SlideShare a Scribd company logo
1 of 18
Download to read offline
Skill-based Conversational
Agent
Idris Yusupov, Yury Kuratov
i.yusupov@phystech.edu, yurii.kuratov@phystech.edu
Moscow Institute of Physics and Technology
Plan
1. Intro to Conversational Agents
2. The Conversational Intelligence Challenge @ NIPS (convai.io)
3. Skill-based Conversational Agent
What is Conversational Agent?
● Siri (Apple)
● Cortana (Microsoft)
● Alexa (Amazon)
● Chat-Bots (Telegram, Facebook messenger)
Two dimensions of Conversational Agents
Artificial Intelligence
Pizza Bot
Siri
ConvAI Bot
ConvAI (The Conversational Intelligence Challenge)
ConvAI
- 6 Teams (McGill, MIPT, University of Wroclaw, …)
- Human evaluation qualification round (July, 2017)
- 1st place: 2.386 of 5 (overall dialog quality)
- 2nd (Ours): 2.318 of 5
- Released dataset: http://convai.io/data/
- about 2k dialogs
- NIPS Final (December, 2017)
- Talk with bots and help to collect the data:
http://t.me/ConvaiBot
Conversation about the text
Conversation about the text
- Skill - narrow model.
- What skills are required to discuss the text?
- Question generation (factoid, common, …)
- Question answering (factoid, common, …)
- Chit-chat skill
- Summarization skill
- Personality skill (Name, birthday …)
- …
- Models for skills:
- Seq2Seq
- Retrieval models
- Templates
- Rules
- ...
Conversation about the text
- Finite state machine (FSM) to model the conversation
- Hard to maintain
Our approach
- Focus on skills implementation
What is done. Skills
- Seq2Seq, OpenNMT
- Question generation (SQuAD)
- Chit-chat (Facebook news)
- Chit-chat (Open Subtitles)
- Question Answering (BiDAF)
- Greeting skill
- Common questions asking skill
- Checking user answer correctness skill
What is done. Skill classifier
Evolution of skill classifier
● Baseline (done)
○ no conversational data
○ use classifier to select skills
● Model with scorer (in progress)
○ we have some data after human evaluation round
○ 2k dialogs (all bots)
○ we are mostly interested in our bot scores
● Model with improved scorer (to be done)
○ data from Mechanical Turk
What is done. Dialog evaluation scorer
- 2 evaluation scorers were built by using ConvAI human evaluation dataset
- Current utterance quality scorer: [context, utterance] => (poor, good)
- Word level GRU, sequence length is 50
- Overall dialog quality scorer: [overall dialog] => (poor, neutral, good)
- Word level GRU, sequence length is a whole dialog
Future work
● Improve classifier by using current utterance quality scorer
● Setup for human dialog evaluation (Amazon Mechanical Turk, Telegram)
● Bot with bot conversation using dialog scorer
● Improve skills
● New skills (summarization, retrieval based models)
Summary
- Skill: it is a narrow model (question generation/answerer, chit-chat, …)
- Conversational agent requires management of such skills
- Management can be done using FSM, but it is hard to maintain them
- Our approach helps to get rid of FSM and focus on skill implementation
- Main idea: use classifier which decides what skill to use
- Future work may lead to interesting results
- Talk with our Telegram bot here: https://t.me/IdrisConvaioTestBot
References
1. The Conversational Intelligence Challenge: http://convai.io/
2. Our bot: https://t.me/IdrisConvaioTestBot
3. Seo M. et al. Bidirectional attention flow for machine comprehension //arXiv preprint
arXiv:1611.01603. – 2016.
4. Zhou, Q., Yang, N., Wei, F., Tan, C., Bao, H., & Zhou, M. (2017). Neural Question Generation from
Text: A Preliminary Study. arXiv preprint arXiv:1704.01792.
5. Bordes, A., & Weston, J. (2016). Learning end-to-end goal-oriented dialog. arXiv preprint
arXiv:1605.07683.
6. Serban I. V. et al. A Deep Reinforcement Learning Chatbot //arXiv preprint arXiv:1709.02349. –
2017.
7. Lewis M. et al. Deal or No Deal? End-to-End Learning for Negotiation Dialogues //arXiv preprint
arXiv:1706.05125. – 2017.

