Assistants
AI-Powered
Dialog Systems
Automated
Crowd-Powered
Dialog Systems
Chorus Deployment
[ HCOMP’16, HCOMP’17 ]
47. Live Note/QA: http://tinyurl.com/KenDefense
47 / 85
Ranking Chatbots: Performance & Topic
Topic Similarity
User Message
Domain of
the Chatbot
Hey what should
I eat in Montreal?
Find me some
good restaurants !
Where can I get
Chinese food?
Example
Triggering
Message
≈
48. Live Note/QA: http://tinyurl.com/KenDefense
48 / 85
Ranking Chatbots: Performance & Topic
Topic Similarity
User Message
Domain of
the Chatbot
Hey what should
I eat in Montreal?
Example
Triggering
Message
Find me some
good restaurants !
Where can I get
Chinese food?
Topic
Similarity
≈
50. Live Note/QA: http://tinyurl.com/KenDefense
50 / 85
Ranking Chatbots: Performance & Topic
Chatbot’s
Performance
Topic Similarity
Posterior
of a
Chatbot
Add more chatbots over time !
≈
53. Live Note/QA: http://tinyurl.com/KenDefense
53 / 85
Find the Best Confidence Threshold
• High Threshold
• Only vote when pretty sure
• High precision, but little benefit
• Low Threshold
• Nearly always vote
• Grant agreement bonus by mistake
• Damage conversation quality
55. Live Note/QA: http://tinyurl.com/KenDefense
55 / 85
Automating Open Conversation
• Setup
• A 5-month-long deployment, 80 Users
• 4 chatbots + 1 voting bot
• Result
• Automated responses were chosen 12.44% of the time.
• Human upvotes were reduced by 13.81%.
• The cost of each message is reduced by 32.76%.
• Conversation quality and user
satisfaction level remains.
• Conversation Quality: Satisfaction,
Clarity, Responsiveness, Comfort
(Liu, et al., 2010)
56. Live Note/QA: http://tinyurl.com/KenDefense
56 / 85
Open Conversation
Personal
Assistants
AI-Powered
Dialog Systems
Automated
Crowd-Powered
Dialog Systems
Chorus Deployment
[ HCOMP’16, HCOMP’17 ]
Evorus
[ CHI’18 , UIST Poster’17 ]
57. Live Note/QA: http://tinyurl.com/KenDefense
57 / 85
Open Conversation
Personal
Assistants
AI-Powered
Dialog Systems
Automated
Crowd-Powered
Dialog Systems
Chorus Deployment
[ HCOMP’16, HCOMP’17 ]
Evorus
[ CHI’18 , UIST Poster’17 ]
63. Live Note/QA: http://tinyurl.com/KenDefense
63 / 85
Guardian: A Crowd-Powered Dialog System
for Web APIs
3
2 Dialog ManagementHi, I’m in San Diego.
Any Chinese restaurants here?
1 Language Understanding
Response Generation
Mandarin Wok Restaurant is
good ! It’s on 4227 Balboa Ave.
term = Chinese
location = San Diego
Yelp
Search
API 2.0
{ ... "name":
"Mandarin Wok
Restaurant”,...
"address":["4227
Balboa Ave”,...], …}
JSON
64. Live Note/QA: http://tinyurl.com/KenDefense
64 / 85
Parameter Extraction
offset
term
location
sw_latitude
sw_longitude
category_filter
accuracy
deals_filter
radius_filter
...
Hi, I’m in San Diego.
Any Chinese
restaurants here?
Parameters
Yelp
Search
API
User
65. Live Note/QA: http://tinyurl.com/KenDefense
65 / 85
Parameter Extraction
offset
term
location
sw_latitude
sw_longitude
category_filter
accuracy
deals_filter
radius_filter
...
Hi, I’m in San Diego.
Any Chinese
restaurants here?
Parameters
Yelp
Search
API
User
1. How to extract
parameters?
2. Which parameters
to use?
66. Live Note/QA: http://tinyurl.com/KenDefense
66 / 85
How to Extract Parameters?
offset
term
location
sw_latitude
sw_longitude
category_filter
accuracy
deals_filter
radius_filter
...
