CodeS: Natural Language to Code Repository via Multi-Layer Sketch
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911812070408192 |
|---|---|
| author | Zan, Daoguang Yu, Ailun Liu, Wei Chen, Dong Shen, Bo Li, Wei Yao, Yafen Gong, Yongshun Chen, Xiaolin Guan, Bei Yang, Zhiguang Wang, Yongji Wang, Qianxiang Cui, Lizhen |
| author_facet | Zan, Daoguang Yu, Ailun Liu, Wei Chen, Dong Shen, Bo Li, Wei Yao, Yafen Gong, Yongshun Chen, Xiaolin Guan, Bei Yang, Zhiguang Wang, Yongji Wang, Qianxiang Cui, Lizhen |
| contents | The impressive performance of large language models (LLMs) on code-related tasks has shown the potential of fully automated software development. In light of this, we introduce a new software engineering task, namely Natural Language to code Repository (NL2Repo). This task aims to generate an entire code repository from its natural language requirements. To address this task, we propose a simple yet effective framework CodeS, which decomposes NL2Repo into multiple sub-tasks by a multi-layer sketch. Specifically, CodeS includes three modules: RepoSketcher, FileSketcher, and SketchFiller. RepoSketcher first generates a repository's directory structure for given requirements; FileSketcher then generates a file sketch for each file in the generated structure; SketchFiller finally fills in the details for each function in the generated file sketch. To rigorously assess CodeS on the NL2Repo task, we carry out evaluations through both automated benchmarking and manual feedback analysis. For benchmark-based evaluation, we craft a repository-oriented benchmark, SketchEval, and design an evaluation metric, SketchBLEU. For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies. Extensive experiments prove the effectiveness and practicality of CodeS on the NL2Repo task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16443 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CodeS: Natural Language to Code Repository via Multi-Layer Sketch Zan, Daoguang Yu, Ailun Liu, Wei Chen, Dong Shen, Bo Li, Wei Yao, Yafen Gong, Yongshun Chen, Xiaolin Guan, Bei Yang, Zhiguang Wang, Yongji Wang, Qianxiang Cui, Lizhen Computation and Language Artificial Intelligence Software Engineering The impressive performance of large language models (LLMs) on code-related tasks has shown the potential of fully automated software development. In light of this, we introduce a new software engineering task, namely Natural Language to code Repository (NL2Repo). This task aims to generate an entire code repository from its natural language requirements. To address this task, we propose a simple yet effective framework CodeS, which decomposes NL2Repo into multiple sub-tasks by a multi-layer sketch. Specifically, CodeS includes three modules: RepoSketcher, FileSketcher, and SketchFiller. RepoSketcher first generates a repository's directory structure for given requirements; FileSketcher then generates a file sketch for each file in the generated structure; SketchFiller finally fills in the details for each function in the generated file sketch. To rigorously assess CodeS on the NL2Repo task, we carry out evaluations through both automated benchmarking and manual feedback analysis. For benchmark-based evaluation, we craft a repository-oriented benchmark, SketchEval, and design an evaluation metric, SketchBLEU. For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies. Extensive experiments prove the effectiveness and practicality of CodeS on the NL2Repo task. |
| title | CodeS: Natural Language to Code Repository via Multi-Layer Sketch |
| topic | Computation and Language Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2403.16443 |