SlideShare uma empresa Scribd logo
1 de 21
Baixar para ler offline
FROM ALEXA PRIZE SOCIALBOT TO
MULTISKILL AI ASSISTANT PLATFORM
Daniel Kornev, CPO @ DeepPavlov.ai
DeepPavlov.ai
Zero Interaction Cost
Wish → Action
DeepPavlov.ai
Little Problem:
Poor Usability*
* Intelligent Assistants Have Poor Usability, Nielsen Norman Group © 2018
DeepPavlov.ai
Good*
Bad
Bad
Bad
Terrible
Soon to be great
Hard to do
Limited by design
Super hard to do
Needs lot of work
UI Technique Status Potential
* For Non-native English speakers it’s still a pain
Voice Input
Natural Language Understanding
Voice Output
Intelligent Interpretation
Agency
DeepPavlov.ai
Bad
Bad
Terrible
Hard to do
Super hard to do
Needs lot of work
UI Technique Status Potential
* More of an engineering problem
Natural Language Understanding
Intelligent Interpretation
Agency*
DeepPavlov.ai
It’s an NLP’s Holy Grail:
human-like comprehension
of texts & languages
DeepPavlov.ai
How to Get The Holy Grail?
Challenge!
DeepPavlov.ai
What Is Alexa Prize?
The Alexa Prize is a global competition for university students
dedicated to accelerating the field of conversational AI.
Teams of university students will develop a socialbot, an Alexa skill
that converses with users on popular societal topics.
The grand challenge for the Alexa Prize is to create a socialbot that
can engage in a fun, high quality conversation on popular societal
topics for 20 minutes and achieve an average rating of at least
4.0/5.0.
DeepPavlov.ai
DREAM socialbot
architecture
1. Multiple Annotators are used to
extract information from the
user input.
2. Skill Selector defines a subset of
active Skills based on the
extracted information.
3. Selected Skills propose their
response candidates.
4. Finally, Response Selector picks
a response to be sent to
Response Annotators and,
eventually, to the user.
All elements of the pipeline are
running asynchronously with two
points of synchronization: Skill
Selector and Response Selector.
Dialogue State serves as a shared
memory.
DeepPavlov.ai
DREAM socialbot
infrastructure
1. The core of the DREAM socialbot is implemented with
DeepPavlov Agent (DP-Agent) framework. It
orchestrates services for Skills, Annotators, Skill
Selector and Response Selector, and is located on AWS
EC2 instances with Docker Swarm.
2. Dialogue State history is stored on a separate instance
with MongoDB.
3. AWS Lambda performs HTTP requests to the DREAM-
agent by sending ASR tokens.
4. Testing infrastructure consists of Telegram bots for
interacting with the dev version of the socialbot or with
selected conversational skill only.
5. Dialogue analytics tool and dashboard were located on a
separate EC2 instance.
6. Cluster and application monitoring had configured alerts
to email and Slack.
DeepPavlov.ai
DeepPavlov
Ecosystem
▪ Open repository of NLP models
and pipelines
• easy to find and reuse NLP
components for development of new
skills or extension of existing
▪ Open repository of conversational
skills
• alternative implementations of the
most popular skills
▪ Open hub for AI Assistant
distributions
• general and domainindustry
specific distributions of skill sets
DeepPavlov.ai
Conversational AI
DeepPavlov Stack
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
HOW TO BUILD MULTISKILL
AI ASSISTANT WITH DEEPPAVLOV
LIVING IN PANDEMICS
MAKES US LONELY
Wouldn’t it be nice to have a friend to care about us?
DeepPavlov.ai
MEET GERTY 3000
Can help Sam with problems on
the Moon Base Sarang?
Can entertain Sam? Yes ✔
Yes ✔
Can we emulate it with
DeepPavlov DREAM?
Yes ✔
Main Question
Functionality Analysis
Case: Gerty
In the Moon Movie
DeepPavlov.ai
Text OR
Voice
Input
TTS
(NeMo)
Deepy:
Example Architecture
Spell
Checking
NeMo ASR Harvesters
Status
Chit-Chat
(AIML)
Emotion
BUILT-IN
SKILL
SELECTOR
RULE-BASED
RESPONSE
SELECTOR
DeepPavlov.ai
services:
agent:
[..]
depends_on:
- mongo
harvesters_maintenance_skill:
[..]
mongo:
[..]
rule_based_response_selector:
[..]
nemo:
[..]
depends_on:
- agent
emotion_classification:
[..]
program_y:
[..]
spell_checking:
[..]
Deepy:
Docker Pipeline
Spell Checking
Annotators
Emotion Classification
Harvesters Status Skill
Skills
Chit-Chat Skill
NeMo ASR & TTS
Other Services
Rule-Based Response Selector
DeepPavlov.ai
services:
agent:
[..]
depends_on:
- mongo
harvesters_maintenance_skill:
[..]
mongo:
[..]
rule_based_response_selector:
[..]
nemo:
[..]
depends_on:
- agent
emotion_classification:
[..]
program_y:
[..]
clone_tts:
[..]
Deepy:
Part of Agent Pipeline
Annotators
Services Are in Groups
Skills
Response Annotators
Depend on groups (e.g., “skills”)
Services Are Isolated
Limited in what they see in dialog
Invoke Agent’s State Manager
Can run via HTTP or be Python-based
"skills": {
"harvesters_maintenance_skill": {
"connector": {
"protocol": "http",
"url": "http://harvesters_maintenance
_skill:3002/respond"
},
"dialog_formatter": "dp_formatters:ful
l_dialog",
"response_formatter": "dp_formatters:b
ase_skill_formatter",
"state_manager_method": "add_hypothesi
s",
"previous_services": ["annotators"]
},
Response Selectors
DeepPavlov.ai
Deepy:
HarvMaint.: Configs
What is (all) harvesters’ status?
Intents
What is harvester status?
Prepare rover for a trip
domain.yml
intents:
- all_statuses_request
- status_request
[..]
- trip_request
responses:
utter_status_request:
- text: "The harvester {harv_id} is {harv_status}.“
[..]
nlu.md
## intent:all_statuses_request
- What is the harvesters status?
- What is the combines status?
[..]
stories.md
## harv_status + prepare_trip
* status_request
- utter_status_request
stories.md – training for dialogs
RASA Configs
nlu.md – training for intents & slots
domain.yml – basic ontology for skill
Simple and easy to use
DeepPavlov.ai
Deepy:
Chit-Chat Skill (AIML)
<?xml version="1.0" encoding="UTF-8"?>
<aiml version="2.0">
<category>
<pattern>I AM ^ TIRED</pattern>
<template>
🙁
<random>
<li>Get some sleep<get name="name"/>.
You're very tired.</li>
<li>Have a rest and be happy! How can
I help you?</li>
</random>
</template>
</category>
[..]
</aiml>
</xml>
Assistant Profile (Name, Place, etc.)
Patterns
Greeting scenario
Topics
Looks up for patterns
Dialog Processing
Picks random pre-defined response
If not sure, confidence is low (0.2)
Returns response + confidence
DeepPavlov.ai
Deepy 3000: Demo
A prototype of a fictional Moonbase A.I. Assistant, inspired by the Moon Movie
(2009) made by Duncan Jones

