|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
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.
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
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.
Ranked #1 on Program Repair on DeepFix
This paper presents a novel end-to-end approach to program repair based on sequence-to-sequence learning.
Evaluation results show that our new semantic program embedding significantly outperforms the syntactic program embeddings based on token sequences and abstract syntax trees.
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.
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.