SlideShare a Scribd company logo
1 of 29
Download to read offline
AI for Software Engineering:
Research & Innovation
Oleksandr ZAITSEV
Universidad Católica Boliviana
oleksandr.zaitsev@cirad.fr
UMR SENS, CIRAD, Montpellier, France
About me
Part 1:
3
Who am I?
4
Who am I?
MSc. in Data Science
Ukrainian Catholic University
Lviv, Ukraine
5
Who am I?
MSc. in Data Science
Ukrainian Catholic University
Lviv, Ukraine
PhD. in Informatics
Inria, Univ. Lille, CNRS, CRIStAL
Lille, France
(use AI to help programmers)
6
Who am I?
MSc. in Data Science
Ukrainian Catholic University
Lviv, Ukraine
PhD. in Informatics
Inria, Univ. Lille, CNRS, CRIStAL
Lille, France
Researcher of Informatics
CIRAD, UMR SENS
Montpellier, France
(use AI to help programmers)
(use SE & AI to help farmers)
🌾
7
Who am I?
MSc. in Data Science
Ukrainian Catholic University
Lviv, Ukraine
PhD. in Informatics
Inria, Univ. Lille, CNRS, CRIStAL
Lille, France
Researcher of Informatics
CIRAD, UMR SENS
Montpellier, France
(use AI to help programmers)
(use SE & AI to help farmers)
🌾
Today we
talk
about this
8
Pharo open-source community
Pharo is a pure object-oriented
dynamically-typed programming
language.
Projects that I contribute to:
1. Cormas
2. pharo-ai
3. DataFrame
4. PolyMath
I have been a member of
the Pharo community for 6 years
(since university)
Cochabamba 🙂
Dayne Guerra Calle
Juan Pablo Sandoval
Evelyn Cusi Lopez
Sebastian Jordan Montaño
Milton Mammani Torrez
Andreina Cota Vidaurre
DrTests, Intern at Inria
Google Summer of Code
Engineer at Inria
Pharo-ai, graph algos
Research in profiling
Engineer at Inria
Roassal Guru
Refactoring Tools
Google Summer of Code
Research on genetic
test generation
Assistant Prof. at Chile
Software Evolution,
Dynamic Analysis
Daniel Campuzano
Intern at Inria
Object-centric debugging
9
10
The goal of my talk
Motivate you to do research
Help you discover some interesting research topics
Introduce you to our research groups
🌱
😎
👀
Part 2:
AI for Software
Engineering
12
What is software engineering?
Software Engineering (SE) is the branch of computer
science that deals with the design, development,
testing, and maintenance of software.
👩🎨 👩💻 👩⚕ 👩🔧
Design Develop Test Maintain
13
Things to understand
Every software has to evolve
🐵
More complexity → less quality
🤬
14
Software is code & code is data
Tabular dataset Code & AST
🧈 🥓🥚
🥖🥓 🥚
🥖🧈 🥓 🥚
🥖🧈 🥑
🥖🧈 🍌
15
Market basket analysis
Customer 1:
Customer 2:
Customer 3:
Customer 4:
Customer 5:
Transactions:
Q1: What are the products that are
frequently purchased together?
Q2: What can we recommend to
people who buy bread?
16
Market basket analysis
Customer 1:
Customer 2:
Customer 3:
Customer 4:
Customer 5:
Transactions:
Q1: What are the products that are
frequently purchased together?
Q2: What can we recommend to
people who buy bread?
Con
fi
dence: 75%
Support: 60%
Support: 60%
🥖🧈 🍌
🥖🧈 🥑 🥖 🧈
🥓
🥖 🧈
🥚
🥖🧈 🥓 🥚
🥖🥓 🥚
🧈 🥓🥚
17
Library update problem
Updated
Client
System
Client
System
Library
v1.0
Library
v2.0
Client
Developer
Library
Developer
depends
Library Evolution
Library Update
18
Data mining for library update
