On the validity of pre-trained transformers for natural language processing in the software engineering domain
This work addresses the validity of pre-trained transformers for software engineering NLP, offering insights for researchers and practitioners in this domain, though it is incremental as it builds on existing transformer methods.
The study investigated the effectiveness of transformer models pre-trained on software engineering data versus general domain data for natural language processing tasks in software engineering, finding that software-specific pre-training improves performance on context-dependent tasks while general models suffice for basic language understanding.
Transformers are the current state-of-the-art of natural language processing in many domains and are using traction within software engineering research as well. Such models are pre-trained on large amounts of data, usually from the general domain. However, we only have a limited understanding regarding the validity of transformers within the software engineering domain, i.e., how good such models are at understanding words and sentences within a software engineering context and how this improves the state-of-the-art. Within this article, we shed light on this complex, but crucial issue. We compare BERT transformer models trained with software engineering data with transformers based on general domain data in multiple dimensions: their vocabulary, their ability to understand which words are missing, and their performance in classification tasks. Our results show that for tasks that require understanding of the software engineering context, pre-training with software engineering data is valuable, while general domain models are sufficient for general language understanding, also within the software engineering domain.