Deep learning for code intelligence: Survey, benchmark and toolkit

Y Wan, Z Bi, Y He, J Zhang, H Zhang, Y Sui… - ACM Computing …, 2024 - dl.acm.org
Code intelligence leverages machine learning techniques to extract knowledge from
extensive code corpora, with the aim of develo** intelligent tools to improve the quality …

Graph neural networks: foundation, frontiers and applications

L Wu, P Cui, J Pei, L Zhao, X Guo - … of the 28th ACM SIGKDD conference …, 2022 - dl.acm.org
The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

Large language models are few-shot summarizers: Multi-intent comment generation via in-context learning

M Geng, S Wang, D Dong, H Wang, G Li, Z **… - Proceedings of the 46th …, 2024 - dl.acm.org
Code comment generation aims at generating natural language descriptions for a code
snippet to facilitate developers' program comprehension activities. Despite being studied for …

Semantic similarity metrics for evaluating source code summarization

S Haque, Z Eberhart, A Bansal… - Proceedings of the 30th …, 2022 - dl.acm.org
Source code summarization involves creating brief descriptions of source code in natural
language. These descriptions are a key component of software documentation such as …

Studying the usage of text-to-text transfer transformer to support code-related tasks

A Mastropaolo, S Scalabrino, N Cooper… - 2021 IEEE/ACM …, 2021 - ieeexplore.ieee.org
Deep learning (DL) techniques are gaining more and more attention in the software
engineering community. They have been used to support several code-related tasks, such …

An empirical comparison of pre-trained models of source code

C Niu, C Li, V Ng, D Chen, J Ge… - 2023 IEEE/ACM 45th …, 2023 - ieeexplore.ieee.org
While a large number of pre-trained models of source code have been successfully
developed and applied to a variety of software engineering (SE) tasks in recent years, our …

Unifying the perspectives of nlp and software engineering: A survey on language models for code

Z Zhang, C Chen, B Liu, C Liao, Z Gong, H Yu… - ar** study of source code representation for deep learning in software engineering
HP Samoaa, F Bayram, P Salza, P Leitner - IET Software, 2022 - Wiley Online Library
The usage of deep learning (DL) approaches for software engineering has attracted much
attention, particularly in source code modelling and analysis. However, in order to use DL …

Cocomic: Code completion by jointly modeling in-file and cross-file context

Y Ding, Z Wang, WU Ahmad, MK Ramanathan… - arxiv preprint arxiv …, 2022 - arxiv.org
While pre-trained language models (LM) for code have achieved great success in code
completion, they generate code conditioned only on the contents within the file, ie, in-file …