Search Results for author:
Found 19 papers, 9 papers with code
Cross-Language Learning for Program Classification using Bilateral Tree-Based Convolutional Neural Networks
It is layered on top of two tree-based convolutional neural networks (TBCNNs), each of which recognizes the algorithm of code written in an individual programming language.
Hierarchical Learning of Cross-Language Mappings through Distributed Vector Representations for Code
Our preliminary evaluations on about 40, 000 Java and C# source files from 9 software projects show that our approach can automatically learn shared embeddings for various code elements in different languages and identify their cross-language mappings with reasonable Mean Average Precision scores.
SAR: Learning Cross-Language API Mappings with Little Knowledge
However, all these approaches still require large amount of manual effort in preparing parallel program corpora, ranging from pairs of APIs, to manually identified code in different languages that are considered as functionally equivalent.
On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformations
With the prevalence of publicly available source code repositories to train deep neural network models, neural program models can do well in source code analysis tasks such as predicting method names in given programs that cannot be easily done by traditional program analysis techniques.
TreeCaps: Tree-Based Capsule Networks for Source Code Processing
Although syntax trees are precisely defined according to the language grammar and easier to construct and process than graphs, previous tree-based learning techniques have not been able to learn semantic information from trees to achieve better accuracy than graph-based techniques.
Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations
Corder is designed to alleviate the need of labeled data for code retrieval and code summarization tasks.
InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees
We trained an InferCode model instance using the Tree-based CNN as the encoder of a large set of Java code and applied it to downstream unsupervised tasks such as code clustering, code clone detection, cross-language code search or reused under a transfer learning scheme to continue training the model weights for supervised tasks such as code classification and method name prediction.
Energy-bounded Learning for Robust Models of Code
In programming, learning code representations has a variety of applications, including code classification, code search, comment generation, bug prediction, and so on.
Towards Using Data-Influence Methods to Detect Noisy Samples in Source Code Corpora
Despite the recent trend of developing and applying neural source code models to software engineering tasks, the quality of such models is insufficient for real-world use.
HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations
We propose a novel method for code summarization utilizing Heterogeneous Code Representations (HCRs) and our specially designed HierarchyNet.
Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5
Specifically, we propose three objectives to adapt the generic CodeT5 for debugging: a bug detection objective to determine whether a given code snippet is buggy or not, a bug localization objective to identify the buggy lines, and a program repair objective to translate the buggy code to its fixed version.
Better Language Models of Code through Self-Improvement
We aim to improve this issue by proposing a simple data augmentation framework.
Class based Influence Functions for Error Detection
Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets.
The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation
We present The Vault, a dataset of high-quality code-text pairs in multiple programming languages for training large language models to understand and generate code.
CodeT5+: Open Code Large Language Models for Code Understanding and Generation
To address these limitations, we propose ``CodeT5+'', a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks.
Ranked #1 on
Code Search
on CodeXGLUE - AdvTest
CodeTF: One-stop Transformer Library for State-of-the-art Code LLM
In this paper, we present CodeTF, an open-source Transformer-based library for state-of-the-art Code LLMs and code intelligence.
Neural Code Generation Enhancement via Functional Overlap Reranking
In this work, we introduce \textit{SRank}, a novel reranking strategy for selecting the best solution from code generation that focuses on modeling the relationship between clusters of solutions.
Ranked #15 on
Code Generation
on HumanEval
RepoHyper: Better Context Retrieval Is All You Need for Repository-Level Code Completion
Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks.
Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals
As a research-product hybrid group in AI for Software Engineering (AI4SE), we present four key takeaways from our experience developing in-IDE AI coding assistants.
