Code for "Learning Structural Edits via Incremental Tree Transformations" (ICLR'21)

Overview

Learning Structural Edits via Incremental Tree Transformations

Code for "Learning Structural Edits via Incremental Tree Transformations" (ICLR'21)

1. Prepare Environment

We recommend using conda to manage the environment:

conda env create -n "structural_edits" -f structural_edits.yml
conda activate structural_edits

Install the punkt tokenizer:

python
>>> import nltk
>>> nltk.download('punkt')
>>> <ctrl-D>

2. Data

Please extract the datasets and vocabulary files by:

cd source_data
tar -xzvf githubedits.tar.gz

All necessary source data has been included as the following:

| --source_data
|       |-- githubedits
|           |-- githubedits.{train|train_20p|dev|test}.jsonl
|           |-- csharp_fixers.jsonl
|           |-- vocab.from_repo.{080910.freq10|edit}.json
|           |-- Syntax.xml
|           |-- configs
|               |-- ...(model config json files)

A sample file containing 20% of the GitHubEdits training data is included as source_data/githubedits/githubedits.train_20p.jsonl for running small experiments.

We have generated and included the vocabulary files as well. To create your own vocabulary, see edit_components/vocab.py.

Copyright: The original data were downloaded from Yin et al., (2019).

3. Experiments

See training and test scripts in scripts/githubedits/. Please configure the PYTHONPATH environment variable in line 6.

3.1 Training

For training, uncomment the desired setting in scripts/githubedits/train.sh and run:

bash scripts/githubedits/train.sh source_data/githubedits/configs/CONFIGURATION_FILE

where CONFIGURATION_FILE is the json file of your setting.

Supervised Learning

For example, if you want to train Graph2Edit + Sequence Edit Encoder on GitHubEdits's 20% sample data, please uncomment only line 21-25 in scripts/githubedits/train.sh and run:

bash scripts/githubedits/train.sh source_data/githubedits/configs/graph2iteredit.seq_edit_encoder.20p.json

(Note: when you run the experiment for the first time, you might need to wait for ~15 minutes for data preprocessing.)

Imitation Learning

To further train the model with PostRefine imitation learning, please replace FOLDER_OF_SUPERVISED_PRETRAINED_MODEL with your model dir in source_data/githubedits/configs/graph2iteredit.seq_edit_encoder.20p.postrefine.imitation.json. Uncomment only line 27-31 in scripts/githubedits/train.sh and run:

bash scripts/githubedits/train.sh source_data/githubedits/configs/graph2iteredit.seq_edit_encoder.20p.postrefine.imitation.json

3.2 Test

To test a trained model, first uncomment only the desired setting in scripts/githubedits/test.sh and replace work_dir with your model directory, and then run:

bash scripts/githubedits/test.sh

4. Reference

If you use our code and data, please cite our paper:

@inproceedings{yao2021learning,
    title={Learning Structural Edits via Incremental Tree Transformations},
    author={Ziyu Yao and Frank F. Xu and Pengcheng Yin and Huan Sun and Graham Neubig},
    booktitle={International Conference on Learning Representations},
    year={2021},
    url={https://openreview.net/forum?id=v9hAX77--cZ}
}

Our implementation is adapted from TranX and Graph2Tree. We are grateful to the two work!

@inproceedings{yin18emnlpdemo,
    title = {{TRANX}: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation},
    author = {Pengcheng Yin and Graham Neubig},
    booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP) Demo Track},
    year = {2018}
}
@inproceedings{yin2018learning,
    title={Learning to Represent Edits},
    author={Pengcheng Yin and Graham Neubig and Miltiadis Allamanis and Marc Brockschmidt and Alexander L. Gaunt},
    booktitle={International Conference on Learning Representations},
    year={2019},
    url={https://openreview.net/forum?id=BJl6AjC5F7},
}
Owner
NeuLab
Graham Neubig's Lab at LTI/CMU
NeuLab
Flybirds - BDD-driven natural language automated testing framework, present by Trip Flight

Flybird | English Version 行为驱动开发(Behavior-driven development,缩写BDD),是一种软件过程的思想或者

Ctrip, Inc. 706 Dec 30, 2022
List of awesome things around semantic segmentation 🎉

Awesome Semantic Segmentation List of awesome things around semantic segmentation 🎉 Semantic segmentation is a computer vision task in which we label

