发布求助
文献互助 智能选刊 最新文献

Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)最新文献

筛选
英文 中文
Bag-of-Words Baselines for Semantic Code Search 语义代码搜索的词袋基线
Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021) Pub Date : 1900-01-01 DOI: 10.18653/v1/2021.nlp4prog-1.10
Xinyu Zhang, Ji Xin, Andrew Yates, Jimmy J. Lin, D. Cheriton
{"title":"Bag-of-Words Baselines for Semantic Code Search","authors":"Xinyu Zhang, Ji Xin, Andrew Yates, Jimmy J. Lin, D. Cheriton","doi":"10.18653/v1/2021.nlp4prog-1.10","DOIUrl":"https://doi.org/10.18653/v1/2021.nlp4prog-1.10","url":null,"abstract":"The task of semantic code search is to retrieve code snippets from a source code corpus based on an information need expressed in natural language. The semantic gap between natural language and programming languages has for long been regarded as one of the most significant obstacles to the effectiveness of keyword-based information retrieval (IR) methods. It is a common assumption that “traditional” bag-of-words IR methods are poorly suited for semantic code search: our work empirically investigates this assumption. Specifically, we examine the effectiveness of two traditional IR methods, namely BM25 and RM3, on the CodeSearchNet Corpus, which consists of natural language queries paired with relevant code snippets. We find that the two keyword-based methods outperform several pre-BERT neural models. We also compare several code-specific data pre-processing strategies and find that specialized tokenization improves effectiveness.","PeriodicalId":435990,"journal":{"name":"Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126903074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Time-Efficient Code Completion Model for the R Programming Language R编程语言的高效代码完成模型
Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021) Pub Date : 1900-01-01 DOI: 10.18653/v1/2021.nlp4prog-1.4
Artem Popov, Dmitrii Orekhov, Denis V. Litvinov, N. Korolev, Gleb Morgachev
{"title":"Time-Efficient Code Completion Model for the R Programming Language","authors":"Artem Popov, Dmitrii Orekhov, Denis V. Litvinov, N. Korolev, Gleb Morgachev","doi":"10.18653/v1/2021.nlp4prog-1.4","DOIUrl":"https://doi.org/10.18653/v1/2021.nlp4prog-1.4","url":null,"abstract":"In this paper we present a deep learning code completion model for the R language. We introduce several techniques to utilize language modeling based architecture in the code completion task. With these techniques, the model requires low resources, but still achieves high quality. We also present an evaluation dataset for the R language completion task. Our dataset contains multiple autocompletion usage contexts that provides robust validation results. The dataset is publicly available.","PeriodicalId":435990,"journal":{"name":"Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121447033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
ConTest: A Unit Test Completion Benchmark featuring Context 竞赛:以上下文为特征的单元测试完成基准
Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021) Pub Date : 1900-01-01 DOI: 10.18653/v1/2021.nlp4prog-1.2
Johannes Villmow, Jonas Depoix, A. Ulges
{"title":"ConTest: A Unit Test Completion Benchmark featuring Context","authors":"Johannes Villmow, Jonas Depoix, A. Ulges","doi":"10.18653/v1/2021.nlp4prog-1.2","DOIUrl":"https://doi.org/10.18653/v1/2021.nlp4prog-1.2","url":null,"abstract":"We introduce CONTEST, a benchmark for NLP-based unit test completion, the task of predicting a test’s assert statements given its setup and focal method, i.e. the method to be tested. ConTest is large-scale (with 365k datapoints). Besides the test code and tested code, it also features context code called by either. We found context to be crucial for accurately predicting assertions. We also introduce baselines based on transformer encoder-decoders, and study the effects of including syntactic information and context. Overall, our models achieve a BLEU score of 38.2, while only generating unparsable code in 1.92% of cases.","PeriodicalId":435990,"journal":{"name":"Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132340650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信