SlideShare a Scribd company logo
1 of 31
• Dialog Management System
• Dialog Manager
• Dialog Management Technologies
• Main features in Ravenclaw
• 2-tier architecture
• Dialog Task Specification
• Dialog Agents
• Agent Behavior
• Concept
• DTS in Ravenclaw
• Hierarchical Plan-based representation
• Core Algorithm
• Execute Phase
• Stack & Tree
• Input phase
• Expectation agenda
• Mixed initiative
• Control the amount of initiative
• Context-based semantic disambigution
• Error handling
Dialog Management System
• determines the next system action with
– Current semantic input
– Current dialog state
– Information about the task
• more-complex model
– Timing, turn-taking
– Barge-ins, backchannels,
multi-participant conversation
– Error handling
– Various appropriate requests
Dialog Manager
• Finite-state dialog manager
• Form-filling (frame-based) dialog manager
• Plan-based dialog manager (RavenClaw)
– Model the goals of the conversation
– Guide the dialog along the path
towards these goals
Dialog Management Technologies
• Task-independence
– Clear separation between
– the domain-specific aspects of the dialog control l
ogic
– And domain-independent
– Reusable dialog control mechanism
• Flexibility
• Scalability
• Transparency
• Modularity
• …
Main features in RavenClaw
2-tier architecture
• DTS(Dialog Task Specification)
– Covers domain specific aspects
– Describes hierarchical plan
– Consist of a tree of dialog agents
Dialog Task Specification
• Types
• Inform
–Generate output(e.g. greeting)
• Request
–Request information
–Collect the user’s response
• Expect
–Expect information from user
• Execute
–Database access
–Api calls
–Etc
• Dialog Agencies
• Planning the execution of their sub-agents
Dialog Agents
• Execute routine
– Basic operations of each agent(4 types)
• Additional configuration for agent/agency
– Precondition
– Trigger
– Success/fail criteria
Agent Behavior
Concept
• Type
– Boolean, string, integer, float, structure, array
• Value/Confidence
– Ex. City_name = {Boston/0.35, Austin/0.27}
– Due to speech recognition error
– Not used in our Chatbot
• Information(value) maintained in scenario
– History of previous values
– Grounding state
– …
Concept
DTS in RavenClaw
Described in DialogTask.cpp with MACRO
DTS in RavenClaw
• No fixed order
– Depends on user input,
encoded domain constraint,
task logic and various execution policies
• Hierarchical plan-based representation
– Most goal-oriented dialog tasks have a naturally
hierarchical structure
– Sub-components are independent
Ease in design, maintenance, scalability and reusability
– Can be extended at run time
Allow for the dynamic construction
Hierarchical Plan-based representation
• 2 data structures
– Dialog stack
– Expectation agenda
• 2 phase
– Execution phase
– Input phase
Core Algorithm
Execute Phase
• Execute agent on top of the stack
– Inform agent : output system prompt
– Request agent – output system prompt  input phase
– Expect agent – do nothing(just expect)
– Execute agent – call APIs
– Agency – push one of subagents on the dialog stack
• Eliminate completed agents from stack
– If the completion condition is meet.
• Push focus claiming agents on stack
– Inspects the focus claims(trigger) conditions.
Execute Phase
• Dialog Stack
– Temporal and hierarchical structure of the discourse
• Tree(DTS)
– Hierarchical goal structure of the task
• Isomorphism between stack and tree
– Sometimes broken when focus shifts
If trigger condition meets, push the agent on the
stack Isomorphism will be maintained
after focus claimed agents finish
Stack & Tree
• Only in Request agent
– Assemble the expectation agenda
• Waits for an user input
– Thread blocked until user input
• Update concept (concept binding)
– Top-down traversal of the expectation agenda
Input phase
Input phase
• Data-structure that describes
what the system expects to hear from the
user in the current turn
– Advantages
Allow over-answer
Mixed-initiative interaction
Automatically performs context-based semantic
disambiguation
Dynamic state-specific language modeling
Expectation agenda
Mixed initiative
• Focus claim if agenda is open.
• By default, open only when under the sam
e topic
– If main topic is set, child agent(agency) can be
focus-shifted.
앞의 예제에서 Hotels가 main topic으로 설정되어
있었다면, focus shift가 되지 않음.
• Expectation scope operators
– ! – open if expectation == focus
– * - always open
– @ - open if agents which are listed
after @ == focus
Control the amount of initiative
Context-based semantic disambiguation
• State/context-specific language model
• Level-based organization of
expectation agenda provides additional
information
• But NOT yet implemented
in RavenClaw engine
Dynamic state-specific language modeling
• Speech recognition and
language understanding
– Still far from perfect
– Non-understanding & misunderstanding
• Domain-independent error handling
– Various advantages
Error handling
• No speech recognition in chatbot
– No confidence level
• No explicit error decision process
In Chatbot
• Data flow
• Message  NLU  DM  NLG  Message
NLU  DM  NLG
DTS – json format
• Original RavenClaw is c-based.
– DTS  JSONize
– RavenClaw engine : c  python
• New classes
• New properties
Customize