Zaitsev O, Ducasse S, Anquetil N, Thiefaine A. DepMiner: Automatic
Recommendation of Transformation Rules for Method Deprecation. InICSR
2022-20th International Conference on Software and System Reuse 2022 Jun 15.
📄
Oleksandr
Zaitsev
Stéphane
Ducasse
Nicolas
Anquetil
Arnaud
Tiefaine
Q1: What are the operations that frequently
appear together in the commit history?
Q2: What is a good replacement for method next() ?
next() nextNode()
Con
fi
dence: 75%
remove(next), add(nextNode)
Support: 60%
19
Genetic algorithms
20
Genetic test generation
Vidaure AC, Lopez EC, Alcocer JP, Bergel A.TestEvoViz: Visual
Introspection for Genetically-Based Test Coverage Evolution.
In VISSOFT 2020
📄
Juan Pablo
Sandoval
Alexandre
Bergel
Andreina
Cota Vidaurre
Evelyn
Cusi Lopez
21
Seq-2-seq neural networks
Encoded
Vector
the cat is black
Encoded
Vector
<s> le chat
est
chat
le
est
noir
Decoder:
Encoder:
noir
<s>
22
Text summarisation
Text:
French authorities have placed seven more
departments covering major cities such as Lille,
Strasbourg and Dijon on high alert as increases
in Covid-19 infections accelerate, the
government said Sunday. Of France's 101
mainland and overseas departments, 28 are now
considered "red zones" where authorities will be
able to impose exceptional measures to slow
the number of new coronavirus cases. The move
comes as France reported a record of nearly
9,000 daily cases on Friday, and a further 8,550
cases in the past 24 hours on Saturday, when the
nationwide test positivity rate increased to 4.7
percent…
Summary:
France puts more departments
on Covid high alert
23
Generate names with neural nets
Oleksandr
Zaitsev
Alexandre
Bergel
Stéphane
Ducasse
Mathieu
Eveilard
Zaitsev, O., Ducasse, S., Bergel, A. and Eveillard, M., 2020, September. Suggesting
Descriptive Method Names: An Exploratory Study of Two Machine Learning Approaches.
In International Conference on the Quality of Information and Communications
Technology (pp. 93-106). Springer, Cham.
📄
Source code (body of a method):
// sum numbers of a collection
sum = 0
this apply: (each) -> {
sum = each + sum }
return sum
Method name:
sum
Text
Short summary
24
N-gram language models
25
Code completion with N-grams
Myroslava
Romaniuk
Oleksandr
Zaitsev
Marcus
Denker
Romaniuk, Myroslava. "Improving Code Completion in Pharo Using N-gram Language
Models." Bachelor thesis, Ukrainian Catholic University, 2020.
📄
26
And much more…
Allamanis M, Barr ET, Devanbu P, Sutton C. A survey of
machine learning for big code and naturalness. ACM
Computing Surveys (CSUR). 2018 Jul 31;51(4):1-37.
📄
Part 3:
Conclusion
28
Our research groups
RMoD team at Inria Unit SENS at CIRAD
✓ Software evolution
✓ Software analysis
✓ Software comprehension
✓ Virtual machines
✓ Programming languages
✓ Agent-based modelling
✓ Multi-agent systems
✓ Agriculture
✓ Ecology
✓ Anthropology
https://umr-sens.fr/
https://rmod.inria.fr/
Get in touch
https://github.com/olekscode
https://www.facebook.com/i.oleks
oleksandr.zaitsev@cirad.fr
https://scholar.google.com/citations?
user=slO6qqMAAAAJ
Oleksandr
Zaitsev

