Litcius/Paper detail

GrammarT5: Grammar-Integrated Pretrained Encoder-Decoder Neural Model for Code

Qihao Zhu, Qingyuan Liang, Zeyu Sun, Yingfei Xiong, Lu Zhang, Shengyu Cheng

202410 citationsDOI

Abstract

Pretrained models for code have exhibited promising performance across various code-related tasks, such as code summarization, code completion, code translation, and bug detection. However, despite their success, the majority of current models still represent code as a token sequence, which may not adequately capture the essence of the underlying code structure.

Topics & Concepts

Computer scienceCode (set theory)Automatic summarizationProgramming languageEncoderCode generationNatural language processingMachine translationArtificial intelligenceSecurity tokenOperating systemComputer securityKey (lock)Set (abstract data type)Software Engineering ResearchSoftware Testing and Debugging TechniquesAdvanced Malware Detection Techniques