Mais conteúdo relacionado

Semelhante a kornev.pdf

A Strong Object Recognition Using Lbp, Ltp And Rlbp
A Strong Object Recognition Using Lbp, Ltp And RlbpA Strong Object Recognition Using Lbp, Ltp And Rlbp
A Strong Object Recognition Using Lbp, Ltp And Rlbp
Rikki Wright
 
Stream SQL eventflow visual programming for real programmers presentation
Stream SQL eventflow visual programming for real programmers presentationStream SQL eventflow visual programming for real programmers presentation
Stream SQL eventflow visual programming for real programmers presentation
streambase
 
Building Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon LexBuilding Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon Lex
Amazon Web Services
 
5 Keys to API Design - API Days Paris 2013
5 Keys to API Design - API Days Paris 20135 Keys to API Design - API Days Paris 2013
5 Keys to API Design - API Days Paris 2013
Daniel Feist
 

Semelhante a kornev.pdf (20)

Envisioning the Future of Language Workbenches
Envisioning the Future of Language WorkbenchesEnvisioning the Future of Language Workbenches
Envisioning the Future of Language Workbenches
 
Computers have feelings too
Computers have feelings tooComputers have feelings too
Computers have feelings too
 
Breaking Through The Challenges of Scalable Deep Learning for Video Analytics
Breaking Through The Challenges of Scalable Deep Learning for Video AnalyticsBreaking Through The Challenges of Scalable Deep Learning for Video Analytics
Breaking Through The Challenges of Scalable Deep Learning for Video Analytics
 
AWS Artificial Intelligence Day - Toronto
AWS Artificial Intelligence Day - TorontoAWS Artificial Intelligence Day - Toronto
AWS Artificial Intelligence Day - Toronto
 