More Related Content

Similar to Commerce chatbot - dialog manager

Modern MySQL Monitoring and Dashboards.
Modern MySQL Monitoring and Dashboards.Modern MySQL Monitoring and Dashboards.
Modern MySQL Monitoring and Dashboards.Mydbops
 
Alfresco Business Reporting - Tech Talk Live 20130501
Alfresco Business Reporting - Tech Talk Live 20130501Alfresco Business Reporting - Tech Talk Live 20130501
Alfresco Business Reporting - Tech Talk Live 20130501Tjarda Peelen
 
It Positions September 2010
It Positions September 2010It Positions September 2010
It Positions September 2010ioanatot
 
Indic threads pune12-typesafe stack software development on the jvm
Indic threads pune12-typesafe stack software development on the jvmIndic threads pune12-typesafe stack software development on the jvm
Indic threads pune12-typesafe stack software development on the jvmIndicThreads
 
The Evolution of a Relational Database Layer over HBase
The Evolution of a Relational Database Layer over HBaseThe Evolution of a Relational Database Layer over HBase
The Evolution of a Relational Database Layer over HBaseDataWorks Summit
 
A Practical Guide to Selecting a Stream Processing Technology
A Practical Guide to Selecting a Stream Processing Technology A Practical Guide to Selecting a Stream Processing Technology
A Practical Guide to Selecting a Stream Processing Technology confluent
 
Policy 2012 presentation
Policy 2012 presentationPolicy 2012 presentation
Policy 2012 presentationbdemchak
 
Process Orchestration with Flowable and Spring Boot
Process Orchestration with Flowable and Spring BootProcess Orchestration with Flowable and Spring Boot
Process Orchestration with Flowable and Spring BootChavdar Baikov
 
Real world RESTful service development problems and solutions
Real world RESTful service development problems and solutionsReal world RESTful service development problems and solutions
Real world RESTful service development problems and solutionsMasoud Kalali
 
Embedded 100912065920-phpapp02
Embedded 100912065920-phpapp02Embedded 100912065920-phpapp02
Embedded 100912065920-phpapp02Atv Reddy
 
Embedded 100912065920-phpapp02
Embedded 100912065920-phpapp02Embedded 100912065920-phpapp02
Embedded 100912065920-phpapp02Atv Reddy
 
GE IOT Predix Time Series & Data Ingestion Service using Apache Apex (Hadoop)
GE IOT Predix Time Series & Data Ingestion Service using Apache Apex (Hadoop)GE IOT Predix Time Series & Data Ingestion Service using Apache Apex (Hadoop)
GE IOT Predix Time Series & Data Ingestion Service using Apache Apex (Hadoop)Apache Apex
 
