Code Generation as a Dual Task of Code Summarization

2019-10-14 · NeurIPS 2019 12 · Bolin Wei, Ge Li, Xin Xia, Zhiyi Fu, Zhi Jin

Code summarization (CS) and code generation (CG) are two crucial tasks in the field of automatic software development. Various neural network-based approaches are proposed to solve these two tasks separately. However, there exists a specific intuitive correlation between CS and CG, which have not been exploited in previous work. In this paper, we apply the relations between two tasks to improve the performance of both tasks. In other words, exploiting the duality between the two tasks, we propose a dual training framework to train the two tasks simultaneously. In this framework, we consider the dualities on probability and attention weights, and design corresponding regularization terms to constrain the duality. We evaluate our approach on two datasets collected from GitHub, and experimental results show that our dual framework can improve the performance of CS and CG tasks over baselines.

📄 PDF Abstract BibTeX arXiv:1910.05923

Code (2)

Bolin0215/CSCGDual 공식 구현 pytorch

code-gen/cgcs tf

Tasks

Code GenerationCode SummarizationSource Code Summarization

Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning

2020-02-24 · Wei Ye, Rui Xie, Jinglei Zhang, Tianxiang Hu 외

Code summarization generates brief natural language description given a source code snippet, while code retrieval fetches relevant source code given a natural language query. Since both tasks aim to model the association…

Code Generation Code Summarization Multi-Task Learning Retrieval+1

Analyzing the Performance of Large Language Models on Code Summarization

2024-04-10 · Rajarshi Haldar, Julia Hockenmaier

Large language models (LLMs) such as Llama 2 perform very well on tasks that involve both natural language and source code, particularly code summarization and code generation. We show that for the task of code summariza…

Code Generation Code Summarization

Chain-of-Descriptions: Improving Code LLMs for VHDL Code Generation and Summarization

2025-07-16 · Prashanth Vijayaraghavan, Apoorva Nitsure, Charles Mackin, Luyao Shi 외 arxiv

Large Language Models (LLMs) have become widely used across diverse NLP tasks and domains, demonstrating their adaptability and effectiveness. In the realm of Electronic Design Automation (EDA), LLMs show promise for tas…

Code Generation

Large Language Models for Code Summarization

2024-05-29 · Balázs Szalontai, Gergő Szalay, Tamás Márton, Anna Sike 외

Recently, there has been increasing activity in using deep learning for software engineering, including tasks like code generation and summarization. In particular, the most recent coding Large Language Models seem to pe…

Code Generation Code Summarization

Meta Learning for Code Summarization

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Source code summarization is the task of generating a high-level natural language description for a segment of programming language code. Current neural models for the task differ in their architecture and the aspects of…

Code Summarization Meta-Learning Source Code Summarization