More Related Content

Similar to AI for Software Engineering:
Research & Innovation

Daniel Preotiuc-Pietro - 2015 - An analysis of the user occupational class th...
Daniel Preotiuc-Pietro - 2015 - An analysis of the user occupational class th...Daniel Preotiuc-Pietro - 2015 - An analysis of the user occupational class th...
Daniel Preotiuc-Pietro - 2015 - An analysis of the user occupational class th...Association for Computational Linguistics
 
Machine Learning Final presentation
Machine Learning Final presentation Machine Learning Final presentation
Machine Learning Final presentation AyanaRukasar
 
Cheminformatics Software Development: Case Studies
Cheminformatics Software Development: Case StudiesCheminformatics Software Development: Case Studies
Cheminformatics Software Development: Case StudiesJeremy Yang
 
HealthBIO 2021_PerkinElmer, leading with innovation - from COVID success into...
HealthBIO 2021_PerkinElmer, leading with innovation - from COVID success into...HealthBIO 2021_PerkinElmer, leading with innovation - from COVID success into...
HealthBIO 2021_PerkinElmer, leading with innovation - from COVID success into...Business Turku
 
How to Use Open Source Technologies in Safety-critical Medical Device Platforms
How to Use Open Source Technologies in Safety-critical Medical Device PlatformsHow to Use Open Source Technologies in Safety-critical Medical Device Platforms
How to Use Open Source Technologies in Safety-critical Medical Device PlatformsShahid Shah
 
The Innovation Commercialization Process: A Case Study
The Innovation Commercialization Process:A Case StudyThe Innovation Commercialization Process:A Case Study
The Innovation Commercialization Process: A Case StudyCheryl Tulkoff
 
40 Artificial Intelligence Companies Improving Healthcare (I-Square Ventures)
40 Artificial Intelligence Companies Improving Healthcare (I-Square Ventures)40 Artificial Intelligence Companies Improving Healthcare (I-Square Ventures)
40 Artificial Intelligence Companies Improving Healthcare (I-Square Ventures)Chiranjeev Bordoloi
 
IT Cluster Skolkovo Presentation at FRUCT.org conference
IT Cluster Skolkovo Presentation at FRUCT.org conferenceIT Cluster Skolkovo Presentation at FRUCT.org conference
IT Cluster Skolkovo Presentation at FRUCT.org conferenceAlbert Yefimov
 
Covid 19 Prediction in India using Machine Learning
Covid 19 Prediction in India using Machine LearningCovid 19 Prediction in India using Machine Learning
Covid 19 Prediction in India using Machine LearningYogeshIJTSRD
 
E biothon workshop 2014 04 15 v1
E biothon workshop 2014 04 15 v1E biothon workshop 2014 04 15 v1
E biothon workshop 2014 04 15 v1Vincent Breton
 
Software Sustainability: Better Software Better Science
Software Sustainability: Better Software Better ScienceSoftware Sustainability: Better Software Better Science
Software Sustainability: Better Software Better ScienceCarole Goble
 
Make Sense Out of Data with Feature Engineering
Make Sense Out of Data with Feature EngineeringMake Sense Out of Data with Feature Engineering
Make Sense Out of Data with Feature EngineeringDataRobot
 
Presentation for lama.pptx
Presentation for lama.pptxPresentation for lama.pptx
Presentation for lama.pptxAdityaNath38
 
Rare diseases and cross border patient data access
Rare diseases and cross border patient data accessRare diseases and cross border patient data access
Rare diseases and cross border patient data accessbndmr
 
"Machine Learning and Internet of Things, the future of medical prevention", ...
"Machine Learning and Internet of Things, the future of medical prevention", ..."Machine Learning and Internet of Things, the future of medical prevention", ...
"Machine Learning and Internet of Things, the future of medical prevention", ...Dataconomy Media
 
How to Use Open Source Technologies in Safety-critical Digital Health Applica...
How to Use Open Source Technologies in Safety-critical Digital Health Applica...How to Use Open Source Technologies in Safety-critical Digital Health Applica...
How to Use Open Source Technologies in Safety-critical Digital Health Applica...Shahid Shah
 
Pistoia Alliance Debates: Clinical trials and wearables, 21st Jan 2016
Pistoia Alliance Debates: Clinical trials and wearables, 21st Jan 2016Pistoia Alliance Debates: Clinical trials and wearables, 21st Jan 2016
Pistoia Alliance Debates: Clinical trials and wearables, 21st Jan 2016Pistoia Alliance
 

Similar to AI for Software Engineering:
Research & Innovation (20)

Daniel Preotiuc-Pietro - 2015 - An analysis of the user occupational class th...
Daniel Preotiuc-Pietro - 2015 - An analysis of the user occupational class th...Daniel Preotiuc-Pietro - 2015 - An analysis of the user occupational class th...
Daniel Preotiuc-Pietro - 2015 - An analysis of the user occupational class th...
 