Stateful Interaction In Serverless Architecture With Redis: Pyounguk Cho
Stateful Interaction In Serverless Architecture With Redis: Pyounguk ChoStateful Interaction In Serverless Architecture With Redis: Pyounguk Cho
Stateful Interaction In Serverless Architecture With Redis: Pyounguk ChoRedis Labs
 
Apache Tez – Present and Future
Apache Tez – Present and FutureApache Tez – Present and Future
Apache Tez – Present and FutureJianfeng Zhang
 
Apache Tez – Present and Future
Apache Tez – Present and FutureApache Tez – Present and Future
Apache Tez – Present and FutureRajesh Balamohan
 
PPT-UEU-Database-Objek-Terdistribusi-Pertemuan-8.pptx
PPT-UEU-Database-Objek-Terdistribusi-Pertemuan-8.pptxPPT-UEU-Database-Objek-Terdistribusi-Pertemuan-8.pptx
PPT-UEU-Database-Objek-Terdistribusi-Pertemuan-8.pptxneju3
 

Similar to Commerce chatbot - dialog manager (20)

Modern MySQL Monitoring and Dashboards.
Modern MySQL Monitoring and Dashboards.Modern MySQL Monitoring and Dashboards.
Modern MySQL Monitoring and Dashboards.
 
Resume_Admin
Resume_AdminResume_Admin
Resume_Admin
 
Alfresco Business Reporting - Tech Talk Live 20130501
Alfresco Business Reporting - Tech Talk Live 20130501Alfresco Business Reporting - Tech Talk Live 20130501
Alfresco Business Reporting - Tech Talk Live 20130501
 
It Positions September 2010
It Positions September 2010It Positions September 2010
It Positions September 2010
 
Indic threads pune12-typesafe stack software development on the jvm
Indic threads pune12-typesafe stack software development on the jvmIndic threads pune12-typesafe stack software development on the jvm
Indic threads pune12-typesafe stack software development on the jvm
 
The Evolution of a Relational Database Layer over HBase
The Evolution of a Relational Database Layer over HBaseThe Evolution of a Relational Database Layer over HBase
The Evolution of a Relational Database Layer over HBase
 
A Practical Guide to Selecting a Stream Processing Technology
A Practical Guide to Selecting a Stream Processing Technology A Practical Guide to Selecting a Stream Processing Technology
A Practical Guide to Selecting a Stream Processing Technology
 
L19 Application Architecture
L19 Application ArchitectureL19 Application Architecture
L19 Application Architecture
 
Policy 2012 presentation
Policy 2012 presentationPolicy 2012 presentation
Policy 2012 presentation
 
Process Orchestration with Flowable and Spring Boot
Process Orchestration with Flowable and Spring BootProcess Orchestration with Flowable and Spring Boot
Process Orchestration with Flowable and Spring Boot
 
Real world RESTful service development problems and solutions
Real world RESTful service development problems and solutionsReal world RESTful service development problems and solutions
Real world RESTful service development problems and solutions
 
Embedded 100912065920-phpapp02
Embedded 100912065920-phpapp02Embedded 100912065920-phpapp02
Embedded 100912065920-phpapp02
 
Embedded 100912065920-phpapp02
Embedded 100912065920-phpapp02Embedded 100912065920-phpapp02
Embedded 100912065920-phpapp02
 
L11 Application Architecture
L11 Application ArchitectureL11 Application Architecture
L11 Application Architecture
 
GE IOT Predix Time Series & Data Ingestion Service using Apache Apex (Hadoop)
GE IOT Predix Time Series & Data Ingestion Service using Apache Apex (Hadoop)GE IOT Predix Time Series & Data Ingestion Service using Apache Apex (Hadoop)
GE IOT Predix Time Series & Data Ingestion Service using Apache Apex (Hadoop)
 
