Open AccessPosted Content
CodeSearchNet Challenge: Evaluating the State of Semantic Code Search.
TL;DR: The methodology used to obtain the corpus and expert labels, as well as a number of simple baseline solutions for the task are described.
read more
Abstract: Semantic code search is the task of retrieving relevant code given a natural language query. While related to other information retrieval tasks, it requires bridging the gap between the language used in code (often abbreviated and highly technical) and natural language more suitable to describe vague concepts and ideas.
To enable evaluation of progress on code search, we are releasing the CodeSearchNet Corpus and are presenting the CodeSearchNet Challenge, which consists of 99 natural language queries with about 4k expert relevance annotations of likely results from CodeSearchNet Corpus. The corpus contains about 6 million functions from open-source code spanning six programming languages (Go, Java, JavaScript, PHP, Python, and Ruby). The CodeSearchNet Corpus also contains automatically generated query-like natural language for 2 million functions, obtained from mechanically scraping and preprocessing associated function documentation. In this article, we describe the methodology used to obtain the corpus and expert labels, as well as a number of simple baseline solutions for the task.
We hope that CodeSearchNet Challenge encourages researchers and practitioners to study this interesting task further and will host a competition and leaderboard to track the progress on the challenge. We are also keen on extending CodeSearchNet Challenge to more queries and programming languages in the future.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
CCT-Code: Cross-Consistency Training for Multilingual Clone Detection and Code Search
TL;DR: In this article , a cross-consistency training (CCT) procedure is proposed to train language models on source code in different programming languages to find code snippets that operate identically but are written in different languages.
3
Improving the Robustness of Summarization Models by Detecting and Removing Input Noise
Kundan Krishna,Yao Zhao,Jie Ren,Balaji Lakshminarayanan,Jiaming Luo,Mohammad Saleh,Peter J. Liu +6 more
TL;DR: This article proposed a light-weight method for detecting and removing such noise in the input during model inference without requiring any extra training, auxiliary models, or even prior knowledge of the type of noise.
3
Assessing the Effectiveness and Security Implications of AI Code Generators
Maryam Taeb,Hongmei Chi,Shonda Bernadin +2 more
TL;DR: The effectiveness and security implications of AI code generators are assessed, focusing on their code generation, code completion, and security suggestions capabilities. The research aims to evaluate the tools' effectiveness and security aspects and provide guidance for developers to avoid introducing vulnerabilities.
Mining Resource-Operation Knowledge to Support Resource Leak Detection
Chong Wang,Yiling Lou,Xin Peng,Jianan Liu,Baihan Zou +4 more
- 30 Nov 2023
TL;DR: This work proposes to represent resource-operation knowledge as abstract resource acquisition/release operation pairs (Abs-RAR pairs for short), and presents a novel approach called MiROK to mine such Abs-Rar pairs to construct a better RAR pair pool.
3
Backdooring Neural Code Search
Weisong Sun,Yuchen Chen,Guanhong Tao,Chunrong Fang,Xiangyu Zhang,Quanjun Zhang,Bing Luo +6 more
- 27 May 2023
TL;DR: Wang et al. as discussed by the authors demonstrate that by modifying one variable/function name, the attacker can make buggy/vulnerable code rank in the top 11% of the best code snippets.
References
•Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
- 12 Jun 2017
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
•Posted Content
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TL;DR: A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
81.7K
Convolutional Neural Networks for Sentence Classification
Yoon Kim
- 25 Aug 2014
TL;DR: The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification, and are proposed to allow for the use of both task-specific and static vectors.
•Book
Introduction to Information Retrieval
Christopher D. Manning,Prabhakar Raghavan,Hinrich Schütze +2 more
- 01 Jan 2008
TL;DR: In this article, the authors present an up-to-date treatment of all aspects of the design and implementation of systems for gathering, indexing, and searching documents; methods for evaluating systems; and an introduction to the use of machine learning methods on text collections.
Neural Machine Translation of Rare Words with Subword Units
Rico Sennrich,Barry Haddow,Alexandra Birch +2 more
- 12 Aug 2016
TL;DR: This paper introduces a simpler and more effective approach, making the NMT model capable of open-vocabulary translation by encoding rare and unknown words as sequences of subword units, and empirically shows that subword models improve over a back-off dictionary baseline for the WMT 15 translation tasks English-German and English-Russian by 1.3 BLEU.