More Related Content

Similar to Skill-based Conversational Agent

To Bot or Not: How Bots can Support Collaboration in Software Engineering (I...
To Bot or Not:  How Bots can Support Collaboration in Software Engineering (I...To Bot or Not:  How Bots can Support Collaboration in Software Engineering (I...
To Bot or Not: How Bots can Support Collaboration in Software Engineering (I...
Margaret-Anne Storey
 
Resume_PriyanshuSrivastava_20124064_CSE_12_7_2016
Resume_PriyanshuSrivastava_20124064_CSE_12_7_2016Resume_PriyanshuSrivastava_20124064_CSE_12_7_2016
Resume_PriyanshuSrivastava_20124064_CSE_12_7_2016
Priyanshu Srivastava
 
NLP BASED INTERVIEW ASSESSMENT SYSTEM
NLP BASED INTERVIEW ASSESSMENT SYSTEMNLP BASED INTERVIEW ASSESSMENT SYSTEM
NLP BASED INTERVIEW ASSESSMENT SYSTEM
vivatechijri
 

Similar to Skill-based Conversational Agent (20)

MINI PRC FINAL.pptx
MINI PRC FINAL.pptxMINI PRC FINAL.pptx
MINI PRC FINAL.pptx
 
IRJET- Information Chatbot for an Educational Institute
IRJET- Information Chatbot for an Educational InstituteIRJET- Information Chatbot for an Educational Institute
IRJET- Information Chatbot for an Educational Institute
 
VOCAL- Voice Command Application using Artificial Intelligence
VOCAL- Voice Command Application using Artificial IntelligenceVOCAL- Voice Command Application using Artificial Intelligence
VOCAL- Voice Command Application using Artificial Intelligence
 
IRJET- Multimedia Chatbot using Classification
IRJET- Multimedia Chatbot using ClassificationIRJET- Multimedia Chatbot using Classification
IRJET- Multimedia Chatbot using Classification
 
A Review Comparative Analysis On Various Chatbots Design
A Review   Comparative Analysis On Various Chatbots DesignA Review   Comparative Analysis On Various Chatbots Design
A Review Comparative Analysis On Various Chatbots Design
 
CHATBOT PPT-2.pptx
CHATBOT PPT-2.pptxCHATBOT PPT-2.pptx
CHATBOT PPT-2.pptx
 
Academic Integrity and Gen AI -Basic Concepts and Skills
Academic Integrity and Gen AI -Basic Concepts and SkillsAcademic Integrity and Gen AI -Basic Concepts and Skills
Academic Integrity and Gen AI -Basic Concepts and Skills
 
Deep Dialog System Review
Deep Dialog System ReviewDeep Dialog System Review
Deep Dialog System Review
 
IRJET- NEEV: An Education Informational Chatbot
IRJET-  	  NEEV: An Education Informational ChatbotIRJET-  	  NEEV: An Education Informational Chatbot
IRJET- NEEV: An Education Informational Chatbot
 
IRJET - Chat-Bot for College Information System using AI
IRJET -  	  Chat-Bot for College Information System using AIIRJET -  	  Chat-Bot for College Information System using AI
IRJET - Chat-Bot for College Information System using AI
 
Comparison GWAP Mechanical Turk
Comparison GWAP Mechanical TurkComparison GWAP Mechanical Turk
Comparison GWAP Mechanical Turk
 
Chat bot in_pythion
Chat bot in_pythionChat bot in_pythion
Chat bot in_pythion
 
IRJET- Recruitment Chatbot
IRJET- Recruitment ChatbotIRJET- Recruitment Chatbot
IRJET- Recruitment Chatbot
 
