Publications

Abstract # Background: Integrated Development Environments (IDEs) have become central to modern software development, offering features like code completion to boost developer productivity and efficiency. Code completion tools rely on predictive models to suggest relevant methods or functions as developers write code. While recent advances, such as the Pythia model, have leveraged natural language processing and recurrent neural networks (RNNs) with long short-term memory (LSTM) to improve prediction accuracy, these models tend to perform significantly better on Python’s standard libraries than on third-party libraries. This disparity arises because training datasets are typically dominated by standard library usage, leaving third-party libraries underrepresented and their code completion predictions less accurate.

Abstract # Background: Traditional compiler architectures, typically built with tightly coupled parsers and code generators, are difficult and expensive to maintain, especially when adapting to frequent changes or multiple variants of a programming language. This is particularly problematic for languages like IEEE-STD-716 ATLAS, which is widely used in test quality assurance and is subject to frequent modifications and customizations across different test stations and equipment.