Proceedings ArticleDOI
Retrieval on source code: a neural code search
Saksham Sachdev,Hongyu Li,Sifei Luan,Seohyun Kim,Koushik Sen,Satish Chandra +5 more
- pp 31-41
Reads0
Chats0
TLDR
This paper investigates the use of natural language processing and information retrieval techniques to carry out natural language search directly over source code, i.e. without having a curated Q&A forum such as Stack Overflow at hand.Abstract:
Searching over large code corpora can be a powerful productivity tool for both beginner and experienced developers because it helps them quickly find examples of code related to their intent. Code search becomes even more attractive if developers could express their intent in natural language, similar to the interaction that Stack Overflow supports. In this paper, we investigate the use of natural language processing and information retrieval techniques to carry out natural language search directly over source code, i.e. without having a curated Q&A forum such as Stack Overflow at hand. Our experiments using a benchmark suite derived from Stack Overflow and GitHub repositories show promising results. We find that while a basic word–embedding based search procedure works acceptably, better results can be obtained by adding a layer of supervision, as well as by a customized ranking strategy.read more
Citations
More filters
Proceedings ArticleDOI
When deep learning met code search
TL;DR: In this paper, the authors evaluate the performance of supervised techniques for code search using natural language and show that adding supervision to an existing unsupervised technique can improve performance, though not necessarily by much.
Proceedings ArticleDOI
NL2Type: inferring JavaScript function types from natural language information
TL;DR: NL2Type is presented, a learning-based approach for predicting likely type signatures of JavaScript functions using a recurrent, LSTM-based neural model that, after learning from an annotated code base, predicts function types for unannotated code.
Journal ArticleDOI
Aroma: Code Recommendation via Structural Code Search
TL;DR: Aroma as mentioned in this paper is a tool and technique for code recommendation via structural code search, which takes a partial code snippet as input, searches the corpus for method bodies containing the partial code snippets, and clusters and intersects the results of the search to recommend a small set of succinct code snippets which both contain the query snippet and appear as part of several methods in the corpus.
Journal ArticleDOI
Aroma: code recommendation via structural code search
TL;DR: Aroma as mentioned in this paper is a tool and technique for code recommendation via structural code search, which takes a partial code snippet as input, searches the corpus for method bodies containing the partial code snippets, and clusters and intersects the results of the search to recommend a small set of succinct code snippets which both contain the query snippet and appear as part of several methods in the corpus.
Posted Content
Adversarial Examples for Models of Code
Noam Yefet,Uri Alon,Eran Yahav +2 more
TL;DR: The main idea of the approach is to force a given trained model to make an incorrect prediction, as specified by the adversary, by introducing small perturbations that do not change the program’s semantics, thereby creating an adversarial example.
References
More filters
Proceedings Article
Distributed Representations of Words and Phrases and their Compositionality
TL;DR: This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
Journal ArticleDOI
Enriching Word Vectors with Subword Information
TL;DR: This paper proposed a new approach based on skip-gram model, where each word is represented as a bag of character n-grams, words being represented as the sum of these representations, allowing to train models on large corpora quickly and allowing to compute word representations for words that did not appear in the training data.
Journal ArticleDOI
Distributional Structure
TL;DR: This discussion will discuss how each language can be described in terms of a distributional structure, i.e. in Terms of the occurrence of parts relative to other parts, and how this description is complete without intrusion of other features such as history or meaning.
Posted Content
Enriching Word Vectors with Subword Information
TL;DR: A new approach based on the skipgram model, where each word is represented as a bag of character n-grams, with words being represented as the sum of these representations, which achieves state-of-the-art performance on word similarity and analogy tasks.
Posted Content
Billion-scale similarity search with GPUs
TL;DR: In this paper, the authors propose a design for k-selection that operates at up to 55% of theoretical peak performance, enabling a nearest neighbor implementation that is 8.5x faster than prior GPU state of the art.