SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations

Recent years have seen the successful application of large pretrained models to code representation learning, resulting in substantial improvements on many code-related downstream tasks. But there are issues surrounding their application to SE tasks. First, the majority of the pre-trained models foc...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE) s. 01 - 13
Hlavní autoři: Niu, Changan, Li, Chuanyi, Ng, Vincent, Ge, Jidong, Huang, Liguo, Luo, Bin
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: ACM 01.05.2022
Témata:
code representation learning
Codes
Computer architecture
Decoding
Natural languages
pre-training
Representation learning
sequence-to-sequence
Task analysis
Transformers
ISSN:1558-1225
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Recent years have seen the successful application of large pretrained models to code representation learning, resulting in substantial improvements on many code-related downstream tasks. But there are issues surrounding their application to SE tasks. First, the majority of the pre-trained models focus on pre-training only the encoder of the Transformer. For generation tasks that are addressed using models with the encoder-decoder architecture, however, there is no reason why the decoder should be left out during pre-training. Second, many existing pre-trained models, including state-of-the-art models such as T5-learning, simply reuse the pretraining tasks designed for natural languages. Moreover, to learn the natural language description of source code needed eventually for code-related tasks such as code summarization, existing pretraining tasks require a bilingual corpus composed of source code and the associated natural language description, which severely limits the amount of data for pre-training. To this end, we propose SPT-Code, a sequence-to-sequence pre-trained model for source code. In order to pre-train SPT-Code in a sequence-to-sequence manner and address the aforementioned weaknesses associated with existing pre-training tasks, we introduce three pre-training tasks that are specifically designed to enable SPT-Code to learn knowledge of source code, the corresponding code structure, as well as a natural language description of the code without relying on any bilingual corpus, and eventually exploit these three sources of information when it is applied to downstream tasks. Experimental results demonstrate that SPT-Code achieves state-of-the-art performance on five code-related downstream tasks after fine-tuning.
ISSN:1558-1225
DOI:10.1145/3510003.3510096