Grant: Discovery Grants Program - Individual
École Polytechnique de Montréal
$46,000.00
Intention Driven Development: Towards a new generation of development platforms
FY 2024-25
Summary
According to Canada Job Bank, the post-pandemic economy will witness a huge shortage of skilled workers with software engineers and designers topping the figures. To deal with the shortage, Gartner, Inc. predicts a paradigm shift powered by low-code platforms that support rapid assembly of new apps using prebuilt reusable components (a.k.a, composable architectures) to open the opportunity to a new class of technically minded line-of-business developers called "citizen developers". However, recent studies on challenges of low-code development show that low-code platforms limit creativity, as solutions are limited by the capabilities of the selected low-code languages. Moreover, the need to learn the syntax of the new low-code languages creates a knowledge barrier between what citizen developers needs and their ability to express these needs in the language syntax.
To address these challenges, my long-term goal is to investigate and build novel model synthesis and conceptualization approaches and tools by leveraging language models and harnessing human-in-the-loop feedback to enable citizen developers to organize and translate their ideas into low-code (models) despite their lack of familiarity with the syntax of the low-code language, an approach I call Intention Driven Development (IDD). In the short term, my research team and I will examine if Model by Conversation can be combined with Model by Example to break the knowledge barrier between citizen developers' design intentions and the actual low-code syntax. Our hypothesis is that a new hybrid (open and task-oriented) conversational dialogue architecture can break this barrier, using pre-trained large language models to learn low-code syntax from few shot examples, which are then refined by human-in-the-loop feedback that improves the composable architecture models.
In this program, I will use my experience in domain-specific languages and chatbots to train two PhD and four Master's students. For short-term objectives: I will start by (i) empirically investigating the challenges of creative design in dialogue-based low-code development to develop guidelines for selecting proper design examples. Then, (ii) I will build a dialogue modelling agent that utilize modern language learning approaches (e.g. transformer architectures) for incorporating the domain knowledge embodied in the low-code meta-models and previous modelling scenarios and examples to interpret citizen developers' ideas into a predefined target low-code syntax. Finally, to accommodate low-code evolution, (iii) I will investigate machine translation approaches to facilitate low-code DSL's artifact co-evolution (e.g., model-to-text templates evolution as a result of meta-model update).
As Canada struggles to fill its 200,000 job vacancies in 2022, including many in the IT sector, IDD may have a transformative socio-economic impact, immediately easing the HQP shortage problem - one of the most pressing in Canadian labour markets.
Program
Discovery Grants Program - Individual
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
RGPIN-2023-05484
Name nom
Hamdaqa, Mohammad
Department département
Computer Engineering and Software Engineering
Organization id
64
Institution établissement
École Polytechnique de Montréal
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
46000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2706
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Software engineering
Research subject fr
Génie logiciel
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Intention Driven Development: Towards a new generation of development platforms
Keywords
modelling by example; modelling by conversation; human-in-the-loop design; empirical software engineering; domain specific modelling; low code development; model driven engineering; requirements engineering; automatic model transformation; automatic code generation
Application summary
According to Canada Job Bank, the post-pandemic economy will witness a huge shortage of skilled workers with software engineers and designers topping the figures. To deal with the shortage, Gartner, Inc. predicts a paradigm shift powered by low-code platforms that support rapid assembly of new apps using prebuilt reusable components (a.k.a, composable architectures) to open the opportunity to a new class of technically minded line-of-business developers called "citizen developers". However, recent studies on challenges of low-code development show that low-code platforms limit creativity, as solutions are limited by the capabilities of the selected low-code languages. Moreover, the need to learn the syntax of the new low-code languages creates a knowledge barrier between what citizen developers needs and their ability to express these needs in the language syntax.
To address these challenges, my long-term goal is to investigate and build novel model synthesis and conceptualization approaches and tools by leveraging language models and harnessing human-in-the-loop feedback to enable citizen developers to organize and translate their ideas into low-code (models) despite their lack of familiarity with the syntax of the low-code language, an approach I call Intention Driven Development (IDD). In the short term, my research team and I will examine if Model by Conversation can be combined with Model by Example to break the knowledge barrier between citizen developers' design intentions and the actual low-code syntax. Our hypothesis is that a new hybrid (open and task-oriented) conversational dialogue architecture can break this barrier, using pre-trained large language models to learn low-code syntax from few shot examples, which are then refined by human-in-the-loop feedback that improves the composable architecture models.
In this program, I will use my experience in domain-specific languages and chatbots to train two PhD and four Master's students. For short-term objectives: I will start by (i) empirically investigating the challenges of creative design in dialogue-based low-code development to develop guidelines for selecting proper design examples. Then, (ii) I will build a dialogue modelling agent that utilize modern language learning approaches (e.g. transformer architectures) for incorporating the domain knowledge embodied in the low-code meta-models and previous modelling scenarios and examples to interpret citizen developers' ideas into a predefined target low-code syntax. Finally, to accommodate low-code evolution, (iii) I will investigate machine translation approaches to facilitate low-code DSL's artifact co-evolution (e.g., model-to-text templates evolution as a result of meta-model update).
As Canada struggles to fill its 200,000 job vacancies in 2022, including many in the IT sector, IDD may have a transformative socio-economic impact, immediately easing the HQP shortage problem - one of the most pressing in Canadian labour markets.