SlideShare ist ein Scribd-Unternehmen logo
1 von 28
Downloaden Sie, um offline zu lesen
DIALOG STRATEGY MANAGEMENT IN
MULTISKILL AI ASSISTANTS WITH
DISCOURSE MANAGEMENT
Daniel Kornev, Chief Product Officer, DeepPavlov.ai
Step 1
Dialog Management is complex
Correctly identify user’s utterance’s goal
Step 2 Correctly generate response(s)
Step 3 Correctly pick the best response
Alice: what’s happened in city hall?
Bot: [Which city hall [Entity Disambiguation]? Where (NYC | Local)? When (Today | Yesterday | at some time)?]
Domain:News: Occupy City Hall happened in July 2020 | Confidence: 0.85
Domain:Factoid: City Hall is the seat of New York City government | Confidence: 0.95
Retrieval: By 1969 City Hall was described as badly crowded because of Bellevue growing … | Confidence: 0.75
Alice: What’s happened in city hall?
Bot: City Hall is the seat of New York City government
DeepPavlov.ai
Dialog Manager was predominantly tactical (single-turn, reactive):
User
•Let’s chat
Bot
•(greeting)
(question)
User
•[utterance]
Bot
•[utterance]
User
•[utterance]
Bot
•[utterance]
User
•[utterance]
Bot
•[utterance]
Skill #1 Skill #2 Skill #3 Skill #4
Pros: Retrieval skills helped us to cover lots of societal topics (goal of the
challenge): we always have something to say
Cons: skills couldn’t drive conversation spanning across several conversation steps
DeepPavlov.ai
Dialog Manager got an influx of scenario-driven skills:
User
•Let’s chat
Bot
•(greeting)
(question)
User
•[utterance]
Bot
•[utterance]
User
•[utterance]
Bot
•[utterance]
User
•[utterance]
Bot
•[utterance]
Small Talk Movies Skill
Pros: Scenario-Driven skills enabled us to give users several conversation turns with
the same context, and limited user understanding within human-curated scenarios
Cons: we didn’t control switching between scenarios
DeepPavlov.ai
link_to added rudimentary support of topic-switching to Dialog Manager (randomly proactive):
User
•Let’s chat
Bot
•(greeting)
(question)
User
•[utterance]
Bot
•[utterance]
User
•[utterance]
Bot
•[utterance]
User
•[utterance]
Bot
•[utterance]
Small Talk Movies Skill
LINK_TO
Pros: Users got several islands of meaning within the conversation. Fine-tuned
management of dialog between sc-, gen-, and ret-based skills helped a lot.
Cons: we didn’t cover enough topics through scenarios
DeepPavlov.ai
Thanks to DFF, Dialog Manager got even more scenario-driven skills:
User
• Let’s chat
Bot
• (greeting)
(question)
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
Greeting Movies Skill
LINK_TO
Pros: Users got even more islands of meaning within the conversation.
Cons: users demand more breadth (more topics), more depth, opinions, understanding!
DFF X Skill DFF Y Skill
LINK_TO
DeepPavlov.ai
Thanks to wiki parser, Dialog Manager’s scenario-driven skills increased depth within their domains:
User
• Let’s chat
Bot
• (greeting)
(question)
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
Greeting Movies Skill
LINK_TO
Pros: Users got even more islands of meaning within the conversation.
Cons: users demand more breadth (more topics), more depth, opinions, understanding!
DFF X Skill DFF Y Skill
LINK_TO
Wiki Parser
DeepPavlov.ai
Thanks to dialog acts, Dialog Manager can better react to user’s needs (reactive):
User
• Let’s chat
Bot
• (greeting)
(question)
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
Greeting Movies Skill
LINK_TO
Pros: we can process user dialog acts with the corresponding responses at higher
level
But: dialog acts are incomplete, and are isolated, single-turn
DFF X Skill DFF Y Skill
LINK_TO
Wiki Parser
DeepPavlov.ai
Thanks to DFF wiki skill, Dialog Manager can increase coverage besides primary topics:
User
• Let’s chat
Bot
• (greeting)
(question)
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
Greeting Movies Skill
LINK_TO
Pros: we can address way more topics on different topics that we don’t have human-
curated scenarios for
But: lack of understanding of user questions, no opinion, no backstory
DFF X Skill DFF Y Skill
LINK_TO
Wiki Parser
DFF Wiki Skill
DeepPavlov.ai
▪ Aimless
• Bot isn’t aware of its own goals (dialog length,
user’s mood, understanding and addressing
user’s goals), and doesn’t take them into
account
▪ Mostly Tactical
• Dialog Management is mostly single-turn-based
(though we give priority to multi-turn scenario-
driven skills)
▪ Mostly Reactive
• Response to Dialog Acts is reactive
• Topic Switching is reactive
• Link_to is mostly random (unless we have
manual transitions)
▪ Mostly Selfless
• Little to no opinion is expressed by our bot in
conversations with users
▪ Mostly Careless
• Bot mostly doesn’t relate to the user’s mood or
discuss user’s emotions
▪ Goal-Aware
• Bot should be aware, and actively drive its goals (dialog length, user’s
mood, understanding and addressing user’s goals)
▪ Strategic
• Dialog Management should be focused on reaching Bot’s goals, foresee
every possible user’s step, and its each action should complement
Bot’s strategy
▪ Proactive
• Bot should know which Speech Function as a response is
appropriate to user’s Speech Function, and then pick the best one
to complement it’s strategy
• Topic Switching should be utilized by Bot from strategic
perspective
• Link_to should utilize relationships between entities within topics
and between topics, and should be used by Bot from strategic
perspective
▪ Be Opinionated
• Bot should be able to express its opinion, be able to explain it, and be
coherent (don’t contradict itself except in minor things)
▪ Be Caring
• Bot should relate to the user’s mood and be able to discuss user’s
emotions
DeepPavlov.ai
In multi-turn conversation bot should plan strategically, across turns
Single-Turn Management is our tactics! To become strategic we need a higher-level
abstraction to act across turns.
DeepPavlov.ai
Eggins and Martin
(1997)
Discourse structure patterns operate across turns: thus overtly interactional & sequential
Discourse Management is a basis for acting across turns, thus becoming strategic
Eggins and Slade
(1997)
Speech Functions control Discourse:
Give
information
Demand
information
Speech Acts
Discourse Moves
Speech Function Example:
open:initiate:give_opinion
Eggins and Slade
(1997)
Speech Functions have hierarchy based on the role in Discourse:
move
open
attend Initiate
Give
