About

Benchmarks

Subtasks

Greatest papers with code

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

NeurIPS 2020 google-research/google-research

More practically, we evaluate these models on the task of learning to execute partial programs, as might arise if using the model as a heuristic function in program synthesis.

LEARNING TO EXECUTE PROGRAM REPAIR SYSTEMATIC GENERALIZATION

Learning and Evaluating Contextual Embedding of Source Code

ICML 2020 google-research/google-research

We fine-tune CuBERT on our benchmark tasks, and compare the resulting models to different variants of Word2Vec token embeddings, BiLSTM and Transformer models, as well as published state-of-the-art models, showing that CuBERT outperforms them all, even with shorter training, and with fewer labeled examples.

CONTEXTUAL EMBEDDING FOR SOURCE CODE EXCEPTION TYPE FUNCTION-DOCSTRING MISMATCH NATURAL LANGUAGE UNDERSTANDING SWAPPED OPERANDS UNSUPERVISED REPRESENTATION LEARNING VARIABLE MISUSE WRONG BINARY OPERATOR

Graph-based, Self-Supervised Program Repair from Diagnostic Feedback

ICML 2020 michiyasunaga/DrRepair

Second, we present a self-supervised learning paradigm for program repair that leverages unlabeled programs available online to create a large amount of extra program repair examples, which we use to pre-train our models.

CODE GENERATION GRAPH LEARNING PROGRAM REPAIR SELF-SUPERVISED LEARNING

Global Relational Models of Source Code

ICLR 2020 VHellendoorn/ICLR20-Great

By studying a popular, non-trivial program repair task, variable-misuse identification, we explore the relative merits of traditional and hybrid model families for code representation.

VARIABLE MISUSE

SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair

24 Dec 2018kth/SequenceR

This paper presents a novel end-to-end approach to program repair based on sequence-to-sequence learning.

PROGRAM REPAIR

Dynamic Neural Program Embedding for Program Repair

20 Nov 2017keowang/dynamic-program-embedding

Evaluation results show that our new semantic program embedding significantly outperforms the syntactic program embeddings based on token sequences and abstract syntax trees.

FAULT LOCALIZATION

Human-In-The-Loop Automatic Program Repair

16 Dec 2019mboehme/learn2fix

Our key challenge is to maximize the oracle's accuracy in predicting which tests are bug-exposing given a small budget of queries.

PROGRAM REPAIR

CoCoNuT: Combining Context-Aware Neural Translation Models using Ensemble for Program Repair

18 Jul 2020lin-tan/CoCoNut-Artifact

To address these challenges, we propose a new G&V technique—CoCoNuT, which uses ensemble learning on the combination of convolutional neural networks (CNNs) and a new context-aware neural machine translation (NMT) architecture to automatically fix bugs in multiple programming languages.

MACHINE TRANSLATION PROGRAM REPAIR

Patching as Translation: the Data and the Metaphor

24 Aug 2020ARiSE-Lab/Patch-as-translation

Given these findings, we demonstrate how a more principled approach to model design, based on our empirical findings and general knowledge of software development, can lead to better solutions.

PROGRAM REPAIR

Deep Reinforcement Learning for Programming Language Correction

31 Jan 2018terne/dtuproject

Novice programmers often struggle with the formal syntax of programming languages.

MACHINE TRANSLATION PROGRAM REPAIR