Dialogue system②
Dialogue system②Dialogue system②
Dialogue system②
 
IRJET- Chatbot using NLP and Deep Learning
IRJET-  	  Chatbot using NLP and Deep LearningIRJET-  	  Chatbot using NLP and Deep Learning
IRJET- Chatbot using NLP and Deep Learning
 
Student information chatbot final report
Student information chatbot  final report Student information chatbot  final report
Student information chatbot final report
 
IRJET- Artificial Intelligence Based Chat-Bot
IRJET-  	  Artificial Intelligence Based Chat-BotIRJET-  	  Artificial Intelligence Based Chat-Bot
IRJET- Artificial Intelligence Based Chat-Bot
 
To Bot or Not: How Bots can Support Collaboration in Software Engineering (I...
To Bot or Not:  How Bots can Support Collaboration in Software Engineering (I...To Bot or Not:  How Bots can Support Collaboration in Software Engineering (I...
To Bot or Not: How Bots can Support Collaboration in Software Engineering (I...
 
Resume_PriyanshuSrivastava_20124064_CSE_12_7_2016
Resume_PriyanshuSrivastava_20124064_CSE_12_7_2016Resume_PriyanshuSrivastava_20124064_CSE_12_7_2016
Resume_PriyanshuSrivastava_20124064_CSE_12_7_2016
 
NLP BASED INTERVIEW ASSESSMENT SYSTEM
NLP BASED INTERVIEW ASSESSMENT SYSTEMNLP BASED INTERVIEW ASSESSMENT SYSTEM
NLP BASED INTERVIEW ASSESSMENT SYSTEM
 

Recently uploaded

Recently uploaded (20)

Incident handling is a clearly defined set of procedures to manage and respon...
Incident handling is a clearly defined set of procedures to manage and respon...Incident handling is a clearly defined set of procedures to manage and respon...
Incident handling is a clearly defined set of procedures to manage and respon...
 
Spring into AI presented by Dan Vega 5/14
Spring into AI presented by Dan Vega 5/14Spring into AI presented by Dan Vega 5/14
Spring into AI presented by Dan Vega 5/14
 
CERVED e Neo4j su una nuvola, migrazione ed evoluzione di un grafo mission cr...
CERVED e Neo4j su una nuvola, migrazione ed evoluzione di un grafo mission cr...CERVED e Neo4j su una nuvola, migrazione ed evoluzione di un grafo mission cr...
CERVED e Neo4j su una nuvola, migrazione ed evoluzione di un grafo mission cr...
 
Abortion Pill Prices Germiston ](+27832195400*)[ 🏥 Women's Abortion Clinic in...
Abortion Pill Prices Germiston ](+27832195400*)[ 🏥 Women's Abortion Clinic in...Abortion Pill Prices Germiston ](+27832195400*)[ 🏥 Women's Abortion Clinic in...
Abortion Pill Prices Germiston ](+27832195400*)[ 🏥 Women's Abortion Clinic in...
 
GraphSummit Milan - Visione e roadmap del prodotto Neo4j
GraphSummit Milan - Visione e roadmap del prodotto Neo4jGraphSummit Milan - Visione e roadmap del prodotto Neo4j
GraphSummit Milan - Visione e roadmap del prodotto Neo4j
 
From Theory to Practice: Utilizing SpiraPlan's REST API
From Theory to Practice: Utilizing SpiraPlan's REST APIFrom Theory to Practice: Utilizing SpiraPlan's REST API
From Theory to Practice: Utilizing SpiraPlan's REST API
 
architecting-ai-in-the-enterprise-apis-and-applications.pdf
architecting-ai-in-the-enterprise-apis-and-applications.pdfarchitecting-ai-in-the-enterprise-apis-and-applications.pdf
architecting-ai-in-the-enterprise-apis-and-applications.pdf
 