Fact
opinion
Demand
Open
Fact
Opinion
Closed
Fact
Opinion
sustain
Continue
Monitor Prolong
Elaborate
Extend
Enhance
Append
Elaborate
Extend
Enhance
React
Respond
Support
Develop
Elaborate
Extend
Enhance
Engage Register Reply
Accept
Comply
Agree
Answer
Acknowledge
Affirm
Confront
Disengage Reply
Decline
Non-comply
Disagree
Withold
Disawow
Contradict
Rejoinder
Support
Track
Check
Confirm
Clarify
Probe
Response
Resolve
Repair
Acquiesce
Confront
Challenge
Detach
Rebound
Counter
Response
Unresolve
Refute
Re-challenge
Eggins and Slade
(1997)
Removing SFs we don’t have to classify from user’s utterances in Alexa Prize
move
open
attend Initiate
Give
Fact
opinion
Demand
Open
Fact
Opinion
Closed
Fact
Opinion
sustain
Continue
Monitor Prolong
Elaborate
Extend
Enhance
Append
Elaborate
Extend
Enhance
React
Respond
Support
Develop
Elaborate
Extend
Enhance
Engage Register Reply
Accept
Comply
Agree
Answer
Acknowledge
Affirm
Confront
Disengage Reply
Decline
Non-comply
Disagree
Withold
Disawow
Contradict
Rejoinder
Support
Track
Check
Confirm
Clarify
Probe
Response
Resolve
Repair
Acquiesce
Confront
Challenge
Detach
Rebound
Counter
Response
Unresolve
Refute
Re-challenge
DeepPavlov (2021)
(removed SFs for commands, discussing physical goods, non-verbal, multiple people)
move
open
attend Initiate
Give
Fact
opinion
Demand
Open
Fact
Opinion
Closed
Fact
Opinion
sustain
Continue
Monitor Prolong
Elaborate
Extend
Enhance
React
Respond
Support
Develop
Elaborate
Extend
Enhance
Engage Register Reply
Agree
Acknowledge
Affirm
Confront
Reply
Disagree
Disawow
Contradict
Rejoinder
Support
Track
Check
Confirm
Clarify
Probe
Response
Resolve
Confront
Challenge
Detach
Rebound
Counter
Response
Unresolve
Refute
Re-challenge
DeepPavlov.ai
Topics != Discourses. Discourses can span across multiple scenarios (e.g., food skill + dff_wiki_skill):
User
• Let’s chat
Bot
• (greeting)
(question)
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
User
• [utterance]
Bot
• [utterance]
Greeting Movies Skill
LINK_TO
Pros: Speech functions automatically track existing discourse. When Bot or user
switches subject of conversation == new discourse has been started.
Cons: how to detect subject switching? What is discourse to us?
DFF X Skill DFF Y Skill
LINK_TO
D #1 (Small Talk) D #2 (Movies) D #3 (Subject A) D #4 (Subject B)
DeepPavlov.ai
Example
Discourse is a combination of key entity (subject), related entities (w/ user & bot relation to them), topic(s)
Discourse #1
• Topics: Entertainment_Movies, Actors
• Key Entity (Subject): Science Fiction Movies
• Related Entities:
movies: Aliens, Terminator,
actors: Sigourney Weaver, Arnold Schwarznegger
Pros: We don’t limit ourselves to one topic (~10 topics as in CoBot DialogAct Topics)
but have flexibility within each topic cause one topic can have myriads of entities to
discuss. When what is discussed is too far from Discourse, our/user’s move is a
change to a new Discourse.
But: why should bot propose a change of a Discourse?
DeepPavlov.ai
Level 1
Dialog Manager should act based on these 3 levels, where each higher-level influences lower level:
Dialog: Bot Goals
• Understand User Interests & Conversation Goal(s)
• Address User Goal(s)
• Prolong Conversation
• Keep or improve user’s mood
• Address Bot Interests
Discourse: Discourse Management
• Maintain existing or change Discourse
Conversation Turn: Speech Function Management
• Pick the most appropriate Speech Function within chosen Discourse
Level 2
Level 3
DeepPavlov.ai
How to express programmatically:
• Bot’s Own Interests: e.g., Bot wants to understand what is love, what is telepathy,
why people want to go to Mars, etc.
• User’s interests: through topic modeling
• User’s Conv. Goals: tell smth (like to preacher), get advice, get into better mood,
small talk, trivia etc.
• User’s mood: TBD (see affective computing)
• Success of Conversation: # of convo turns & discourses, # of personal details
shared, user mood changes, rating (where applicable)
DeepPavlov.ai
- Speech Function Classifier
Discourse Management
- Speech Function Predictor
- Speech
Function
Classifier
Discourse Mgmt
- Speech
Function
Predictor
- DFF Generic Responses Skill
Discourse Management
- Personality
Detector
- etc.
etc.
- Basic Scenario-Driven Skills
- DFF Scenario-Driven Skills
- Generative Skills
- Retrieval Skils
Existing Skills
DeepPavlov.ai
Normal Version Experimental Version
Dialog Length Dialog Length
DeepPavlov.ai
Multiskill
orchestration
Conversa-
tionalskills
NLP
frameworks
ML platforms
Proprietary Open Source
▪ Multiskill Orchestration
• DeepPavlov Agent is an engine for
conversational skill deployment and
orchestration
▪ Conversational skills
• DeepPavlov Dream is a collection of pre-
build conversational skills and a default
distribution package for Dream AI
Assistant
▪ NLP frameworks
• DeepPavlov Library provides pretrained
models and simple declarative approach
to build NLP processing pipelines
▪ ML platforms
• TensorFlow and PyTorch as backends
DeepPavlov.ai
demo.deeppavlov.ai select [Deepy]
Web Demo
@deeppavlov_dream_ai_bot
TG Bot
github.com/deepmipt/deepy
Build Your AI Assistant:
Clone and build your own!
medium.com/deeppavlov
Read us:
forum.deeppavlov.ai
Talk to us: @DeepPavlovDreamDiscussions
TG:
@DeepPavlov
Twitter/TG:
DeepPavlov.ai
Goal-aware Bot:
Bot Goals
Prolong
Conversation
Keep or Improve
User Mood
Pursue Bot’s
Interests
Identify User’s
Interests
Identify User’s
Goals
Address User
Goals
DeepPavlov.ai
Example
Interest Modeling is a combination of a topic (and user’s level of interest to it, 0…1), list of “instance of” entities in
a given topic, generic activities for each of these “instance of”, and “level of interest” (0…1) to each of the activities
Interest #1
• Topic: Sports
Instance Of Activity Level of Interest
Football Playing 0.8
Watching 0.9
Discussing 0.9
Tennis Playing 0.1
Watching 0.8
Discussing 0.7
Modeling user interests by conceptual clustering
Daniela Godoy, 2006
DeepPavlov.ai
Example
Bot’s Current Task is the dialog fragment across one or more conversation turns on the goal the bot is currently
pursuing. It is our Active Skill, and it also includes current discourse as context.
Task #1
• Goal: Prolong Conversation
• Skill: Small Talk
• Discourse #1
Task #2
• Goal: Identify User’s Interests
• Skill: Friendship
• Discourse #2

