# Aligning Programming Language and Natural Language: Exploring Design Choices in Multi-Modal Transformer-Based Embedding for Bug Localization

arXiv: https://arxiv.org/abs/2406.17615 · HTML: https://mlsanity.com/paper/2406.17615/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 45 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Builds on (most cited first, 9 of 9)

- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks](https://mlsanity.com/paper/1903.05987/) (2019)
- [How to Train BERT with an Academic Budget](https://mlsanity.com/paper/2104.07705/) (2021)
- [Making Transformers Solve Compositional Tasks](https://mlsanity.com/paper/2108.04378/) (2021)
- [Span Selection Pre-training for Question Answering](https://mlsanity.com/paper/1909.04120/) (2019)
- [Fault Localization with Code Coverage Representation Learning](https://mlsanity.com/paper/2103.00270/) (2021)
- [AutoTrans: Automating Transformer Design via Reinforced Architecture Search](https://mlsanity.com/paper/2009.02070/) (2020)
- [Grid Search Hyperparameter Benchmarking of BERT, ALBERT, and LongFormer on DuoRC](https://mlsanity.com/paper/2101.06326/) (2021)

## Abstract (arXiv)

Bug localization refers to the identification of source code files which is in a programming language and also responsible for the unexpected behavior of software using the bug report, which is a natural language. As bug localization is labor-intensive, bug localization models are employed to assist software developers. Due to the domain difference between source code files and bug reports, modern bug-localization systems, based on deep learning models, rely heavily on embedding techniques that project bug reports and source code files into a shared vector space. The creation of an embedding involves several design choices, but the impact of these choices on the quality of embedding and the performance of bug localization models remains unexplained in current research. To address this gap, our study evaluated 14 distinct embedding models to gain insights into the effects of various design choices. Subsequently, we developed bug localization models utilizing these embedding models to assess the influence of these choices on the performance of the localization models. Our findings indicate that the pre-training strategies significantly affect the quality of the embedding. Moreover, we discovered that the familiarity of the embedding models with the data has a notable impact on the bug localization model's performance. Notably, when the training and testing data are collected from different projects, the performance of the bug localization models exhibits substantial fluctuations.