36 citations · 253 across the 30 of their papers we have counts for
11 papers · 1 filter
Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively
Haojie Zhang, Ge Li, Jia Li +3
Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently. However, fine-tuning an extremely large-scale pre-trained lan…
CodePAD: Sequence-based Code Generation with Pushdown Automaton
Yihong Dong, Xue Jiang, Yuchen Liu +2
In the process of code generation, it is essential to guarantee the generated code satisfies grammar constraints of programming language (PL). However, neglecting grammar constrain…
Poison Attack and Defense on Deep Source Code Processing Models
Jia Li, Zhuo Li, Huangzhao Zhang +4
In the software engineering community, deep learning (DL) has recently been applied to many source code processing tasks. Due to the poor interpretability of DL models, their secur…
CodeEditor: Learning to Edit Source Code with Pre-trained Models
Jia Li, Ge Li, Zhuo Li +4
Developers often perform repetitive code editing activities for various reasons (e.g., code refactoring) during software development. Pre-trained code editing models have achieved…
Incorporating Domain Knowledge through Task Augmentation for Front-End JavaScript Code Generation
Sijie Shen, Xiang Zhu, Yihong Dong +3
Code generation aims to generate a code snippet automatically from natural language descriptions. Generally, the mainstream code generation methods rely on a large amount of paired…
Antecedent Predictions Are More Important Than You Think: An Effective Method for Tree-Based Code Generation
Yihong Dong, Ge Li, Xue Jiang +1
Code generation focuses on the automatic conversion of natural language (NL) utterances into code snippets. The sequence-to-tree (Seq2Tree) approaches are proposed for code generat…
Learning Program Representations with a Tree-Structured Transformer
Wenhan Wang, Kechi Zhang, Ge Li +4
Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks. Various neural network models are proposed to…
AixBench: A Code Generation Benchmark Dataset
Yiyang Hao, Ge Li, Yongqiang Liu +5
We present a benchmark dataset for evaluating method-level code generation task. The benchmark contains a dataset of 175 samples for automated evaluation and a dataset of 161 sampl…
What does Transformer learn about source code?
Kechi Zhang, Ge Li, Zhi Jin
In the field of source code processing, the transformer-based representation models have shown great powerfulness and have achieved state-of-the-art (SOTA) performance in many task…
Non-autoregressive Model for Full-line Code Completion
Fang Liu, Zhiyi Fu, Ge Li +3
Code completion tools are frequently used by software developers to accelerate software development by suggesting the following code elements. Completing a sequence of code tokens…
Learning to Recommend Method Names with Global Context
Fang Liu, Ge Li, Zhiyi Fu +3
In programming, the names for the program entities, especially for the methods, are the intuitive characteristic for understanding the functionality of the code. To ensure the read…