Weitere ähnliche Inhalte

Was ist angesagt?

Language Empowering Intelligent Assistants (CHT)
Language Empowering Intelligent Assistants (CHT)Language Empowering Intelligent Assistants (CHT)
Language Empowering Intelligent Assistants (CHT)Yun-Nung (Vivian) Chen
 
Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...krisztianbalog
 
Building DSLs: Marriage of High Essence and Groovy Metaprogramming
Building DSLs: Marriage of High Essence and Groovy MetaprogrammingBuilding DSLs: Marriage of High Essence and Groovy Metaprogramming
Building DSLs: Marriage of High Essence and Groovy MetaprogrammingSkills Matter
 
"Sorry, I didn't get that!" - Statistical Learning from Dialogues for Intelli...
"Sorry, I didn't get that!" - Statistical Learning from Dialogues for Intelli..."Sorry, I didn't get that!" - Statistical Learning from Dialogues for Intelli...
"Sorry, I didn't get that!" - Statistical Learning from Dialogues for Intelli...Yun-Nung (Vivian) Chen
 
Dialogue systems and personal assistants
Dialogue systems and personal assistantsDialogue systems and personal assistants
Dialogue systems and personal assistantsNatalia Konstantinova
 
Applying Science to Conversational UX Design
Applying Science to Conversational UX DesignApplying Science to Conversational UX Design
Applying Science to Conversational UX DesignRaphael Arar
 
IEEE ICASSP 2021
IEEE ICASSP 2021IEEE ICASSP 2021
IEEE ICASSP 2021KunZhou18
 
Oral Qualification Examination_Kun_Zhou
Oral Qualification Examination_Kun_ZhouOral Qualification Examination_Kun_Zhou
Oral Qualification Examination_Kun_ZhouKunZhou18
 

Was ist angesagt? (10)

Language Empowering Intelligent Assistants (CHT)
Language Empowering Intelligent Assistants (CHT)Language Empowering Intelligent Assistants (CHT)
Language Empowering Intelligent Assistants (CHT)
 
Chatbot的智慧與靈魂
Chatbot的智慧與靈魂Chatbot的智慧與靈魂
Chatbot的智慧與靈魂
 
Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...
 
Building DSLs: Marriage of High Essence and Groovy Metaprogramming
Building DSLs: Marriage of High Essence and Groovy MetaprogrammingBuilding DSLs: Marriage of High Essence and Groovy Metaprogramming
Building DSLs: Marriage of High Essence and Groovy Metaprogramming
 
"Sorry, I didn't get that!" - Statistical Learning from Dialogues for Intelli...
"Sorry, I didn't get that!" - Statistical Learning from Dialogues for Intelli..."Sorry, I didn't get that!" - Statistical Learning from Dialogues for Intelli...
"Sorry, I didn't get that!" - Statistical Learning from Dialogues for Intelli...
 
