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
•Posted Content
Yet Another Combination of IR- and Neural-based Comment Generation
TL;DR: In this article, a cross-encoder-based classifier is used to decide the comment generation method to be used dynamically, i.e. if the retrieved similar code snippet is a true positive (i.e., is semantically similar to the input), and then the input to the neural-based model to generate the comment.
4
Proceedings Article
TABS: Efficient Textual Adversarial Attack for Pre-trained NL Code Model Using Semantic Beam Search
TL;DR: In this article , the authors adopt beam search to find out better adversarial examples, and contextual semantic filtering to effectively reduce the search space, which shows good performance in terms of attack success rate, the number of queries, and semantic similarity.
•Posted Content
Generating Code with the Help of Retrieved Template Functions and Stack Overflow Answers.
TL;DR: In this article, a sequence-to-sequence code generator model is enhanced with the ability to attend to reference code snippets supplied by a semantic code search engine, and a framework is presented to precisely retrieve template functions as well as intent-snippet pairs.
4
A Structural Transformer with Relative Positions in Trees for Code-to-Sequence Tasks
Johannes Villmow,Adrian Ulges,Ulrich Schwanecke +2 more
- 18 Jul 2021
TL;DR: The authors use self-attention with relative position representations to consider structural relationships between nodes using a representation that encodes movements between any pair of nodes in the tree, and demonstrate how those movements can be computed efficiently on the fly.
4
Evaluating and Explaining Large Language Models for Code Using Syntactic Structures
David N. Palacio,Alejandro Velasco,Daniel Rodríguez-Cárdenas,Kevin Moran,Denys Poshyvanyk +4 more
TL;DR: ASTxplainer is introduced, an explainability method specific to LLMs for code that enables both new methods for LLM evaluation and visualizations of LLM predictions that aid end-users in understanding model predictions.
4
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.