Machine Learning Final presentation
Machine Learning Final presentation Machine Learning Final presentation
Machine Learning Final presentation
 
Cheminformatics Software Development: Case Studies
Cheminformatics Software Development: Case StudiesCheminformatics Software Development: Case Studies
Cheminformatics Software Development: Case Studies
 
HealthBIO 2021_PerkinElmer, leading with innovation - from COVID success into...
HealthBIO 2021_PerkinElmer, leading with innovation - from COVID success into...HealthBIO 2021_PerkinElmer, leading with innovation - from COVID success into...
HealthBIO 2021_PerkinElmer, leading with innovation - from COVID success into...
 
How to Use Open Source Technologies in Safety-critical Medical Device Platforms
How to Use Open Source Technologies in Safety-critical Medical Device PlatformsHow to Use Open Source Technologies in Safety-critical Medical Device Platforms
How to Use Open Source Technologies in Safety-critical Medical Device Platforms
 
The Innovation Commercialization Process: A Case Study
The Innovation Commercialization Process:A Case StudyThe Innovation Commercialization Process:A Case Study
The Innovation Commercialization Process: A Case Study
 
40 Artificial Intelligence Companies Improving Healthcare (I-Square Ventures)
40 Artificial Intelligence Companies Improving Healthcare (I-Square Ventures)40 Artificial Intelligence Companies Improving Healthcare (I-Square Ventures)
40 Artificial Intelligence Companies Improving Healthcare (I-Square Ventures)
 
DC_OC15_mo
DC_OC15_moDC_OC15_mo
DC_OC15_mo
 
IT Cluster Skolkovo Presentation at FRUCT.org conference
IT Cluster Skolkovo Presentation at FRUCT.org conferenceIT Cluster Skolkovo Presentation at FRUCT.org conference
IT Cluster Skolkovo Presentation at FRUCT.org conference
 
Covid 19 Prediction in India using Machine Learning
Covid 19 Prediction in India using Machine LearningCovid 19 Prediction in India using Machine Learning
Covid 19 Prediction in India using Machine Learning
 
E biothon workshop 2014 04 15 v1
E biothon workshop 2014 04 15 v1E biothon workshop 2014 04 15 v1
E biothon workshop 2014 04 15 v1
 
Software Sustainability: Better Software Better Science
Software Sustainability: Better Software Better ScienceSoftware Sustainability: Better Software Better Science
Software Sustainability: Better Software Better Science
 
2015 genome-center
2015 genome-center2015 genome-center
2015 genome-center
 
Make Sense Out of Data with Feature Engineering
Make Sense Out of Data with Feature EngineeringMake Sense Out of Data with Feature Engineering
Make Sense Out of Data with Feature Engineering
 
Presentation for lama.pptx
Presentation for lama.pptxPresentation for lama.pptx
Presentation for lama.pptx
 
C4l 2008
C4l 2008C4l 2008
C4l 2008
 
Rare diseases and cross border patient data access
Rare diseases and cross border patient data accessRare diseases and cross border patient data access
Rare diseases and cross border patient data access
 
"Machine Learning and Internet of Things, the future of medical prevention", ...
"Machine Learning and Internet of Things, the future of medical prevention", ..."Machine Learning and Internet of Things, the future of medical prevention", ...
"Machine Learning and Internet of Things, the future of medical prevention", ...
 
How to Use Open Source Technologies in Safety-critical Digital Health Applica...
How to Use Open Source Technologies in Safety-critical Digital Health Applica...How to Use Open Source Technologies in Safety-critical Digital Health Applica...
How to Use Open Source Technologies in Safety-critical Digital Health Applica...
 
Pistoia Alliance Debates: Clinical trials and wearables, 21st Jan 2016
Pistoia Alliance Debates: Clinical trials and wearables, 21st Jan 2016Pistoia Alliance Debates: Clinical trials and wearables, 21st Jan 2016
Pistoia Alliance Debates: Clinical trials and wearables, 21st Jan 2016
 

More from Oleksandr Zaitsev

Cormas: Modelling for Citizens with Citizens. Building accessible and reliabl...
Cormas: Modelling for Citizens with Citizens. Building accessible and reliabl...Cormas: Modelling for Citizens with Citizens. Building accessible and reliabl...
Cormas: Modelling for Citizens with Citizens. Building accessible and reliabl...Oleksandr Zaitsev
 