Dam Minh Tien 18 Nov 26, 2022
Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation [Arxiv] [Paper] As acquiring pixel-wise an

Lukas Hoyer 305 Dec 29, 2022
WatermarkRemoval-WDNet-WACV2021

WatermarkRemoval-WDNet-WACV2021 Thank you for your attention. Citation Please cite the related works in your publications if it helps your research: @

LUYI 63 Dec 05, 2022
Mouse Brain in the Model Zoo

Deep Neural Mouse Brain Modeling This is the repository for the ongoing deep neural mouse modeling project, an attempt to characterize the representat

Colin Conwell 15 Aug 22, 2022
[3DV 2020] PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction

PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction International Conference on 3D Vision, 2020 Sai Sagar Jinka1, Rohan

Rohan Chacko 39 Oct 12, 2022
[Nature Machine Intelligence' 21] "Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence"

[UCADI] COVID-19 Diagnosis With Federated Learning Intro We developed a Federated Learning (FL) Framework for global researchers to collaboratively tr

HUST EIC AI-LAB 30 Dec 12, 2022
Learning What and Where to Draw

###Learning What and Where to Draw Scott Reed, Zeynep Akata, Santosh Mohan, Samuel Tenka, Bernt Schiele, Honglak Lee This is the code for our NIPS 201

Scott Ellison Reed 337 Nov 18, 2022
CellRank's reproducibility repository.

CellRank's reproducibility repository We believe that reproducibility is key and have made it as simple as possible to reproduce our results. Please e

Theis Lab 8 Oct 08, 2022
A GUI to automatically create a TOPAS-readable MLC simulation file

Python script to create a TOPAS-readable simulation file descriring a Multi-Leaf-Collimator. Builds the MLC using the data from a 3D .stl file.

Sebastian Schäfer 0 Jun 19, 2022
Official PyTorch implementation of the paper "Self-Supervised Relational Reasoning for Representation Learning", NeurIPS 2020 Spotlight.

Official PyTorch implementation of the paper: "Self-Supervised Relational Reasoning for Representation Learning" (2020), Patacchiola, M., and Storkey,

Massimiliano Patacchiola 135 Jan 03, 2023
Codebase for the Summary Loop paper at ACL2020

Summary Loop This repository contains the code for ACL2020 paper: The Summary Loop: Learning to Write Abstractive Summaries Without Examples. Training

Canny Lab @ The University of California, Berkeley 44 Nov 04, 2022
Semi-supervised Stance Detection of Tweets Via Distant Network Supervision

SANDS This is an annonymous repository containing code and data necessary to reproduce the results published in "Semi-supervised Stance Detection of T

2 Sep 22, 2022
Federated Learning Based on Dynamic Regularization

Federated Learning Based on Dynamic Regularization This is implementation of Federated Learning Based on Dynamic Regularization. Requirements Please i

39 Jan 07, 2023
Dark Finix: All in one hacking framework with almost 100 tools

Dark Finix - Hacking Framework. Dark Finix is a all in one hacking framework wit

Md. Nur habib 2 Feb 18, 2022
Object DGCNN and DETR3D, Our implementations are built on top of MMdetection3D.

Object DGCNN & DETR3D This repo contains the implementations of Object DGCNN (https://arxiv.org/abs/2110.06923) and DETR3D (https://arxiv.org/abs/2110

Wang, Yue 539 Jan 07, 2023
Convert Mission Planner (ArduCopter) Waypoint Missions to Litchi CSV Format to execute on DJI Drones

Mission Planner to Litchi Convert Mission Planner (ArduCopter) Waypoint Surveys to Litchi CSV Format to execute on DJI Drones Litchi doesn't support S

Yaros 24 Dec 09, 2022
REBEL: Relation Extraction By End-to-end Language generation

REBEL: Relation Extraction By End-to-end Language generation This is the repository for the Findings of EMNLP 2021 paper REBEL: Relation Extraction By

Babelscape 222 Jan 06, 2023
Training Very Deep Neural Networks Without Skip-Connections

DiracNets v2 update (January 2018): The code was updated for DiracNets-v2 in which we removed NCReLU by adding per-channel a and b multipliers without

Sergey Zagoruyko 585 Oct 12, 2022
Simple SN-GAN to generate CryptoPunks

CryptoPunks GAN Simple SN-GAN to generate CryptoPunks. Neural network architecture and training code has been modified from the PyTorch DCGAN example.

Teddy Koker 66 Dec 15, 2022