Multilingual training for Software Engineering
Authors:
- Toufique AhmedTAToufique Ahmed
- Premkumar DevanbuPDPremkumar Devanbu
Preprint
Abstract
Well-trained machine-learning models, which leverage large amounts of open-source software data, have now become an interesting approach to automating many software engineering tasks. Several SE tasks have all been subject to this approach, with performance gradually improving over the past several years with better models and training methods. More, and more diverse, clean, labeled data is better for training; but constructing good-quality datasets is time-consuming and challenging. Ways of augmenting the volume and diversity of clean, labeled data generally have wide applicability. For some languages (e.g., Ruby) labeled data is less abundant; in others (e.g., JavaScript) the available data maybe more focused on some application domains, and thus less diverse. As a way around such data bottlenecks, we present evidence suggesting that human-written code in different languages (which performs the same function), is rather similar, and particularly preserving of identifier naming patterns; we further present evidence suggesting that identifiers are a very important element of training data for software engineering tasks. We leverage this rather fortuitous phenomenon to find evidence that available multilingual training data (across different languages) can be used to amplify performance. We study this for 3 different tasks: code summarization, code retrieval, and function naming. We note that this data-augmenting approach is broadly compatible with different tasks, languages, and machine-learning models.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- SeCNN: A semantic CNN parser for code comment generationJournal of Systems and Software, 2021
- Ensemble Models for Neural Source Code Summarization of Subroutines2021
- Learning to Find Usages of Library Functions in Optimized BinariesIEEE Transactions on Software Engineering, 2021
- ComFormer: Code Comment Generation via Transformer and Fusion Method-based Hybrid Code Representation2021
- A Survey of Multilingual Neural Machine TranslationACM Computing Surveys, 2020
- Reinforcement-Learning-Guided Source Code Summarization Using Hierarchical AttentionIEEE Transactions on Software Engineering, 2020
- Deep code comment generation with hybrid lexical and syntactical informationEmpirical Software Engineering, 2019
- code2vec: learning distributed representations of codeProceedings of the ACM on Programming Languages, 2019
- Cliff´s Delta Calculator: A non-parametric effect size program for two groups of observationsUniversitas Psychologica, 2010
- Effective identifier names for comprehension and memoryInnovations in Systems and Software Engineering, 2007