Agent-Based Modelling in Pharo Using Cormas
Agent-Based Modelling in Pharo Using CormasAgent-Based Modelling in Pharo Using Cormas
Agent-Based Modelling in Pharo Using CormasOleksandr Zaitsev
 
How Libraries Evolve. A Survey of Two Industrial Companies and an Open-Source...
How Libraries Evolve. A Survey of Two Industrial Companies and an Open-Source...How Libraries Evolve. A Survey of Two Industrial Companies and an Open-Source...
How Libraries Evolve. A Survey of Two Industrial Companies and an Open-Source...Oleksandr Zaitsev
 
Data Mining-based Tools to Support Library Update. PhD Defence of Oleksandr Z...
Data Mining-based Tools to Support Library Update. PhD Defence of Oleksandr Z...Data Mining-based Tools to Support Library Update. PhD Defence of Oleksandr Z...
Data Mining-based Tools to Support Library Update. PhD Defence of Oleksandr Z...Oleksandr Zaitsev
 
How Fast is AI in Pharo? Benchmarking Linear Regression
How Fast is AI in Pharo? Benchmarking Linear RegressionHow Fast is AI in Pharo? Benchmarking Linear Regression
How Fast is AI in Pharo? Benchmarking Linear RegressionOleksandr Zaitsev
 
DepMiner: Automatic Recommendation of Transformation Rules for Method Depreca...
DepMiner: Automatic Recommendation of Transformation Rules for Method Depreca...DepMiner: Automatic Recommendation of Transformation Rules for Method Depreca...
DepMiner: Automatic Recommendation of Transformation Rules for Method Depreca...Oleksandr Zaitsev
 
Suggesting Descriptive Method Names: An Exploratory Study of Two Machine Lear...
Suggesting Descriptive Method Names: An Exploratory Study of Two Machine Lear...Suggesting Descriptive Method Names: An Exploratory Study of Two Machine Lear...
Suggesting Descriptive Method Names: An Exploratory Study of Two Machine Lear...Oleksandr Zaitsev
 
Machine Learning-based Tools to Support Library Update
Machine Learning-based Tools to Support Library UpdateMachine Learning-based Tools to Support Library Update
Machine Learning-based Tools to Support Library UpdateOleksandr Zaitsev
 
Introduction to Git Version Control System
Introduction to Git Version Control SystemIntroduction to Git Version Control System
Introduction to Git Version Control SystemOleksandr Zaitsev
 
Aspects of software naturalness through the generation of IdentifierNames
Aspects of software naturalness through the generation of IdentifierNamesAspects of software naturalness through the generation of IdentifierNames
Aspects of software naturalness through the generation of IdentifierNamesOleksandr Zaitsev
 

More from Oleksandr Zaitsev (16)

Cormas: Modelling for Citizens with Citizens. Building accessible and reliabl...
Cormas: Modelling for Citizens with Citizens. Building accessible and reliabl...Cormas: Modelling for Citizens with Citizens. Building accessible and reliabl...
Cormas: Modelling for Citizens with Citizens. Building accessible and reliabl...
 
Cormas RMoD
Cormas RMoDCormas RMoD
Cormas RMoD
 
Cirad Parcours
Cirad ParcoursCirad Parcours
Cirad Parcours
 
Cirad Concours
Cirad ConcoursCirad Concours
Cirad Concours
 
Agent-Based Modelling in Pharo Using Cormas
Agent-Based Modelling in Pharo Using CormasAgent-Based Modelling in Pharo Using Cormas
Agent-Based Modelling in Pharo Using Cormas
 
How Libraries Evolve. A Survey of Two Industrial Companies and an Open-Source...
How Libraries Evolve. A Survey of Two Industrial Companies and an Open-Source...How Libraries Evolve. A Survey of Two Industrial Companies and an Open-Source...
How Libraries Evolve. A Survey of Two Industrial Companies and an Open-Source...
 
Data Mining-based Tools to Support Library Update. PhD Defence of Oleksandr Z...
Data Mining-based Tools to Support Library Update. PhD Defence of Oleksandr Z...Data Mining-based Tools to Support Library Update. PhD Defence of Oleksandr Z...
Data Mining-based Tools to Support Library Update. PhD Defence of Oleksandr Z...
 
