Recently, machine learning (ML) methods have been used to create powerful language
models for a broad range of natural language processing tasks. An important subset of this …

The immense amounts of source code provide ample challenges and opportunities during
software development. To handle the size of code bases, developers commonly search for …

Benchmark datasets have a significant impact on accelerating research in programming
language tasks. In this paper, we introduce CodeXGLUE, a benchmark dataset to foster …

In this work we systematically review the recent advancements in software engineering with
language models, covering 70+ models, 40+ evaluation tasks, 180+ datasets, and 900 …

The performance of neural code search is significantly influenced by the quality of the
training data from which the neural models are derived. A large corpus of high-quality query …

Code summarization aims to generate brief natural language descriptions for source codes.
The state-of-the-art approaches follow a transformer-based encoder-decoder architecture …

Researchers have recently achieved significant advances in deep learning techniques,
which in turn has substantially advanced other research disciplines, such as natural …

Simultaneously modeling source code and natural language has many exciting applications
in automated software development and understanding. Pursuant to achieving such …

Code writing is repetitive and predictable, inspiring us to develop various code intelligence
techniques. This survey focuses on code search, that is, to retrieve code that matches a …

The relationship of comments to code, and in particular, the task of generating useful
comments given the code, has long been of interest. The earliest approaches have been …