Hi, I’m in San Diego.
Any Chinese
restaurants here?
Parameters
Yelp
Search
API
User
1. How to extract
parameters?
2. Which parameters
to use?
67. Live Note/QA: http://tinyurl.com/KenDefense
67 / 85
Real-time On-Demand Crowd-powered Entity Extraction.
Huang, et al. Collective Intelligence 2017.
Crowd-Powered Parameter Extraction
Hi, I’m in San Diego.
Answer
Aggregate
Location =
San Diego
RecruitedPlayers
Time Constraint
(10 – 20 sec)
68. Live Note/QA: http://tinyurl.com/KenDefense
68 / 85
Which Parameters to Use?
offset
term
location
sw_latitude
sw_longitude
category_filter
accuracy
deals_filter
radius_filter
...
Hi, I’m in San Diego.
Any Chinese
restaurants here?
Parameters
Yelp
Search
API
User
1. How to extract
parameters?
2. Which parameters
to use?
69. Live Note/QA: http://tinyurl.com/KenDefense
69 / 85
Parameter Rating Problem
offset
term
location
sw_latitude
sw_longitude
category_filter
accuracy
deals_filter
radius_filter
...
offset
term
location
sw_latitude
sw_longitude
category_filter
accuracy
deals_filter
radius_filter
...
Pick good parameters for the dialog system.
71. Live Note/QA: http://tinyurl.com/KenDefense
71 / 85
Match Questions with Parameters
I like Chinese food.
What do you want to eat?
? !
I’m in Pittsburgh.
Which city are you in?
? !
Dinner.
Is it dinner or lunch?
? !
...
Yelp API
Question Collection
72. Live Note/QA: http://tinyurl.com/KenDefense
72 / 85
Match Questions with Parameters
offset
I like Chinese food.
What do you want to eat?
? !
I’m in Pittsburgh.
Which city are you in?
? !
Dinner.
Is it dinner or lunch?
? !
...
term
location
sw_latitude
sw_longitude
category_filter
Yelp API
Question Collection
Parameter Filtering
73. Live Note/QA: http://tinyurl.com/KenDefense
73 / 85
Match Questions with Parameters
offset
I like Chinese food.
What do you want to eat?
? !
I’m in Pittsburgh.
Which city are you in?
? !
Dinner.
Is it dinner or lunch?
? !
...
location
?
!
term
? !
!
?
!
? !
?
!
?
!
category_filter
? !
?
!
?
!
?
!
? !
?
!
? !
?
! ? !
? ! ? !
?
!
?
!
?
!
?
!
?
!
?
!?
!
? !
? !
? !
? !
? !? !
?
!
?
!
? !
? !? !
? !
? !
? !
?
!
? !
?
!
term
location
sw_latitude
sw_longitude
category_filter
BetterParameter
Yelp API
Question Collection
Parameter Filtering
Question-Parameter Matching
74. Live Note/QA: http://tinyurl.com/KenDefense
74 / 85
Evaluation on Parameter Ranking
0
0.2
0.4
0.6
0.8
1
MAP MRR
Question Matching
Ask Siri
Ask a Friend
• Average results of 8 Web APIs’ parameters
75. Live Note/QA: http://tinyurl.com/KenDefense
75 / 85
Guardian: A Crowd-Powered Dialog System
for Web APIs
3
2 Dialog ManagementHi, I’m in San Diego.
Any Chinese restaurants here?
1 Language Understanding
Response Generation
Mandarin Wok Restaurant is
good ! It’s on 4227 Balboa Ave.
term = Chinese
location = San Diego
Yelp
Search
API 2.0
{ ... "name":
"Mandarin Wok
Restaurant”,...
"address":["4227
Balboa Ave”,...], …}
JSON
76. Live Note/QA: http://tinyurl.com/KenDefense
76 / 85
Task
Find Chinese
restaurants in
Pittsburgh.
Check current weather
by using a zip code.
Find information
of “Titanic”.