PolyMath (ESUG 2022)
PolyMath (ESUG 2022)PolyMath (ESUG 2022)
PolyMath (ESUG 2022)
 
How Fast is AI in Pharo? Benchmarking Linear Regression
How Fast is AI in Pharo? Benchmarking Linear RegressionHow Fast is AI in Pharo? Benchmarking Linear Regression
How Fast is AI in Pharo? Benchmarking Linear Regression
 
DepMiner: Automatic Recommendation of Transformation Rules for Method Depreca...
DepMiner: Automatic Recommendation of Transformation Rules for Method Depreca...DepMiner: Automatic Recommendation of Transformation Rules for Method Depreca...
DepMiner: Automatic Recommendation of Transformation Rules for Method Depreca...
 
Suggesting Descriptive Method Names: An Exploratory Study of Two Machine Lear...
Suggesting Descriptive Method Names: An Exploratory Study of Two Machine Lear...Suggesting Descriptive Method Names: An Exploratory Study of Two Machine Lear...
Suggesting Descriptive Method Names: An Exploratory Study of Two Machine Lear...
 
Machine Learning-based Tools to Support Library Update
Machine Learning-based Tools to Support Library UpdateMachine Learning-based Tools to Support Library Update
Machine Learning-based Tools to Support Library Update
 
Introduction to Git Version Control System
Introduction to Git Version Control SystemIntroduction to Git Version Control System
Introduction to Git Version Control System
 
PhD Roadmap
PhD RoadmapPhD Roadmap
PhD Roadmap
 
Magic Literals in Pharo
Magic Literals in PharoMagic Literals in Pharo
Magic Literals in Pharo
 
Aspects of software naturalness through the generation of IdentifierNames
Aspects of software naturalness through the generation of IdentifierNamesAspects of software naturalness through the generation of IdentifierNames
Aspects of software naturalness through the generation of IdentifierNames
 

Recently uploaded

Building Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop SlideBuilding Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop SlideChristina Lin
 
chapter--4-software-project-planning.ppt
chapter--4-software-project-planning.pptchapter--4-software-project-planning.ppt
chapter--4-software-project-planning.pptkotipi9215
 
Intelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalmIntelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalmSujith Sukumaran
 
Professional Resume Template for Software Developers
Professional Resume Template for Software DevelopersProfessional Resume Template for Software Developers
Professional Resume Template for Software DevelopersVinodh Ram
 
Folding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesFolding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesPhilip Schwarz
 
software engineering Chapter 5 System modeling.pptx
software engineering Chapter 5 System modeling.pptxsoftware engineering Chapter 5 System modeling.pptx
software engineering Chapter 5 System modeling.pptxnada99848
 
Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024Andreas Granig
 
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...MyIntelliSource, Inc.
 
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...Christina Lin
 
Cloud Data Center Network Construction - IEEE
Cloud Data Center Network Construction - IEEECloud Data Center Network Construction - IEEE
Cloud Data Center Network Construction - IEEEVICTOR MAESTRE RAMIREZ
 
What is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need ItWhat is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need ItWave PLM
 
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...soniya singh
 
MYjobs Presentation Django-based project
MYjobs Presentation Django-based projectMYjobs Presentation Django-based project
MYjobs Presentation Django-based projectAnoyGreter
 
Implementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureImplementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureDinusha Kumarasiri
 
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed DataAlluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed DataAlluxio, Inc.
 
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...gurkirankumar98700
 
KnowAPIs-UnknownPerf-jaxMainz-2024 (1).pptx
KnowAPIs-UnknownPerf-jaxMainz-2024 (1).pptxKnowAPIs-UnknownPerf-jaxMainz-2024 (1).pptx
KnowAPIs-UnknownPerf-jaxMainz-2024 (1).pptxTier1 app
 
Salesforce Certified Field Service Consultant
Salesforce Certified Field Service ConsultantSalesforce Certified Field Service Consultant
Salesforce Certified Field Service ConsultantAxelRicardoTrocheRiq
 
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...stazi3110
 

Recently uploaded (20)

Building Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop SlideBuilding Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
 
chapter--4-software-project-planning.ppt
chapter--4-software-project-planning.pptchapter--4-software-project-planning.ppt
chapter--4-software-project-planning.ppt
 