Mule SAP connector
Mule SAP connectorMule SAP connector
Mule SAP connector
 
Stateful Interaction In Serverless Architecture With Redis: Pyounguk Cho
Stateful Interaction In Serverless Architecture With Redis: Pyounguk ChoStateful Interaction In Serverless Architecture With Redis: Pyounguk Cho
Stateful Interaction In Serverless Architecture With Redis: Pyounguk Cho
 
Apache Tez – Present and Future
Apache Tez – Present and FutureApache Tez – Present and Future
Apache Tez – Present and Future
 
Apache Tez – Present and Future
Apache Tez – Present and FutureApache Tez – Present and Future
Apache Tez – Present and Future
 
PPT-UEU-Database-Objek-Terdistribusi-Pertemuan-8.pptx
PPT-UEU-Database-Objek-Terdistribusi-Pertemuan-8.pptxPPT-UEU-Database-Objek-Terdistribusi-Pertemuan-8.pptx
PPT-UEU-Database-Objek-Terdistribusi-Pertemuan-8.pptx
 

More from HoChul Shin

Commerce chatbot - 실습
Commerce chatbot - 실습Commerce chatbot - 실습
Commerce chatbot - 실습HoChul Shin
 
Commerce chatbot - 11번가 대화형 커머스 챗봇 적용 사례
Commerce chatbot - 11번가 대화형 커머스 챗봇 적용 사례Commerce chatbot - 11번가 대화형 커머스 챗봇 적용 사례
Commerce chatbot - 11번가 대화형 커머스 챗봇 적용 사례HoChul Shin
 
ML + 주식 phase 2
ML + 주식  phase 2ML + 주식  phase 2
ML + 주식 phase 2HoChul Shin
 
머신러닝 + 주식 삽질기
머신러닝 + 주식 삽질기머신러닝 + 주식 삽질기
머신러닝 + 주식 삽질기HoChul Shin
 
부동산 텔레그램봇 사내공유 @Tech
부동산 텔레그램봇 사내공유 @Tech부동산 텔레그램봇 사내공유 @Tech
부동산 텔레그램봇 사내공유 @TechHoChul Shin
 
부동산 텔레그램 봇
부동산 텔레그램 봇부동산 텔레그램 봇
부동산 텔레그램 봇HoChul Shin
 
Node.js DBMS short summary
Node.js DBMS short summaryNode.js DBMS short summary
Node.js DBMS short summaryHoChul Shin
 
Python3 brief summary
Python3 brief summaryPython3 brief summary
Python3 brief summaryHoChul Shin
 

More from HoChul Shin (9)

Commerce chatbot - 실습
Commerce chatbot - 실습Commerce chatbot - 실습
Commerce chatbot - 실습
 
Commerce chatbot - 11번가 대화형 커머스 챗봇 적용 사례
Commerce chatbot - 11번가 대화형 커머스 챗봇 적용 사례Commerce chatbot - 11번가 대화형 커머스 챗봇 적용 사례
Commerce chatbot - 11번가 대화형 커머스 챗봇 적용 사례
 
ML + 주식 phase 2
ML + 주식  phase 2ML + 주식  phase 2
ML + 주식 phase 2
 
머신러닝 + 주식 삽질기
머신러닝 + 주식 삽질기머신러닝 + 주식 삽질기
머신러닝 + 주식 삽질기
 
부동산 텔레그램봇 사내공유 @Tech
부동산 텔레그램봇 사내공유 @Tech부동산 텔레그램봇 사내공유 @Tech
부동산 텔레그램봇 사내공유 @Tech
 
부동산 텔레그램 봇
부동산 텔레그램 봇부동산 텔레그램 봇
부동산 텔레그램 봇
 
Node.js DBMS short summary
Node.js DBMS short summaryNode.js DBMS short summary
Node.js DBMS short summary
 
Python3 brief summary
Python3 brief summaryPython3 brief summary
Python3 brief summary
 
Lua vs python
Lua vs pythonLua vs python
Lua vs python
 

Recently uploaded

SHRMPro HRMS Software Solutions Presentation
SHRMPro HRMS Software Solutions PresentationSHRMPro HRMS Software Solutions Presentation
SHRMPro HRMS Software Solutions PresentationShrmpro
 
