自然语言到Python的源代码使用变压器

2021 International Conference on Intelligent Technologies (CONIT) Pub Date : 2021-06-25 DOI:10.1109/CONIT51480.2021.9498268

Meet Shah, Rajat Shenoy, R. Shankarmani

{"title":"自然语言到Python的源代码使用变压器","authors":"Meet Shah, Rajat Shenoy, R. Shankarmani","doi":"10.1109/CONIT51480.2021.9498268","DOIUrl":null,"url":null,"abstract":"Writing code using natural language is a very exciting application of Neural Machine Translation. To achieve a small part of such an application, in this paper, we try to generate python source code snippets from natural English language descriptions using the Django dataset. We trained the self-attention based transformer architecture on the snippets from the dataset. We achieved a BLEU score of 64.29","PeriodicalId":426131,"journal":{"name":"2021 International Conference on Intelligent Technologies (CONIT)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Natural Language to Python Source Code using Transformers\",\"authors\":\"Meet Shah, Rajat Shenoy, R. Shankarmani\",\"doi\":\"10.1109/CONIT51480.2021.9498268\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Writing code using natural language is a very exciting application of Neural Machine Translation. To achieve a small part of such an application, in this paper, we try to generate python source code snippets from natural English language descriptions using the Django dataset. We trained the self-attention based transformer architecture on the snippets from the dataset. We achieved a BLEU score of 64.29\",\"PeriodicalId\":426131,\"journal\":{\"name\":\"2021 International Conference on Intelligent Technologies (CONIT)\",\"volume\":\"86 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-06-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 International Conference on Intelligent Technologies (CONIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CONIT51480.2021.9498268\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Intelligent Technologies (CONIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CONIT51480.2021.9498268","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 4

摘要

使用自然语言编写代码是神经机器翻译的一个非常令人兴奋的应用。为了实现这样一个应用程序的一小部分，在本文中，我们尝试使用Django数据集从自然英语语言描述生成python源代码片段。我们在数据集中的片段上训练了基于自关注的转换器架构。我们获得了64.29分的BLEU分数

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Natural Language to Python Source Code using Transformers

Writing code using natural language is a very exciting application of Neural Machine Translation. To achieve a small part of such an application, in this paper, we try to generate python source code snippets from natural English language descriptions using the Django dataset. We trained the self-attention based transformer architecture on the snippets from the dataset. We achieved a BLEU score of 64.29

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2021 International Conference on Intelligent Technologies (CONIT)

自引率

0.00%

发文量