Call Girls In Mukherjee Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
Call Girls In Mukherjee Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...Call Girls In Mukherjee Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
Call Girls In Mukherjee Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
 
Intelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalmIntelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalm
 
Professional Resume Template for Software Developers
Professional Resume Template for Software DevelopersProfessional Resume Template for Software Developers
Professional Resume Template for Software Developers
 
Folding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesFolding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a series
 
software engineering Chapter 5 System modeling.pptx
software engineering Chapter 5 System modeling.pptxsoftware engineering Chapter 5 System modeling.pptx
software engineering Chapter 5 System modeling.pptx
 
Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024
 
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
 
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...
 
Cloud Data Center Network Construction - IEEE
Cloud Data Center Network Construction - IEEECloud Data Center Network Construction - IEEE
Cloud Data Center Network Construction - IEEE
 
What is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need ItWhat is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need It
 
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
 
MYjobs Presentation Django-based project
MYjobs Presentation Django-based projectMYjobs Presentation Django-based project
MYjobs Presentation Django-based project
 
Implementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureImplementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with Azure
 
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed DataAlluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
 
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
 
KnowAPIs-UnknownPerf-jaxMainz-2024 (1).pptx
KnowAPIs-UnknownPerf-jaxMainz-2024 (1).pptxKnowAPIs-UnknownPerf-jaxMainz-2024 (1).pptx
KnowAPIs-UnknownPerf-jaxMainz-2024 (1).pptx
 
Salesforce Certified Field Service Consultant
Salesforce Certified Field Service ConsultantSalesforce Certified Field Service Consultant
Salesforce Certified Field Service Consultant
 