API
Result
9 out of 10 9 out of 10 6 out of 10
Final
Response
10 out of 10 9 out of 10 10 out of 10
Evaluation: Task Completion Rate
Crowd Recover Errors Crowd Recover Errors
2
3
77. Live Note/QA: http://tinyurl.com/KenDefense
77 / 85
Open Conversation
Personal
Assistants
AI-Powered
Dialog Systems
Automated
Crowd-Powered
Dialog Systems
Chorus Deployment
[ HCOMP’16, HCOMP’17 ]
Evorus
[ CHI’18 , UIST Poster’17 ]
Guardian
[ HCOMP’15, CI’17 ]
78. Live Note/QA: http://tinyurl.com/KenDefense
78 / 85
Thesis Statement
By allowing new chatbots to be easily integrated, reusing prior
crowd answers, and gradually reducing the crowd's role in
choosing high-quality responses,
a deployed crowd-powered dialog system can be automated
over time to support real-world open conversations.
79. Live Note/QA: http://tinyurl.com/KenDefense
79 / 85
Thesis Statement
By allowing new chatbots to be easily integrated, reusing prior
crowd answers, and gradually reducing the crowd's role in
choosing high-quality responses,
a deployed crowd-powered dialog system can be automated
over time to support real-world open conversations.
Chorus Deployment Evorus
Guardian
[ HCOMP’15, CI’17 ]
[ HCOMP’16, HCOMP’17 ] [ CHI’18 , UIST Poster’17 ]
80. Live Note/QA: http://tinyurl.com/KenDefense
80 / 85
Some More Projects…
Ignition HCOMP’17
WearMail
Swaminathan et al. UIST’17
InstructableCrowd
CHI LBW’16, TOCHI (Under Review)
Visual Storytelling (VIST)
NAACL’16, Ferraro et al. EMNLP’15,
EmotionLines
Chen et al.,
LREC’18
81. Live Note/QA: http://tinyurl.com/KenDefense
81 / 85
Crowd Research is Critical
For Building Future Computer Systems.
• Collect data to guide AI models
• Accomplish tasks that are not yet fully automated
• Pave the way for future AI systems
82. Live Note/QA: http://tinyurl.com/KenDefense
82 / 85
Future Work
• Deployed Chorus as An Open Research Platform
Chorus API
1000+ chatbots
• Chorus on Smart Devices
Echo, Google Home…
• Future Crowd-AI Systems!
Object Recognition
Speech Recognition
Programming Tools
… And More!
83. Live Note/QA: http://tinyurl.com/KenDefense
83 / 85
Future Work
• Deployed Chorus as An Open Research Platform
Chorus API
1000+ chatbots
• Chorus on Smart Devices
Echo, Google Home…
• Future Crowd-AI Systems!
Object Recognition
Speech Recognition
Programming Tools
… And More!
84. Live Note/QA: http://tinyurl.com/KenDefense
84 / 85
Acknowledgment
• Family, Yan-Zhu (Lavender) Chen
• Jeffrey P. Bigham
• Walter S. Lasecki, Chris Callison-Burch, Alex Rudnicky, Margaret
Mitchell, Lun-Wei Ku, Hsin-Hsi Chen, Saiph Savage, Jane Hsu…
• Shoou-I Yu, Joseph Chee Chang, Chih-Yi (Jessica) Lin, Shihyun Lo,
Chu-Cheng Lin, Yun-Nung (Vivian) Chen, Lingpeng Kong, Luan Yi,
William Wang, Zi Yang, Yen-Chia Hsu, Kuen-Bang Hou (Favonia),
Kerry Shih-Ping Chang, Janet Huang, Yi-Chia Wang, Kai-min Kevin
Chang…
• Anhong Guo, Sai Ganesh, Kotaro Hara, Yashesh Gaur, Gierad Laput,
Robert Xiao, Yang Zhang, Patrick Carrington, Luz Rello, Cole Gleason,
Kristin Williams, Alex Chen, Susumu Saito…
• Amos Azaria, Oscar Romero Lopez…
• Stacey Young
We introduce the new approach to open conversation
We introduce the new approach to open conversation
We introduce the new approach to open conversation
We introduce the new approach to open conversation
We introduce the new approach to open conversation
Say some challenges of crowdsourcing system
Keep context
Malicious / Lazy workers
Dino-shape clear container
living tiny organisms
glow blue in dark
Dino-shape clear container
living tiny organisms
glow blue in dark
Dino-shape clear container
living tiny organisms
glow blue in dark
“Feasible” is weird. Maybe something else?