Amazon Web Services - Strategy and Current Offering
Amazon Web Services - Strategy and Current OfferingAmazon Web Services - Strategy and Current Offering
Amazon Web Services - Strategy and Current Offering
 
Comparative Study of programming Languages
Comparative Study of programming LanguagesComparative Study of programming Languages
Comparative Study of programming Languages
 
OWF14 - Big Data : The State of Machine Learning in 2014
OWF14 - Big Data : The State of Machine  Learning in 2014OWF14 - Big Data : The State of Machine  Learning in 2014
OWF14 - Big Data : The State of Machine Learning in 2014
 
What Web Framework To Use?
What Web Framework To Use?What Web Framework To Use?
What Web Framework To Use?
 
Add Intelligence to Applications with AWS ML: Machine Learning Workshops SF
Add Intelligence to Applications with AWS ML: Machine Learning Workshops SFAdd Intelligence to Applications with AWS ML: Machine Learning Workshops SF
Add Intelligence to Applications with AWS ML: Machine Learning Workshops SF
 
A Strong Object Recognition Using Lbp, Ltp And Rlbp
A Strong Object Recognition Using Lbp, Ltp And RlbpA Strong Object Recognition Using Lbp, Ltp And Rlbp
A Strong Object Recognition Using Lbp, Ltp And Rlbp
 
Stream SQL eventflow visual programming for real programmers presentation
Stream SQL eventflow visual programming for real programmers presentationStream SQL eventflow visual programming for real programmers presentation
Stream SQL eventflow visual programming for real programmers presentation
 
Cloud AI GenAI Overview.pptx
Cloud AI GenAI Overview.pptxCloud AI GenAI Overview.pptx
Cloud AI GenAI Overview.pptx
 
Building Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon LexBuilding Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon Lex
 
Cloud-Native Roadshow - Google - Seattle
Cloud-Native Roadshow - Google - Seattle Cloud-Native Roadshow - Google - Seattle
Cloud-Native Roadshow - Google - Seattle
 
Java And Community Support
Java And Community SupportJava And Community Support
Java And Community Support
 
Sentiment Analysis Using Solr
Sentiment Analysis Using SolrSentiment Analysis Using Solr
Sentiment Analysis Using Solr
 
God Mode for designing scenario-driven skills for DeepPavlov Dream
God Mode for designing scenario-driven skills for DeepPavlov DreamGod Mode for designing scenario-driven skills for DeepPavlov Dream
God Mode for designing scenario-driven skills for DeepPavlov Dream
 
5 Keys to API Design - API Days Paris 2013
5 Keys to API Design - API Days Paris 20135 Keys to API Design - API Days Paris 2013
5 Keys to API Design - API Days Paris 2013
 
Ask me anything: A Conversational Interface to Augment Information Security w...
Ask me anything:A Conversational Interface to Augment Information Security w...Ask me anything:A Conversational Interface to Augment Information Security w...
Ask me anything: A Conversational Interface to Augment Information Security w...
 
Otto AI
Otto AIOtto AI
Otto AI
 

Último

PLE-statistics document for primary schs
PLE-statistics document for primary schsPLE-statistics document for primary schs
PLE-statistics document for primary schs
cnajjemba
 
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...
gajnagarg
 
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Klinik kandungan
 
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
gajnagarg
 
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
nirzagarg
 
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
nirzagarg
 
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
Bertram Ludäscher
 
怎样办理圣路易斯大学毕业证(SLU毕业证书)成绩单学校原版复制
怎样办理圣路易斯大学毕业证(SLU毕业证书)成绩单学校原版复制怎样办理圣路易斯大学毕业证(SLU毕业证书)成绩单学校原版复制
怎样办理圣路易斯大学毕业证(SLU毕业证书)成绩单学校原版复制
vexqp
 
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
gajnagarg
 
Jual Cytotec Asli Obat Aborsi No. 1 Paling Manjur
Jual Cytotec Asli Obat Aborsi No. 1 Paling ManjurJual Cytotec Asli Obat Aborsi No. 1 Paling Manjur
Jual Cytotec Asli Obat Aborsi No. 1 Paling Manjur
ptikerjasaptiker
 
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
nirzagarg
 
怎样办理旧金山城市学院毕业证(CCSF毕业证书)成绩单学校原版复制
怎样办理旧金山城市学院毕业证(CCSF毕业证书)成绩单学校原版复制怎样办理旧金山城市学院毕业证(CCSF毕业证书)成绩单学校原版复制
怎样办理旧金山城市学院毕业证(CCSF毕业证书)成绩单学校原版复制
vexqp
 
Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1
ranjankumarbehera14
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 

Último (20)

DATA SUMMIT 24 Building Real-Time Pipelines With FLaNK
DATA SUMMIT 24  Building Real-Time Pipelines With FLaNKDATA SUMMIT 24  Building Real-Time Pipelines With FLaNK
DATA SUMMIT 24 Building Real-Time Pipelines With FLaNK
 
PLE-statistics document for primary schs
PLE-statistics document for primary schsPLE-statistics document for primary schs
PLE-statistics document for primary schs
 
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...
 
