26 Open source projects that are alternatives of or similar to MSR2021-ProgramRepair

Triple Branch BERT Siamese Network for fake news classification on LIAR-PLUS dataset in PyTorch

A Python 3 module that provides functions for splitting identifiers found in source code files.

[ICML 2021] Break-It-Fix-It: Unsupervised Learning for Program Repair

A toolkit for pre-processing large source code corpora

Build a Movie Reviews Sentiment Classifier with Google's BERT Language Model

Instructions for how to convert a BERT Tensorflow model to work with HuggingFace's pytorch-transformers, and spaCy. This walk-through uses DeepPavlov's RuBERT as example.

台北QA問答機器人(使用BERT、ALBERT)

CPR: A new automated program repair technique based on concolic execution which works on patch abstraction with the sub-optimal goal of refining the patch to less over-fit the initial test cases.

Source code for the ACL workshop paper and Kaggle competition by Google AI team

Easy text classification for everyone : Bert based models via Huggingface transformers (KR / EN)

A data set and model for german sentiment classification.

This repository contains the dataset and the PyTorch implementations of the models from the paper Recognizing Emotion Cause in Conversations.

An easy to use python package for deep learning-based german sentiment classification.

Fixing static analysis violations in Java source code using Datalog

Research code for ACL 2020 paper: "Distilling Knowledge Learned in BERT for Text Generation".

Pytorch re-implementation of R-BERT model

A High-performance, High-extensibility and High-portability APR System

Code and data form the paper BERT Got a Date: Introducing Transformers to Temporal Tagging

An implementation of the SZZ algorithm, i.e., an approach to identify bug-introducing commits.

Financial Domain Question Answering with pre-trained BERT Language Model

This is an automated transformation inference tool that leverages a big code corpus to guide the abstraction of transformation patterns.

Semantic program repair system for C programs

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

One Person, One Model, One World: Learning Continual User Representation without Forgetting

Fast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models for Local Sequence Transduction": www.aclweb.org/anthology/D19-1435.pdf (EMNLP-IJCNLP 2019)

Use-cases of Hugging Face's BERT (e.g. paraphrase generation, unsupervised extractive summarization).