Telling a story
The key point of this part is that each chatbot doesn’t need to be perfect
If your think this it too abstract, we have a more concrete visulizaiton:
Let’s first take a look at the overview of the automation.
The way we are going to automate Chorus is to have Chorus incorperate with a big set of external dialog systesm, and gradually learn when to call them to obtain responses.
For instacne, (Yelp example)
Let’s first take a look at the overview of the automation.
The way we are going to automate Chorus is to have Chorus incorperate with a big set of external dialog systesm, and gradually learn when to call them to obtain responses.
For instacne, (Yelp example)
Working system from day 1
The comparison is shown in Figure 4(B). Moreover, an accepted non-user message sent by Evorus costed $0.142 in Phase-1 deployment on average, while it costed $0.211 during the Control Phase. Namely, with automated chatbots and the vote bot, the cost of each message is reduced by 32.76%.
Let’s first take a look at the overview of the automation.
The way we are going to automate Chorus is to have Chorus incorperate with a big set of external dialog systesm, and gradually learn when to call them to obtain responses.
For instacne, (Yelp example)
So the first question is: How to build a big set of external dialog systems quickly?
We think of Web APIs.
This page shows the ProgrammableWeb, a web site that collects Web APIs.
Nowadays, it contains 16 thousands of Web APIs.
We have a lot of them.
they are well-defined.
And a lot of them are even free.
We think of Web APIs.
This page shows the ProgrammableWeb, a web site that collects Web APIs.
Nowadays, it contains 16 thousands of Web APIs.
We have a lot of them.
they are well-defined.
And a lot of them are even free.
Guaridan’s framework contains three main steps:
First, the workers have a conversation with the user, and extract the parameter values with a dialog ESP Game.
Second, behind the scenes, the system will us these values to call the Yelp API and run the query.
Finally, when Yelp API returns the result, it’s in a JSON file. We also use the crowd to interpret the response.
We visualize the JSON file as a user friendly interface. The workers can click through the data and explore the information inside the JSON.
By using Guardian, we can have a running dialog system without using any training data or even pre-knowledge of task.
How to choose parameters?
We think of this problem as a Parameter Rating Problem.
Imagine you have a list of all parameters of Yelp API.
The task is to rate how good is each parameter for dialog systems.
The output is the rating score attached to each parameter, and thus you can have a ranking list of all parameters.
How to choose parameters?
We think of this problem as a Parameter Rating Problem.
Imagine you have a list of all parameters of Yelp API.
The task is to rate how good is each parameter for dialog systems.
The output is the rating score attached to each parameter, and thus you can have a ranking list of all parameters.
How to choose parameters?
We think of this problem as a Parameter Rating Problem.
Imagine you have a list of all parameters of Yelp API.
The task is to rate how good is each parameter for dialog systems.
The output is the rating score attached to each parameter, and thus you can have a ranking list of all parameters.
We propose a multi-player Dialog ESP Game to extract parameter values from a running conversation.
ESP Game is originally proposed for image labeling, now we adopt the idea to dialog.
In the interface, we show the dialog, we show the description of the parameter, and ask the workers to type what the other workers might type
If there are two answers matching with each other, we take it as the extracted parameter value.
This method works well. Now we can extract parameters without having any training data.
Therefore, based on all the works we’ve done, we propose a system called “Guardian”:
There are 2 ways to aagregate the answers.
How to choose parameters?
We think of this problem as a Parameter Rating Problem.
Imagine you have a list of all parameters of Yelp API.
The task is to rate how good is each parameter for dialog systems.
The output is the rating score attached to each parameter, and thus you can have a ranking list of all parameters.
How to choose parameters?
We think of this problem as a Parameter Rating Problem.
Imagine you have a list of all parameters of Yelp API.