Dialogue systems and personal assistants
Dialogue systems and personal assistantsDialogue systems and personal assistants
Dialogue systems and personal assistants
 
Applying Science to Conversational UX Design
Applying Science to Conversational UX DesignApplying Science to Conversational UX Design
Applying Science to Conversational UX Design
 
IEEE ICASSP 2021
IEEE ICASSP 2021IEEE ICASSP 2021
IEEE ICASSP 2021
 
Oral Qualification Examination_Kun_Zhou
Oral Qualification Examination_Kun_ZhouOral Qualification Examination_Kun_Zhou
Oral Qualification Examination_Kun_Zhou
 
My+Magic
My+MagicMy+Magic
My+Magic
 

Ähnlich wie Managing Dialog Strategy in Multiskill AI Assistant with Discourse Management

Multimodality at Dialogue 2022 by DeepPavlov.pdf
Multimodality at Dialogue 2022 by DeepPavlov.pdfMultimodality at Dialogue 2022 by DeepPavlov.pdf
Multimodality at Dialogue 2022 by DeepPavlov.pdfDaniel Kornev
 
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?krisztianbalog
 
FCO Think Tank 1.10.09
FCO Think Tank 1.10.09FCO Think Tank 1.10.09
FCO Think Tank 1.10.09Rob Pearson
 
Xylos webinar 'Let your investment pay off: how do you turn your chatbot into...
Xylos webinar 'Let your investment pay off: how do you turn your chatbot into...Xylos webinar 'Let your investment pay off: how do you turn your chatbot into...
Xylos webinar 'Let your investment pay off: how do you turn your chatbot into...Xylos
 
Presenting to Executive Leadership
Presenting to Executive LeadershipPresenting to Executive Leadership
Presenting to Executive LeadershipBrian Sullivan
 
Cross-Sector Partnerships 101: Structuring Your Cross-Sector Partnership So...
Cross-Sector Partnerships 101: Structuring Your Cross-Sector Partnership So...Cross-Sector Partnerships 101: Structuring Your Cross-Sector Partnership So...
Cross-Sector Partnerships 101: Structuring Your Cross-Sector Partnership So...Alison Gold
 
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...UXPA International
 
Ten Challenges for Building Great Learning Resources
Ten Challenges for Building Great Learning ResourcesTen Challenges for Building Great Learning Resources
Ten Challenges for Building Great Learning ResourcesRaptivity
 
Chatbot interaction design — IxDA London July 2017
Chatbot interaction design — IxDA London July 2017Chatbot interaction design — IxDA London July 2017
Chatbot interaction design — IxDA London July 2017Boon Yew Chew
 
Workshop: Chatbot in a box - Introduction to conversation design and conducti...
Workshop: Chatbot in a box - Introduction to conversation design and conducti...Workshop: Chatbot in a box - Introduction to conversation design and conducti...
Workshop: Chatbot in a box - Introduction to conversation design and conducti...Jon Temple
 
Webinar - Driving eLearning Engagement and Interactivity using Raptivity: Tip...
Webinar - Driving eLearning Engagement and Interactivity using Raptivity: Tip...Webinar - Driving eLearning Engagement and Interactivity using Raptivity: Tip...
Webinar - Driving eLearning Engagement and Interactivity using Raptivity: Tip...Raptivity
 
Getting to Know the Community
Getting to Know the CommunityGetting to Know the Community
Getting to Know the CommunityBryan Boroughf
 
Key Issues and Applications of Social Networking Technologies in Libraries
Key Issues and Applications of Social Networking Technologies in LibrariesKey Issues and Applications of Social Networking Technologies in Libraries
Key Issues and Applications of Social Networking Technologies in LibrariesMeredith Farkas
 
CTO Universe Leadership Series: More Effective Agile Leadership
CTO Universe Leadership Series: More Effective Agile LeadershipCTO Universe Leadership Series: More Effective Agile Leadership
CTO Universe Leadership Series: More Effective Agile LeadershipAggregage
 
[GAN by Hung-yi Lee]Part 3: The recent research of my group
[GAN by Hung-yi Lee]Part 3: The recent research of my group[GAN by Hung-yi Lee]Part 3: The recent research of my group
[GAN by Hung-yi Lee]Part 3: The recent research of my groupNAVER Engineering
 
Website Strategy Planning for Nonprofits
Website Strategy Planning for NonprofitsWebsite Strategy Planning for Nonprofits
Website Strategy Planning for Nonprofits501 Commons
 
Rapid User Research - a talk from Agile 2013 by Aviva Rosenstein
Rapid User Research - a talk from Agile 2013 by Aviva RosensteinRapid User Research - a talk from Agile 2013 by Aviva Rosenstein
Rapid User Research - a talk from Agile 2013 by Aviva RosensteinAviva Rosenstein
 
Go or No-Go: Operability and Contingency Planning at Etsy.com
Go or No-Go: Operability and Contingency Planning at Etsy.comGo or No-Go: Operability and Contingency Planning at Etsy.com
Go or No-Go: Operability and Contingency Planning at Etsy.comJohn Allspaw
 
Digital Outreach Framework
Digital Outreach FrameworkDigital Outreach Framework
Digital Outreach Frameworkritzsingh
 

Ähnlich wie Managing Dialog Strategy in Multiskill AI Assistant with Discourse Management (20)

Multimodality at Dialogue 2022 by DeepPavlov.pdf
Multimodality at Dialogue 2022 by DeepPavlov.pdfMultimodality at Dialogue 2022 by DeepPavlov.pdf
Multimodality at Dialogue 2022 by DeepPavlov.pdf
 
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
 
Visualised flow
Visualised flowVisualised flow
Visualised flow
 
FCO Think Tank 1.10.09
FCO Think Tank 1.10.09FCO Think Tank 1.10.09
FCO Think Tank 1.10.09
 
Xylos webinar 'Let your investment pay off: how do you turn your chatbot into...
Xylos webinar 'Let your investment pay off: how do you turn your chatbot into...Xylos webinar 'Let your investment pay off: how do you turn your chatbot into...
Xylos webinar 'Let your investment pay off: how do you turn your chatbot into...
 
