论文标题
开放域代码生成的基于执行的评估
Execution-Based Evaluation for Open-Domain Code Generation
论文作者
论文摘要
为了将编码查询的范围扩展到更现实的设置，我们提出了Odex，这是第一个基于开放域执行的自然语言（NL）到Python代码生成数据集。 Odex具有945个NL代码对，涵盖了79个不同的库，以及1,707个人工写的测试用例进行执行。我们的NL代码对从Stackoverflow论坛收获，以鼓励自然和实用的编码查询。此外，Odex用英语，西班牙语，日语和俄语支持四种自然语言作为意图。 Odex推出了表现最佳代码语言模型（LM）之间引人入胜的行为差异。虽然Codex可以实现更好的总体结果，但CodeGen通过缩放有效地改进了CodeGen 6.1b与Codex 12b相当的性能。这两种模型均显示开放域和封闭域之间的巨大差距，但是密码差距往往会随着模型大小而减小，而法典差距增加。我们发布ODEX，以促进对代码生成社区开放域问题的研究。
To extend the scope of coding queries to more realistic settings, we propose ODEX, the first Open-Domain EXecution-based natural language (NL) to Python code generation dataset. ODEX has 945 NL-Code pairs spanning 79 diverse libraries, along with 1,707 human-written test cases for execution. Our NL-Code pairs are harvested from StackOverflow forums to encourage natural and practical coding queries. Moreover, ODEX supports four natural languages as intents, in English, Spanish, Japanese, and Russian. ODEX unveils intriguing behavioral differences among top-performing code language models (LM). While CODEX achieves better overall results, CODEGEN improves effectively via scaling -- CODEGEN 6.1B performs comparably with CODEX 12B. Both models show substantial gaps between open and closed domains, but CODEGEN gaps tend to decrease with model size while CODEX gaps increase. We release ODEX to facilitate research into open-domain problems for the code generation community.