Announcing Codolex 2.0 from GDK Software
Announcing Codolex 2.0 from GDK SoftwareAnnouncing Codolex 2.0 from GDK Software
Announcing Codolex 2.0 from GDK SoftwareJim McKeeth
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️Delhi Call girls
 
10 Trends Likely to Shape Enterprise Technology in 2024
10 Trends Likely to Shape Enterprise Technology in 202410 Trends Likely to Shape Enterprise Technology in 2024
10 Trends Likely to Shape Enterprise Technology in 2024Mind IT Systems
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrainmasabamasaba
 
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...Health
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsArshad QA
 
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...masabamasaba
 
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdf
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdfintroduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdf
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdfVishalKumarJha10
 
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfonteinmasabamasaba
 
AI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplateAI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplatePresentation.STUDIO
 
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...masabamasaba
 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...Shane Coughlan
 
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdfPayment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdfkalichargn70th171
 
The title is not connected to what is inside
The title is not connected to what is insideThe title is not connected to what is inside
The title is not connected to what is insideshinachiaurasa2
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisamasabamasaba
 
%in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park %in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park masabamasaba
 
8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech students8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech studentsHimanshiGarg82
 
%in Durban+277-882-255-28 abortion pills for sale in Durban
%in Durban+277-882-255-28 abortion pills for sale in Durban%in Durban+277-882-255-28 abortion pills for sale in Durban
%in Durban+277-882-255-28 abortion pills for sale in Durbanmasabamasaba
 

Recently uploaded (20)

SHRMPro HRMS Software Solutions Presentation
SHRMPro HRMS Software Solutions PresentationSHRMPro HRMS Software Solutions Presentation
SHRMPro HRMS Software Solutions Presentation
 
Announcing Codolex 2.0 from GDK Software
Announcing Codolex 2.0 from GDK SoftwareAnnouncing Codolex 2.0 from GDK Software
Announcing Codolex 2.0 from GDK Software
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
 
10 Trends Likely to Shape Enterprise Technology in 2024
10 Trends Likely to Shape Enterprise Technology in 202410 Trends Likely to Shape Enterprise Technology in 2024
10 Trends Likely to Shape Enterprise Technology in 2024
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
 
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview Questions
 
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
 
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdf
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdfintroduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdf
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdf
 
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
 
AI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplateAI & Machine Learning Presentation Template
AI & Machine Learning Presentation Template
 
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
 
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdfPayment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
 
The title is not connected to what is inside
The title is not connected to what is insideThe title is not connected to what is inside
The title is not connected to what is inside
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
 
%in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park %in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park
 
8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech students8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech students
 
%in Durban+277-882-255-28 abortion pills for sale in Durban
%in Durban+277-882-255-28 abortion pills for sale in Durban%in Durban+277-882-255-28 abortion pills for sale in Durban
%in Durban+277-882-255-28 abortion pills for sale in Durban
 