Presenting to Executive Leadership
Presenting to Executive LeadershipPresenting to Executive Leadership
Presenting to Executive Leadership
 
Cross-Sector Partnerships 101: Structuring Your Cross-Sector Partnership So...
Cross-Sector Partnerships 101: Structuring Your Cross-Sector Partnership So...Cross-Sector Partnerships 101: Structuring Your Cross-Sector Partnership So...
Cross-Sector Partnerships 101: Structuring Your Cross-Sector Partnership So...
 
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...
 
Ten Challenges for Building Great Learning Resources
Ten Challenges for Building Great Learning ResourcesTen Challenges for Building Great Learning Resources
Ten Challenges for Building Great Learning Resources
 
Chatbot interaction design — IxDA London July 2017
Chatbot interaction design — IxDA London July 2017Chatbot interaction design — IxDA London July 2017
Chatbot interaction design — IxDA London July 2017
 
Workshop: Chatbot in a box - Introduction to conversation design and conducti...
Workshop: Chatbot in a box - Introduction to conversation design and conducti...Workshop: Chatbot in a box - Introduction to conversation design and conducti...
Workshop: Chatbot in a box - Introduction to conversation design and conducti...
 
Webinar - Driving eLearning Engagement and Interactivity using Raptivity: Tip...
Webinar - Driving eLearning Engagement and Interactivity using Raptivity: Tip...Webinar - Driving eLearning Engagement and Interactivity using Raptivity: Tip...
Webinar - Driving eLearning Engagement and Interactivity using Raptivity: Tip...
 
Getting to Know the Community
Getting to Know the CommunityGetting to Know the Community
Getting to Know the Community
 
Key Issues and Applications of Social Networking Technologies in Libraries
Key Issues and Applications of Social Networking Technologies in LibrariesKey Issues and Applications of Social Networking Technologies in Libraries
Key Issues and Applications of Social Networking Technologies in Libraries
 
CTO Universe Leadership Series: More Effective Agile Leadership
CTO Universe Leadership Series: More Effective Agile LeadershipCTO Universe Leadership Series: More Effective Agile Leadership
CTO Universe Leadership Series: More Effective Agile Leadership
 
[GAN by Hung-yi Lee]Part 3: The recent research of my group
[GAN by Hung-yi Lee]Part 3: The recent research of my group[GAN by Hung-yi Lee]Part 3: The recent research of my group
[GAN by Hung-yi Lee]Part 3: The recent research of my group
 
Website Strategy Planning for Nonprofits
Website Strategy Planning for NonprofitsWebsite Strategy Planning for Nonprofits
Website Strategy Planning for Nonprofits
 
Rapid User Research - a talk from Agile 2013 by Aviva Rosenstein
Rapid User Research - a talk from Agile 2013 by Aviva RosensteinRapid User Research - a talk from Agile 2013 by Aviva Rosenstein
Rapid User Research - a talk from Agile 2013 by Aviva Rosenstein
 
Go or No-Go: Operability and Contingency Planning at Etsy.com
Go or No-Go: Operability and Contingency Planning at Etsy.comGo or No-Go: Operability and Contingency Planning at Etsy.com
Go or No-Go: Operability and Contingency Planning at Etsy.com
 
Digital Outreach Framework
Digital Outreach FrameworkDigital Outreach Framework
Digital Outreach Framework
 

Mehr von Daniel Kornev

Multiskill Conversational AI
Multiskill Conversational AIMultiskill Conversational AI
Multiskill Conversational AIDaniel Kornev
 
Building AI Assistants with DeepPavlov - truly final.pdf
Building AI Assistants with DeepPavlov - truly final.pdfBuilding AI Assistants with DeepPavlov - truly final.pdf
Building AI Assistants with DeepPavlov - truly final.pdfDaniel Kornev
 
Daniel Kornev's Slides for Working in Digital Media and Tech Services event
Daniel Kornev's Slides for Working in Digital Media and Tech Services eventDaniel Kornev's Slides for Working in Digital Media and Tech Services event
Daniel Kornev's Slides for Working in Digital Media and Tech Services eventDaniel Kornev
 
Functional Iliteracy
Functional IliteracyFunctional Iliteracy
Functional IliteracyDaniel Kornev
 
Digital Work Environments - History and What's Next after Siri and Cortana?
Digital Work Environments - History and What's Next after Siri and Cortana?Digital Work Environments - History and What's Next after Siri and Cortana?
Digital Work Environments - History and What's Next after Siri and Cortana?Daniel Kornev
 
Cortana - The Internals
Cortana - The InternalsCortana - The Internals
Cortana - The InternalsDaniel Kornev
 
Palantir, Quid, RecordedFuture: Augmented Intelligence Frontier
Palantir, Quid, RecordedFuture: Augmented Intelligence FrontierPalantir, Quid, RecordedFuture: Augmented Intelligence Frontier
Palantir, Quid, RecordedFuture: Augmented Intelligence FrontierDaniel Kornev
 
Augmented Intelligence 2.0
Augmented Intelligence 2.0Augmented Intelligence 2.0
Augmented Intelligence 2.0Daniel Kornev
 