A Deep Dive into Secure Product Development Frameworks.pdf
A Deep Dive into Secure Product Development Frameworks.pdfA Deep Dive into Secure Product Development Frameworks.pdf
A Deep Dive into Secure Product Development Frameworks.pdf
 
Weeding your micro service landscape.pdf
Weeding your micro service landscape.pdfWeeding your micro service landscape.pdf
Weeding your micro service landscape.pdf
 
From Knowledge Graphs via Lego Bricks to scientific conversations.pptx
From Knowledge Graphs via Lego Bricks to scientific conversations.pptxFrom Knowledge Graphs via Lego Bricks to scientific conversations.pptx
From Knowledge Graphs via Lego Bricks to scientific conversations.pptx
 
OpenChain Webinar: AboutCode and Beyond - End-to-End SCA
OpenChain Webinar: AboutCode and Beyond - End-to-End SCAOpenChain Webinar: AboutCode and Beyond - End-to-End SCA
OpenChain Webinar: AboutCode and Beyond - End-to-End SCA
 
Effective Strategies for Wix's Scaling challenges - GeeCon
Effective Strategies for Wix's Scaling challenges - GeeConEffective Strategies for Wix's Scaling challenges - GeeCon
Effective Strategies for Wix's Scaling challenges - GeeCon
 
BusinessGPT - Security and Governance for Generative AI
BusinessGPT  - Security and Governance for Generative AIBusinessGPT  - Security and Governance for Generative AI
BusinessGPT - Security and Governance for Generative AI
 
Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024
Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024
Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024
 
Modern binary build systems - PyCon 2024
Modern binary build systems - PyCon 2024Modern binary build systems - PyCon 2024
Modern binary build systems - PyCon 2024
 
[GeeCON2024] How I learned to stop worrying and love the dark silicon apocalypse
[GeeCON2024] How I learned to stop worrying and love the dark silicon apocalypse[GeeCON2024] How I learned to stop worrying and love the dark silicon apocalypse
[GeeCON2024] How I learned to stop worrying and love the dark silicon apocalypse
 
The mythical technical debt. (Brooke, please, forgive me)
The mythical technical debt. (Brooke, please, forgive me)The mythical technical debt. (Brooke, please, forgive me)
The mythical technical debt. (Brooke, please, forgive me)
 
UNI DI NAPOLI FEDERICO II - Il ruolo dei grafi nell'AI Conversazionale Ibrida
UNI DI NAPOLI FEDERICO II - Il ruolo dei grafi nell'AI Conversazionale IbridaUNI DI NAPOLI FEDERICO II - Il ruolo dei grafi nell'AI Conversazionale Ibrida
UNI DI NAPOLI FEDERICO II - Il ruolo dei grafi nell'AI Conversazionale Ibrida
 
Abortion Pill Prices Mthatha (@](+27832195400*)[ 🏥 Women's Abortion Clinic In...
Abortion Pill Prices Mthatha (@](+27832195400*)[ 🏥 Women's Abortion Clinic In...Abortion Pill Prices Mthatha (@](+27832195400*)[ 🏥 Women's Abortion Clinic In...
Abortion Pill Prices Mthatha (@](+27832195400*)[ 🏥 Women's Abortion Clinic In...
 
Encryption Recap: A Refresher on Key Concepts
Encryption Recap: A Refresher on Key ConceptsEncryption Recap: A Refresher on Key Concepts
Encryption Recap: A Refresher on Key Concepts
 