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
 

AI for Software Engineering:
Research & Innovation

  • 1. AI for Software Engineering: Research & Innovation Oleksandr ZAITSEV Universidad Católica Boliviana oleksandr.zaitsev@cirad.fr UMR SENS, CIRAD, Montpellier, France
  • 4. 4 Who am I? MSc. in Data Science Ukrainian Catholic University Lviv, Ukraine
  • 5. 5 Who am I? MSc. in Data Science Ukrainian Catholic University Lviv, Ukraine PhD. in Informatics Inria, Univ. Lille, CNRS, CRIStAL Lille, France (use AI to help programmers)
  • 6. 6 Who am I? MSc. in Data Science Ukrainian Catholic University Lviv, Ukraine PhD. in Informatics Inria, Univ. Lille, CNRS, CRIStAL Lille, France Researcher of Informatics CIRAD, UMR SENS Montpellier, France (use AI to help programmers) (use SE & AI to help farmers) 🌾
  • 7. 7 Who am I? MSc. in Data Science Ukrainian Catholic University Lviv, Ukraine PhD. in Informatics Inria, Univ. Lille, CNRS, CRIStAL Lille, France Researcher of Informatics CIRAD, UMR SENS Montpellier, France (use AI to help programmers) (use SE & AI to help farmers) 🌾 Today we talk about this
  • 8. 8 Pharo open-source community Pharo is a pure object-oriented dynamically-typed programming language. Projects that I contribute to: 1. Cormas 2. pharo-ai 3. DataFrame 4. PolyMath I have been a member of the Pharo community for 6 years (since university)
  • 9. Cochabamba 🙂 Dayne Guerra Calle Juan Pablo Sandoval Evelyn Cusi Lopez Sebastian Jordan Montaño Milton Mammani Torrez Andreina Cota Vidaurre DrTests, Intern at Inria Google Summer of Code Engineer at Inria Pharo-ai, graph algos Research in profiling Engineer at Inria Roassal Guru Refactoring Tools Google Summer of Code Research on genetic test generation Assistant Prof. at Chile Software Evolution, Dynamic Analysis Daniel Campuzano Intern at Inria Object-centric debugging 9
  • 10. 10 The goal of my talk Motivate you to do research Help you discover some interesting research topics Introduce you to our research groups 🌱 😎 👀
  • 11. Part 2: AI for Software Engineering
  • 12. 12 What is software engineering? Software Engineering (SE) is the branch of computer science that deals with the design, development, testing, and maintenance of software. 👩🎨 👩💻 👩⚕ 👩🔧 Design Develop Test Maintain
  • 13. 13 Things to understand Every software has to evolve 🐵 More complexity → less quality 🤬
  • 14. 14 Software is code & code is data Tabular dataset Code & AST
  • 15. 🧈 🥓🥚 🥖🥓 🥚 🥖🧈 🥓 🥚 🥖🧈 🥑 🥖🧈 🍌 15 Market basket analysis Customer 1: Customer 2: Customer 3: Customer 4: Customer 5: Transactions: Q1: What are the products that are frequently purchased together? Q2: What can we recommend to people who buy bread?
  • 16. 16 Market basket analysis Customer 1: Customer 2: Customer 3: Customer 4: Customer 5: Transactions: Q1: What are the products that are frequently purchased together? Q2: What can we recommend to people who buy bread? Con fi dence: 75% Support: 60% Support: 60% 🥖🧈 🍌 🥖🧈 🥑 🥖 🧈 🥓 🥖 🧈 🥚 🥖🧈 🥓 🥚 🥖🥓 🥚 🧈 🥓🥚
  • 18. 18 Data mining for library update Zaitsev O, Ducasse S, Anquetil N, Thiefaine A. DepMiner: Automatic Recommendation of Transformation Rules for Method Deprecation. InICSR 2022-20th International Conference on Software and System Reuse 2022 Jun 15. 📄 Oleksandr Zaitsev Stéphane Ducasse Nicolas Anquetil Arnaud Tiefaine Q1: What are the operations that frequently appear together in the commit history? Q2: What is a good replacement for method next() ? next() nextNode() Con fi dence: 75% remove(next), add(nextNode) Support: 60%
  • 20. 20 Genetic test generation Vidaure AC, Lopez EC, Alcocer JP, Bergel A.TestEvoViz: Visual Introspection for Genetically-Based Test Coverage Evolution. In VISSOFT 2020 📄 Juan Pablo Sandoval Alexandre Bergel Andreina Cota Vidaurre Evelyn Cusi Lopez
  • 21. 21 Seq-2-seq neural networks Encoded Vector the cat is black Encoded Vector <s> le chat est chat le est noir Decoder: Encoder: noir <s>
  • 22. 22 Text summarisation Text: French authorities have placed seven more departments covering major cities such as Lille, Strasbourg and Dijon on high alert as increases in Covid-19 infections accelerate, the government said Sunday. Of France's 101 mainland and overseas departments, 28 are now considered "red zones" where authorities will be able to impose exceptional measures to slow the number of new coronavirus cases. The move comes as France reported a record of nearly 9,000 daily cases on Friday, and a further 8,550 cases in the past 24 hours on Saturday, when the nationwide test positivity rate increased to 4.7 percent… Summary: France puts more departments on Covid high alert
  • 23. 23 Generate names with neural nets Oleksandr Zaitsev Alexandre Bergel Stéphane Ducasse Mathieu Eveilard Zaitsev, O., Ducasse, S., Bergel, A. and Eveillard, M., 2020, September. Suggesting Descriptive Method Names: An Exploratory Study of Two Machine Learning Approaches. In International Conference on the Quality of Information and Communications Technology (pp. 93-106). Springer, Cham. 📄 Source code (body of a method): // sum numbers of a collection sum = 0 this apply: (each) -> { sum = each + sum } return sum Method name: sum Text Short summary
  • 25. 25 Code completion with N-grams Myroslava Romaniuk Oleksandr Zaitsev Marcus Denker Romaniuk, Myroslava. "Improving Code Completion in Pharo Using N-gram Language Models." Bachelor thesis, Ukrainian Catholic University, 2020. 📄
  • 26. 26 And much more… Allamanis M, Barr ET, Devanbu P, Sutton C. A survey of machine learning for big code and naturalness. ACM Computing Surveys (CSUR). 2018 Jul 31;51(4):1-37. 📄
  • 28. 28 Our research groups RMoD team at Inria Unit SENS at CIRAD ✓ Software evolution ✓ Software analysis ✓ Software comprehension ✓ Virtual machines ✓ Programming languages ✓ Agent-based modelling ✓ Multi-agent systems ✓ Agriculture ✓ Ecology ✓ Anthropology https://umr-sens.fr/ https://rmod.inria.fr/