Developer Relations, Google Russia - VC & Startups Outreach Program
Developer Relations, Google Russia - VC & Startups Outreach ProgramDeveloper Relations, Google Russia - VC & Startups Outreach Program
Developer Relations, Google Russia - VC & Startups Outreach ProgramDaniel Kornev
 
Project Universe – Context-aware Project Management System
Project Universe – Context-aware Project Management SystemProject Universe – Context-aware Project Management System
Project Universe – Context-aware Project Management SystemDaniel Kornev
 
Brave New World of Computer Science - Part I
Brave New World of Computer Science - Part IBrave New World of Computer Science - Part I
Brave New World of Computer Science - Part IDaniel Kornev
 
Brave New World of Computer Science - Part II
Brave New World of Computer Science - Part IIBrave New World of Computer Science - Part II
Brave New World of Computer Science - Part IIDaniel Kornev
 
Ubiquitous Computing
Ubiquitous ComputingUbiquitous Computing
Ubiquitous ComputingDaniel Kornev
 

Mehr von Daniel Kornev (14)

Multiskill Conversational AI
Multiskill Conversational AIMultiskill Conversational AI
Multiskill Conversational AI
 
Building AI Assistants with DeepPavlov - truly final.pdf
Building AI Assistants with DeepPavlov - truly final.pdfBuilding AI Assistants with DeepPavlov - truly final.pdf
Building AI Assistants with DeepPavlov - truly final.pdf
 
Daniel Kornev's Slides for Working in Digital Media and Tech Services event
Daniel Kornev's Slides for Working in Digital Media and Tech Services eventDaniel Kornev's Slides for Working in Digital Media and Tech Services event
Daniel Kornev's Slides for Working in Digital Media and Tech Services event
 
Functional Iliteracy
Functional IliteracyFunctional Iliteracy
Functional Iliteracy
 
Digital Work Environments - History and What's Next after Siri and Cortana?
Digital Work Environments - History and What's Next after Siri and Cortana?Digital Work Environments - History and What's Next after Siri and Cortana?
Digital Work Environments - History and What's Next after Siri and Cortana?
 
Cortana - The Internals
Cortana - The InternalsCortana - The Internals
Cortana - The Internals
 
Palantir, Quid, RecordedFuture: Augmented Intelligence Frontier
Palantir, Quid, RecordedFuture: Augmented Intelligence FrontierPalantir, Quid, RecordedFuture: Augmented Intelligence Frontier
Palantir, Quid, RecordedFuture: Augmented Intelligence Frontier
 
Augmented Intelligence 2.0
Augmented Intelligence 2.0Augmented Intelligence 2.0
Augmented Intelligence 2.0
 
Developer Relations, Google Russia - VC & Startups Outreach Program
Developer Relations, Google Russia - VC & Startups Outreach ProgramDeveloper Relations, Google Russia - VC & Startups Outreach Program
Developer Relations, Google Russia - VC & Startups Outreach Program
 
Project Universe – Context-aware Project Management System
Project Universe – Context-aware Project Management SystemProject Universe – Context-aware Project Management System
Project Universe – Context-aware Project Management System
 
Brave New World of Computer Science - Part I
Brave New World of Computer Science - Part IBrave New World of Computer Science - Part I
Brave New World of Computer Science - Part I
 
Brave New World of Computer Science - Part II
Brave New World of Computer Science - Part IIBrave New World of Computer Science - Part II
Brave New World of Computer Science - Part II
 
Context In UX
Context In UXContext In UX
Context In UX
 
Ubiquitous Computing
Ubiquitous ComputingUbiquitous Computing
Ubiquitous Computing
 

Kürzlich hochgeladen

How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.Curtis Poe
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfRankYa
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfPrecisely
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 

Kürzlich hochgeladen (20)