Digital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareDigital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham Ware
 
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
 
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
 
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
 
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
 
怎样办理圣路易斯大学毕业证(SLU毕业证书)成绩单学校原版复制
怎样办理圣路易斯大学毕业证(SLU毕业证书)成绩单学校原版复制怎样办理圣路易斯大学毕业证(SLU毕业证书)成绩单学校原版复制
怎样办理圣路易斯大学毕业证(SLU毕业证书)成绩单学校原版复制
 
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
 
Jual Cytotec Asli Obat Aborsi No. 1 Paling Manjur
Jual Cytotec Asli Obat Aborsi No. 1 Paling ManjurJual Cytotec Asli Obat Aborsi No. 1 Paling Manjur
Jual Cytotec Asli Obat Aborsi No. 1 Paling Manjur
 
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
 
SR-101-01012024-EN.docx Federal Constitution of the Swiss Confederation
SR-101-01012024-EN.docx  Federal Constitution  of the Swiss ConfederationSR-101-01012024-EN.docx  Federal Constitution  of the Swiss Confederation
SR-101-01012024-EN.docx Federal Constitution of the Swiss Confederation
 
怎样办理旧金山城市学院毕业证(CCSF毕业证书)成绩单学校原版复制
怎样办理旧金山城市学院毕业证(CCSF毕业证书)成绩单学校原版复制怎样办理旧金山城市学院毕业证(CCSF毕业证书)成绩单学校原版复制
怎样办理旧金山城市学院毕业证(CCSF毕业证书)成绩单学校原版复制
 
Aspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraAspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - Almora
 
Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1
 
7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.ppt7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.ppt
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
 