Skill-based Conversational Agent

  • 1. Skill-based Conversational Agent Idris Yusupov, Yury Kuratov i.yusupov@phystech.edu, yurii.kuratov@phystech.edu Moscow Institute of Physics and Technology
  • 2. Plan 1. Intro to Conversational Agents 2. The Conversational Intelligence Challenge @ NIPS (convai.io) 3. Skill-based Conversational Agent
  • 3. What is Conversational Agent? ● Siri (Apple) ● Cortana (Microsoft) ● Alexa (Amazon) ● Chat-Bots (Telegram, Facebook messenger)
  • 4. Two dimensions of Conversational Agents Artificial Intelligence Pizza Bot Siri ConvAI Bot
  • 5. ConvAI (The Conversational Intelligence Challenge)
  • 6. ConvAI - 6 Teams (McGill, MIPT, University of Wroclaw, …) - Human evaluation qualification round (July, 2017) - 1st place: 2.386 of 5 (overall dialog quality) - 2nd (Ours): 2.318 of 5 - Released dataset: http://convai.io/data/ - about 2k dialogs - NIPS Final (December, 2017) - Talk with bots and help to collect the data: http://t.me/ConvaiBot
  • 7.
  • 9. Conversation about the text - Skill - narrow model. - What skills are required to discuss the text? - Question generation (factoid, common, …) - Question answering (factoid, common, …) - Chit-chat skill - Summarization skill - Personality skill (Name, birthday …) - … - Models for skills: - Seq2Seq - Retrieval models - Templates - Rules - ...
  • 10. Conversation about the text - Finite state machine (FSM) to model the conversation - Hard to maintain
  • 11. Our approach - Focus on skills implementation
  • 12. What is done. Skills - Seq2Seq, OpenNMT - Question generation (SQuAD) - Chit-chat (Facebook news) - Chit-chat (Open Subtitles) - Question Answering (BiDAF) - Greeting skill - Common questions asking skill - Checking user answer correctness skill
  • 13. What is done. Skill classifier
  • 14. Evolution of skill classifier ● Baseline (done) ○ no conversational data ○ use classifier to select skills ● Model with scorer (in progress) ○ we have some data after human evaluation round ○ 2k dialogs (all bots) ○ we are mostly interested in our bot scores ● Model with improved scorer (to be done) ○ data from Mechanical Turk
  • 15. What is done. Dialog evaluation scorer - 2 evaluation scorers were built by using ConvAI human evaluation dataset - Current utterance quality scorer: [context, utterance] => (poor, good) - Word level GRU, sequence length is 50 - Overall dialog quality scorer: [overall dialog] => (poor, neutral, good) - Word level GRU, sequence length is a whole dialog
  • 16. Future work ● Improve classifier by using current utterance quality scorer ● Setup for human dialog evaluation (Amazon Mechanical Turk, Telegram) ● Bot with bot conversation using dialog scorer ● Improve skills ● New skills (summarization, retrieval based models)
  • 17. Summary - Skill: it is a narrow model (question generation/answerer, chit-chat, …) - Conversational agent requires management of such skills - Management can be done using FSM, but it is hard to maintain them - Our approach helps to get rid of FSM and focus on skill implementation - Main idea: use classifier which decides what skill to use - Future work may lead to interesting results - Talk with our Telegram bot here: https://t.me/IdrisConvaioTestBot
  • 18. References 1. The Conversational Intelligence Challenge: http://convai.io/ 2. Our bot: https://t.me/IdrisConvaioTestBot 3. Seo M. et al. Bidirectional attention flow for machine comprehension //arXiv preprint arXiv:1611.01603. – 2016. 4. Zhou, Q., Yang, N., Wei, F., Tan, C., Bao, H., & Zhou, M. (2017). Neural Question Generation from Text: A Preliminary Study. arXiv preprint arXiv:1704.01792. 5. Bordes, A., & Weston, J. (2016). Learning end-to-end goal-oriented dialog. arXiv preprint arXiv:1605.07683. 6. Serban I. V. et al. A Deep Reinforcement Learning Chatbot //arXiv preprint arXiv:1709.02349. – 2017. 7. Lewis M. et al. Deal or No Deal? End-to-End Learning for Negotiation Dialogues //arXiv preprint arXiv:1706.05125. – 2017.