How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 

Managing Dialog Strategy in Multiskill AI Assistant with Discourse Management

  • 1. DIALOG STRATEGY MANAGEMENT IN MULTISKILL AI ASSISTANTS WITH DISCOURSE MANAGEMENT Daniel Kornev, Chief Product Officer, DeepPavlov.ai
  • 2.
  • 3. Step 1 Dialog Management is complex Correctly identify user’s utterance’s goal Step 2 Correctly generate response(s) Step 3 Correctly pick the best response Alice: what’s happened in city hall? Bot: [Which city hall [Entity Disambiguation]? Where (NYC | Local)? When (Today | Yesterday | at some time)?] Domain:News: Occupy City Hall happened in July 2020 | Confidence: 0.85 Domain:Factoid: City Hall is the seat of New York City government | Confidence: 0.95 Retrieval: By 1969 City Hall was described as badly crowded because of Bellevue growing … | Confidence: 0.75 Alice: What’s happened in city hall? Bot: City Hall is the seat of New York City government
  • 4. DeepPavlov.ai Dialog Manager was predominantly tactical (single-turn, reactive): User •Let’s chat Bot •(greeting) (question) User •[utterance] Bot •[utterance] User •[utterance] Bot •[utterance] User •[utterance] Bot •[utterance] Skill #1 Skill #2 Skill #3 Skill #4 Pros: Retrieval skills helped us to cover lots of societal topics (goal of the challenge): we always have something to say Cons: skills couldn’t drive conversation spanning across several conversation steps
  • 5. DeepPavlov.ai Dialog Manager got an influx of scenario-driven skills: User •Let’s chat Bot •(greeting) (question) User •[utterance] Bot •[utterance] User •[utterance] Bot •[utterance] User •[utterance] Bot •[utterance] Small Talk Movies Skill Pros: Scenario-Driven skills enabled us to give users several conversation turns with the same context, and limited user understanding within human-curated scenarios Cons: we didn’t control switching between scenarios
  • 6. DeepPavlov.ai link_to added rudimentary support of topic-switching to Dialog Manager (randomly proactive): User •Let’s chat Bot •(greeting) (question) User •[utterance] Bot •[utterance] User •[utterance] Bot •[utterance] User •[utterance] Bot •[utterance] Small Talk Movies Skill LINK_TO Pros: Users got several islands of meaning within the conversation. Fine-tuned management of dialog between sc-, gen-, and ret-based skills helped a lot. Cons: we didn’t cover enough topics through scenarios
  • 7. DeepPavlov.ai Thanks to DFF, Dialog Manager got even more scenario-driven skills: User • Let’s chat Bot • (greeting) (question) User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] Greeting Movies Skill LINK_TO Pros: Users got even more islands of meaning within the conversation. Cons: users demand more breadth (more topics), more depth, opinions, understanding! DFF X Skill DFF Y Skill LINK_TO
  • 8. DeepPavlov.ai Thanks to wiki parser, Dialog Manager’s scenario-driven skills increased depth within their domains: User • Let’s chat Bot • (greeting) (question) User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] Greeting Movies Skill LINK_TO Pros: Users got even more islands of meaning within the conversation. Cons: users demand more breadth (more topics), more depth, opinions, understanding! DFF X Skill DFF Y Skill LINK_TO Wiki Parser
  • 9. DeepPavlov.ai Thanks to dialog acts, Dialog Manager can better react to user’s needs (reactive): User • Let’s chat Bot • (greeting) (question) User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] Greeting Movies Skill LINK_TO Pros: we can process user dialog acts with the corresponding responses at higher level But: dialog acts are incomplete, and are isolated, single-turn DFF X Skill DFF Y Skill LINK_TO Wiki Parser
  • 10. DeepPavlov.ai Thanks to DFF wiki skill, Dialog Manager can increase coverage besides primary topics: User • Let’s chat Bot • (greeting) (question) User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] Greeting Movies Skill LINK_TO Pros: we can address way more topics on different topics that we don’t have human- curated scenarios for But: lack of understanding of user questions, no opinion, no backstory DFF X Skill DFF Y Skill LINK_TO Wiki Parser DFF Wiki Skill
  • 11. DeepPavlov.ai ▪ Aimless • Bot isn’t aware of its own goals (dialog length, user’s mood, understanding and addressing user’s goals), and doesn’t take them into account ▪ Mostly Tactical • Dialog Management is mostly single-turn-based (though we give priority to multi-turn scenario- driven skills) ▪ Mostly Reactive • Response to Dialog Acts is reactive • Topic Switching is reactive • Link_to is mostly random (unless we have manual transitions) ▪ Mostly Selfless • Little to no opinion is expressed by our bot in conversations with users ▪ Mostly Careless • Bot mostly doesn’t relate to the user’s mood or discuss user’s emotions ▪ Goal-Aware • Bot should be aware, and actively drive its goals (dialog length, user’s mood, understanding and addressing user’s goals) ▪ Strategic • Dialog Management should be focused on reaching Bot’s goals, foresee every possible user’s step, and its each action should complement Bot’s strategy ▪ Proactive • Bot should know which Speech Function as a response is appropriate to user’s Speech Function, and then pick the best one to complement it’s strategy • Topic Switching should be utilized by Bot from strategic perspective • Link_to should utilize relationships between entities within topics and between topics, and should be used by Bot from strategic perspective ▪ Be Opinionated • Bot should be able to express its opinion, be able to explain it, and be coherent (don’t contradict itself except in minor things) ▪ Be Caring • Bot should relate to the user’s mood and be able to discuss user’s emotions
  • 12. DeepPavlov.ai In multi-turn conversation bot should plan strategically, across turns Single-Turn Management is our tactics! To become strategic we need a higher-level abstraction to act across turns.
  • 13. DeepPavlov.ai Eggins and Martin (1997) Discourse structure patterns operate across turns: thus overtly interactional & sequential Discourse Management is a basis for acting across turns, thus becoming strategic
  • 14. Eggins and Slade (1997) Speech Functions control Discourse: Give information Demand information Speech Acts Discourse Moves Speech Function Example: open:initiate:give_opinion