The task is to rate how good is each parameter for dialog systems.
The output is the rating score attached to each parameter, and thus you can have a ranking list of all parameters.
As a crowdsourcing person, people would ask: Why don’t you just tell the crowd what you want and do a survey on each parameters?
So we did.
This is our interface. This survey is conducted on CrowdFlower.
For each parameter, we show the parameter name, parameter’s description, and the task of the API.
Then we ask the worker to imagine a scenario, and rate how likely you are going to provide the information of this parameter as a user.
To be more careful, we run experiment on three different scenarios.
First, ask Siri. Imagine you’re talking to Siri, how likely you’re going to provide this information?
Second, as a friend. Imagine you can not use Internet right now and call a friend for help, how likely you’re going to provide this information?
Third, we also ask the workers to rate how wired is the parameter, and use “Not Weird” as rating.
How does this work?
Like this!
The ideas we propose here is to collect questions related to this task, and then ask the workers use questions to vote for parameters.
Take the Yelp API for example, we first collect all possible questions from the crowd.
Like “what do you want to eat?”, “where are you?”, “What’s your budget?”and so on.
And then we ask workers to associate questions with parameters.
So essentially, the workers are using questions to vote for parameters.
We assume the parameters that are associated with more questions are better for dialog systems.
How does this work?
Like this!
The ideas we propose here is to collect questions related to this task, and then ask the workers use questions to vote for parameters.
Take the Yelp API for example, we first collect all possible questions from the crowd.
Like “what do you want to eat?”, “where are you?”, “What’s your budget?”and so on.
And then we ask workers to associate questions with parameters.
So essentially, the workers are using questions to vote for parameters.
We assume the parameters that are associated with more questions are better for dialog systems.
How does this work?
?/! -> Q/A
Like this!
The ideas we propose here is to collect questions related to this task, and then ask the workers use questions to vote for parameters.
Take the Yelp API for example, we first collect all possible questions from the crowd.
Like “what do you want to eat?”, “where are you?”, “What’s your budget?”and so on.
And then we ask workers to associate questions with parameters.
So essentially, the workers are using questions to vote for parameters.
We assume the parameters that are associated with more questions are better for dialog systems.
How does this work?
What does it mean to be better?! Retrieve parameters better than a friend
Other than question-matching approaching
It turned out our workflow outperforms all three baselines.
When you take a look at the result, you will know the quality is much better and close to practical use.
Guaridan’s framework contains three main steps:
First, the workers have a conversation with the user, and extract the parameter values with a dialog ESP Game.
Second, behind the scenes, the system will us these values to call the Yelp API and run the query.
Finally, when Yelp API returns the result, it’s in a JSON file. We also use the crowd to interpret the response.
We visualize the JSON file as a user friendly interface. The workers can click through the data and explore the information inside the JSON.
By using Guardian, we can have a running dialog system without using any training data or even pre-knowledge of task.
We implement the system on 3 different Web APIs.
Yelp API for restaurant search, Weather Underground API for weather query, and RottenTomatoes API for movie query.
We design three small tasks for each API, and run 10 trials on each systems.
Here we only talking about the task completion rate.
By task completion we mean the system provides the valid responses that contains the information the user requires.
You can see the task completion rate is almost perfect.
It’s because, first, the task here is relatively simple, second, even when the results returned from the API is incorrect, most of the time, crowd workers is able to figure it out the recover the correct answers.
We also compare our result with the task completion rate reported by literature.
The numbers are not directly comparable, but you can still see that our system reaches the same level of task completion rate with automated systems.
We introduce the new approach to open conversation
We introduce the new approach to open conversation
1. Leverage crowd wisdom to empower users to solve tasks which can not be solved by existing tech
2. Evorus demonstrates the potential of utilizing crowdsourced data as a scaffolding for training future AI systems
3. Pave the way for future AI systems to solve these problems
1. Leverage crowd wisdom to empower users to solve tasks which can not be solved by existing tech
2. Evorus demonstrates the potential of utilizing crowdsourced data as a scaffolding for training future AI systems
3. Pave the way for future AI systems to solve these problems