MerIt: improving neural program synthesis by merging collective intelligence

Program synthesis is the task of automatically generating programs from user intent, which is one of the central problems in automated software engineering. Recently many researchers use a neural network to learn the distribution over programs based on user intent (such as API and type name), known...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Automated software engineering Ročník 29; číslo 2; s. 45
Hlavní autori: Zhang, Yating, Wang, Daiyan, Dong, Wei
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.11.2022
Springer Nature B.V
Predmet:
Algorithms
Ant colony optimization
Artificial Intelligence
Automation
Computer Science
Intelligence (information)
Neural networks
Software engineering
Software Engineering/Programming and Operating Systems
Synthesis
Neural program synthesis
Collective intelligence
Swarm intelligence
User intent
Pattern mining
ISSN:0928-8910, 1573-7535
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Program synthesis is the task of automatically generating programs from user intent, which is one of the central problems in automated software engineering. Recently many researchers use a neural network to learn the distribution over programs based on user intent (such as API and type name), known as neural program synthesis (NPS). The generated programs of NPS are highly dependent on user intent. However, it is difficult for users to provide an accurate and complete intent for the NPS model, which decreases the synthesis accuracy of NPS. Collective Intelligence (CI) is an emerging trend, which illustrates that collective wisdom surpasses individual wisdom. Inspired by CI techniques, we propose an automatic task-specific user intent merging framework for NPS named MerIt ( Mer ge User I n t ent of Program Synthesis). The key point of our framework is that we propose an improved Unsupervised Ant Colony Optimization (UACO) algorithm to selectively merge effective intent from multiple developers, and design three selection strategies to guide the merge process. The experiments show that our approach is able to provide more adequate and efficient input for NPS and improve the synthesis accuracy. Besides, our evaluation shows that selectively merging knowledge from multiple developers could be a significant way of promoting automated software engineering.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0928-8910
1573-7535
DOI:10.1007/s10515-022-00343-z