  • 15. Eggins and Slade (1997) Speech Functions have hierarchy based on the role in Discourse: move open attend Initiate Give Fact opinion Demand Open Fact Opinion Closed Fact Opinion sustain Continue Monitor Prolong Elaborate Extend Enhance Append Elaborate Extend Enhance React Respond Support Develop Elaborate Extend Enhance Engage Register Reply Accept Comply Agree Answer Acknowledge Affirm Confront Disengage Reply Decline Non-comply Disagree Withold Disawow Contradict Rejoinder Support Track Check Confirm Clarify Probe Response Resolve Repair Acquiesce Confront Challenge Detach Rebound Counter Response Unresolve Refute Re-challenge
  • 16. Eggins and Slade (1997) Removing SFs we don’t have to classify from user’s utterances in Alexa Prize move open attend Initiate Give Fact opinion Demand Open Fact Opinion Closed Fact Opinion sustain Continue Monitor Prolong Elaborate Extend Enhance Append Elaborate Extend Enhance React Respond Support Develop Elaborate Extend Enhance Engage Register Reply Accept Comply Agree Answer Acknowledge Affirm Confront Disengage Reply Decline Non-comply Disagree Withold Disawow Contradict Rejoinder Support Track Check Confirm Clarify Probe Response Resolve Repair Acquiesce Confront Challenge Detach Rebound Counter Response Unresolve Refute Re-challenge
  • 17. DeepPavlov (2021) (removed SFs for commands, discussing physical goods, non-verbal, multiple people) move open attend Initiate Give Fact opinion Demand Open Fact Opinion Closed Fact Opinion sustain Continue Monitor Prolong Elaborate Extend Enhance React Respond Support Develop Elaborate Extend Enhance Engage Register Reply Agree Acknowledge Affirm Confront Reply Disagree Disawow Contradict Rejoinder Support Track Check Confirm Clarify Probe Response Resolve Confront Challenge Detach Rebound Counter Response Unresolve Refute Re-challenge
  • 18. DeepPavlov.ai Topics != Discourses. Discourses can span across multiple scenarios (e.g., food skill + dff_wiki_skill): User • Let’s chat Bot • (greeting) (question) User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] User • [utterance] Bot • [utterance] Greeting Movies Skill LINK_TO Pros: Speech functions automatically track existing discourse. When Bot or user switches subject of conversation == new discourse has been started. Cons: how to detect subject switching? What is discourse to us? DFF X Skill DFF Y Skill LINK_TO D #1 (Small Talk) D #2 (Movies) D #3 (Subject A) D #4 (Subject B)
  • 19. DeepPavlov.ai Example Discourse is a combination of key entity (subject), related entities (w/ user & bot relation to them), topic(s) Discourse #1 • Topics: Entertainment_Movies, Actors • Key Entity (Subject): Science Fiction Movies • Related Entities: movies: Aliens, Terminator, actors: Sigourney Weaver, Arnold Schwarznegger Pros: We don’t limit ourselves to one topic (~10 topics as in CoBot DialogAct Topics) but have flexibility within each topic cause one topic can have myriads of entities to discuss. When what is discussed is too far from Discourse, our/user’s move is a change to a new Discourse. But: why should bot propose a change of a Discourse?
  • 20. DeepPavlov.ai Level 1 Dialog Manager should act based on these 3 levels, where each higher-level influences lower level: Dialog: Bot Goals • Understand User Interests & Conversation Goal(s) • Address User Goal(s) • Prolong Conversation • Keep or improve user’s mood • Address Bot Interests Discourse: Discourse Management • Maintain existing or change Discourse Conversation Turn: Speech Function Management • Pick the most appropriate Speech Function within chosen Discourse Level 2 Level 3
  • 21. DeepPavlov.ai How to express programmatically: • Bot’s Own Interests: e.g., Bot wants to understand what is love, what is telepathy, why people want to go to Mars, etc. • User’s interests: through topic modeling • User’s Conv. Goals: tell smth (like to preacher), get advice, get into better mood, small talk, trivia etc. • User’s mood: TBD (see affective computing) • Success of Conversation: # of convo turns & discourses, # of personal details shared, user mood changes, rating (where applicable)
  • 22. DeepPavlov.ai - Speech Function Classifier Discourse Management - Speech Function Predictor - Speech Function Classifier Discourse Mgmt - Speech Function Predictor - DFF Generic Responses Skill Discourse Management - Personality Detector - etc. etc. - Basic Scenario-Driven Skills - DFF Scenario-Driven Skills - Generative Skills - Retrieval Skils Existing Skills
  • 23. DeepPavlov.ai Normal Version Experimental Version Dialog Length Dialog Length
  • 24. DeepPavlov.ai Multiskill orchestration Conversa- tionalskills NLP frameworks ML platforms Proprietary Open Source ▪ Multiskill Orchestration • DeepPavlov Agent is an engine for conversational skill deployment and orchestration ▪ Conversational skills • DeepPavlov Dream is a collection of pre- build conversational skills and a default distribution package for Dream AI Assistant ▪ NLP frameworks • DeepPavlov Library provides pretrained models and simple declarative approach to build NLP processing pipelines ▪ ML platforms • TensorFlow and PyTorch as backends
  • 25. DeepPavlov.ai demo.deeppavlov.ai select [Deepy] Web Demo @deeppavlov_dream_ai_bot TG Bot github.com/deepmipt/deepy Build Your AI Assistant: Clone and build your own! medium.com/deeppavlov Read us: forum.deeppavlov.ai Talk to us: @DeepPavlovDreamDiscussions TG: @DeepPavlov Twitter/TG:
  • 26. DeepPavlov.ai Goal-aware Bot: Bot Goals Prolong Conversation Keep or Improve User Mood Pursue Bot’s Interests Identify User’s Interests Identify User’s Goals Address User Goals
  • 27. DeepPavlov.ai Example Interest Modeling is a combination of a topic (and user’s level of interest to it, 0…1), list of “instance of” entities in a given topic, generic activities for each of these “instance of”, and “level of interest” (0…1) to each of the activities Interest #1 • Topic: Sports Instance Of Activity Level of Interest Football Playing 0.8 Watching 0.9 Discussing 0.9 Tennis Playing 0.1 Watching 0.8 Discussing 0.7 Modeling user interests by conceptual clustering Daniela Godoy, 2006
  • 28. DeepPavlov.ai Example Bot’s Current Task is the dialog fragment across one or more conversation turns on the goal the bot is currently pursuing. It is our Active Skill, and it also includes current discourse as context. Task #1 • Goal: Prolong Conversation • Skill: Small Talk • Discourse #1 Task #2 • Goal: Identify User’s Interests • Skill: Friendship • Discourse #2