Commerce chatbot - dialog manager

  • 1.
  • 2. • Dialog Management System • Dialog Manager • Dialog Management Technologies • Main features in Ravenclaw • 2-tier architecture • Dialog Task Specification • Dialog Agents • Agent Behavior • Concept • DTS in Ravenclaw • Hierarchical Plan-based representation • Core Algorithm • Execute Phase • Stack & Tree • Input phase • Expectation agenda • Mixed initiative • Control the amount of initiative • Context-based semantic disambigution • Error handling
  • 4. • determines the next system action with – Current semantic input – Current dialog state – Information about the task • more-complex model – Timing, turn-taking – Barge-ins, backchannels, multi-participant conversation – Error handling – Various appropriate requests Dialog Manager
  • 5. • Finite-state dialog manager • Form-filling (frame-based) dialog manager • Plan-based dialog manager (RavenClaw) – Model the goals of the conversation – Guide the dialog along the path towards these goals Dialog Management Technologies
  • 6. • Task-independence – Clear separation between – the domain-specific aspects of the dialog control l ogic – And domain-independent – Reusable dialog control mechanism • Flexibility • Scalability • Transparency • Modularity • … Main features in RavenClaw
  • 8. • DTS(Dialog Task Specification) – Covers domain specific aspects – Describes hierarchical plan – Consist of a tree of dialog agents Dialog Task Specification
  • 9. • Types • Inform –Generate output(e.g. greeting) • Request –Request information –Collect the user’s response • Expect –Expect information from user • Execute –Database access –Api calls –Etc • Dialog Agencies • Planning the execution of their sub-agents Dialog Agents
  • 10. • Execute routine – Basic operations of each agent(4 types) • Additional configuration for agent/agency – Precondition – Trigger – Success/fail criteria Agent Behavior
  • 12. • Type – Boolean, string, integer, float, structure, array • Value/Confidence – Ex. City_name = {Boston/0.35, Austin/0.27} – Due to speech recognition error – Not used in our Chatbot • Information(value) maintained in scenario – History of previous values – Grounding state – … Concept
  • 14. Described in DialogTask.cpp with MACRO DTS in RavenClaw
  • 15. • No fixed order – Depends on user input, encoded domain constraint, task logic and various execution policies • Hierarchical plan-based representation – Most goal-oriented dialog tasks have a naturally hierarchical structure – Sub-components are independent Ease in design, maintenance, scalability and reusability – Can be extended at run time Allow for the dynamic construction Hierarchical Plan-based representation
  • 16. • 2 data structures – Dialog stack – Expectation agenda • 2 phase – Execution phase – Input phase Core Algorithm
  • 18. • Execute agent on top of the stack – Inform agent : output system prompt – Request agent – output system prompt  input phase – Expect agent – do nothing(just expect) – Execute agent – call APIs – Agency – push one of subagents on the dialog stack • Eliminate completed agents from stack – If the completion condition is meet. • Push focus claiming agents on stack – Inspects the focus claims(trigger) conditions. Execute Phase
  • 19. • Dialog Stack – Temporal and hierarchical structure of the discourse • Tree(DTS) – Hierarchical goal structure of the task • Isomorphism between stack and tree – Sometimes broken when focus shifts If trigger condition meets, push the agent on the stack Isomorphism will be maintained after focus claimed agents finish Stack & Tree
  • 20. • Only in Request agent – Assemble the expectation agenda • Waits for an user input – Thread blocked until user input • Update concept (concept binding) – Top-down traversal of the expectation agenda Input phase
  • 22. • Data-structure that describes what the system expects to hear from the user in the current turn – Advantages Allow over-answer Mixed-initiative interaction Automatically performs context-based semantic disambiguation Dynamic state-specific language modeling Expectation agenda
  • 24. • Focus claim if agenda is open. • By default, open only when under the sam e topic – If main topic is set, child agent(agency) can be focus-shifted. 앞의 예제에서 Hotels가 main topic으로 설정되어 있었다면, focus shift가 되지 않음. • Expectation scope operators – ! – open if expectation == focus – * - always open – @ - open if agents which are listed after @ == focus Control the amount of initiative
  • 26. • State/context-specific language model • Level-based organization of expectation agenda provides additional information • But NOT yet implemented in RavenClaw engine Dynamic state-specific language modeling
  • 27. • Speech recognition and language understanding – Still far from perfect – Non-understanding & misunderstanding • Domain-independent error handling – Various advantages Error handling
  • 28. • No speech recognition in chatbot – No confidence level • No explicit error decision process In Chatbot
  • 29. • Data flow • Message  NLU  DM  NLG  Message NLU  DM  NLG
  • 30. DTS – json format
  • 31. • Original RavenClaw is c-based. – DTS  JSONize – RavenClaw engine : c  python • New classes • New properties Customize