kornev.pdf

  • 1. FROM ALEXA PRIZE SOCIALBOT TO MULTISKILL AI ASSISTANT PLATFORM Daniel Kornev, CPO @ DeepPavlov.ai
  • 3. DeepPavlov.ai Little Problem: Poor Usability* * Intelligent Assistants Have Poor Usability, Nielsen Norman Group © 2018
  • 4. DeepPavlov.ai Good* Bad Bad Bad Terrible Soon to be great Hard to do Limited by design Super hard to do Needs lot of work UI Technique Status Potential * For Non-native English speakers it’s still a pain Voice Input Natural Language Understanding Voice Output Intelligent Interpretation Agency
  • 5. DeepPavlov.ai Bad Bad Terrible Hard to do Super hard to do Needs lot of work UI Technique Status Potential * More of an engineering problem Natural Language Understanding Intelligent Interpretation Agency*
  • 6. DeepPavlov.ai It’s an NLP’s Holy Grail: human-like comprehension of texts & languages
  • 7. DeepPavlov.ai How to Get The Holy Grail? Challenge!
  • 8.
  • 9. DeepPavlov.ai What Is Alexa Prize? The Alexa Prize is a global competition for university students dedicated to accelerating the field of conversational AI. Teams of university students will develop a socialbot, an Alexa skill that converses with users on popular societal topics. The grand challenge for the Alexa Prize is to create a socialbot that can engage in a fun, high quality conversation on popular societal topics for 20 minutes and achieve an average rating of at least 4.0/5.0.
  • 10. DeepPavlov.ai DREAM socialbot architecture 1. Multiple Annotators are used to extract information from the user input. 2. Skill Selector defines a subset of active Skills based on the extracted information. 3. Selected Skills propose their response candidates. 4. Finally, Response Selector picks a response to be sent to Response Annotators and, eventually, to the user. All elements of the pipeline are running asynchronously with two points of synchronization: Skill Selector and Response Selector. Dialogue State serves as a shared memory.
  • 11. DeepPavlov.ai DREAM socialbot infrastructure 1. The core of the DREAM socialbot is implemented with DeepPavlov Agent (DP-Agent) framework. It orchestrates services for Skills, Annotators, Skill Selector and Response Selector, and is located on AWS EC2 instances with Docker Swarm. 2. Dialogue State history is stored on a separate instance with MongoDB. 3. AWS Lambda performs HTTP requests to the DREAM- agent by sending ASR tokens. 4. Testing infrastructure consists of Telegram bots for interacting with the dev version of the socialbot or with selected conversational skill only. 5. Dialogue analytics tool and dashboard were located on a separate EC2 instance. 6. Cluster and application monitoring had configured alerts to email and Slack.
  • 12. DeepPavlov.ai DeepPavlov Ecosystem ▪ Open repository of NLP models and pipelines • easy to find and reuse NLP components for development of new skills or extension of existing ▪ Open repository of conversational skills • alternative implementations of the most popular skills ▪ Open hub for AI Assistant distributions • general and domainindustry specific distributions of skill sets
  • 13. DeepPavlov.ai Conversational AI DeepPavlov Stack 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
  • 14. DeepPavlov.ai HOW TO BUILD MULTISKILL AI ASSISTANT WITH DEEPPAVLOV LIVING IN PANDEMICS MAKES US LONELY Wouldn’t it be nice to have a friend to care about us?
  • 15. DeepPavlov.ai MEET GERTY 3000 Can help Sam with problems on the Moon Base Sarang? Can entertain Sam? Yes ✔ Yes ✔ Can we emulate it with DeepPavlov DREAM? Yes ✔ Main Question Functionality Analysis Case: Gerty In the Moon Movie
  • 16. DeepPavlov.ai Text OR Voice Input TTS (NeMo) Deepy: Example Architecture Spell Checking NeMo ASR Harvesters Status Chit-Chat (AIML) Emotion BUILT-IN SKILL SELECTOR RULE-BASED RESPONSE SELECTOR
  • 17. DeepPavlov.ai services: agent: [..] depends_on: - mongo harvesters_maintenance_skill: [..] mongo: [..] rule_based_response_selector: [..] nemo: [..] depends_on: - agent emotion_classification: [..] program_y: [..] spell_checking: [..] Deepy: Docker Pipeline Spell Checking Annotators Emotion Classification Harvesters Status Skill Skills Chit-Chat Skill NeMo ASR & TTS Other Services Rule-Based Response Selector
  • 18. DeepPavlov.ai services: agent: [..] depends_on: - mongo harvesters_maintenance_skill: [..] mongo: [..] rule_based_response_selector: [..] nemo: [..] depends_on: - agent emotion_classification: [..] program_y: [..] clone_tts: [..] Deepy: Part of Agent Pipeline Annotators Services Are in Groups Skills Response Annotators Depend on groups (e.g., “skills”) Services Are Isolated Limited in what they see in dialog Invoke Agent’s State Manager Can run via HTTP or be Python-based "skills": { "harvesters_maintenance_skill": { "connector": { "protocol": "http", "url": "http://harvesters_maintenance _skill:3002/respond" }, "dialog_formatter": "dp_formatters:ful l_dialog", "response_formatter": "dp_formatters:b ase_skill_formatter", "state_manager_method": "add_hypothesi s", "previous_services": ["annotators"] }, Response Selectors
  • 19. DeepPavlov.ai Deepy: HarvMaint.: Configs What is (all) harvesters’ status? Intents What is harvester status? Prepare rover for a trip domain.yml intents: - all_statuses_request - status_request [..] - trip_request responses: utter_status_request: - text: "The harvester {harv_id} is {harv_status}.“ [..] nlu.md ## intent:all_statuses_request - What is the harvesters status? - What is the combines status? [..] stories.md ## harv_status + prepare_trip * status_request - utter_status_request stories.md – training for dialogs RASA Configs nlu.md – training for intents & slots domain.yml – basic ontology for skill Simple and easy to use
  • 20. DeepPavlov.ai Deepy: Chit-Chat Skill (AIML) <?xml version="1.0" encoding="UTF-8"?> <aiml version="2.0"> <category> <pattern>I AM ^ TIRED</pattern> <template> 🙁 <random> <li>Get some sleep<get name="name"/>. You're very tired.</li> <li>Have a rest and be happy! How can I help you?</li> </random> </template> </category> [..] </aiml> </xml> Assistant Profile (Name, Place, etc.) Patterns Greeting scenario Topics Looks up for patterns Dialog Processing Picks random pre-defined response If not sure, confidence is low (0.2) Returns response + confidence
  • 21. DeepPavlov.ai Deepy 3000: Demo A prototype of a fictional Moonbase A.I. Assistant, inspired by the Moon Movie (2009) made by Duncan Jones