System Combination for Grammatical Error Correction Based on Integer Programming

Related tags

Deep Learninggec_ip
Overview

System Combination for Grammatical Error Correction Based on Integer Programming


This repository contains the code and scripts that implement the system combination approach for grammatical error correction in Lin and Ng (2021).

Reference

Ruixi Lin and Hwee Tou Ng (2021). System Combination for Grammatical Error Correction Based on Integer Programming.

Please cite:

@inproceedings{lin2021gecip,
  author    = "Lin, Ruixi and Ng, Hwee Tou",
  title     = "System Combination for Grammatical Error Correction Based on Integer Programming",
  booktitle = "Proceedings of Recent Advances in Natural Language Processing",
  year      = "2021",
  pages     = "829-834"
}

Table of contents

Prerequisites

Example

License

Prerequisites

conda create --name comb python=3.6
conda activate comb
pip install spacy
python -m spacy download en

For the nonlinear integer programming solver, we use

LINGO10.0

Note that educational institutions can obtain a free license to use the LINGO solver.

Example

Combine the 3 GEC systems listed in the paper using the IP approach. The three systems are UEdin-MS (https://aclanthology.org/W19-4427), Kakao (https://aclanthology.org/W19-4423), and Tohoku (https://aclanthology.org/D19-1119). The core functions for the IP objective are implemented in model.lg4. You can find model.lg4 under lingo/inputs.

  1. Run python prepare_data.py -dir . -list kakao uedinms tohoku to generate aggregated TP, FP, and FN counts. The counts files are stored under lingo/inputs.

  2. Load model.lg4 into the LINGO console and specify the input data path with the counts file path, select the INLP model, and run optimizations. Store the solutions to lingo/outputs/sol_kakao_uedinms_tohoku.txt.

  3. Run ./comb.sh . sol_kakao_uedinms_tohoku.txt to load LINGO solutions, merge and apply edits. The resulted blind test file can be found under submissions. It can be zipped and submitted to the BEA CodeLab website (https://competitions.codalab.org/competitions/20228) for evaluations.

The data folder provides individual GEC system output files, and .m2 files generated using ERRANT for the listed systems. For more information, please visit the ERRANT github page.

We include the IP combined .m2 files under merged_m2, and the corresponding text files under submissions.

License

The source code and models in this repository are licensed under the GNU General Public License v3.0 (see LICENSE). For further research interests and commercial use of the code and models, please contact Ruixi Lin ([email protected]) and Prof. Hwee Tou Ng ([email protected]).

Owner
NUS NLP Group
National University of Singapore
NUS NLP Group
Official repository for "Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring".

RNN-MBP Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring (AAAI-2022) by Chao Zhu, Hang Dong, Jinshan Pan

SIV-LAB 22 Aug 31, 2022
Allows including an action inside another action (by preprocessing the Yaml file). This is how composite actions should have worked.

actions-includes Allows including an action inside another action (by preprocessing the Yaml file). Instead of using uses or run in your action step,

Tim Ansell 70 Nov 04, 2022
Image process framework based on plugin like imagej, it is esay to glue with scipy.ndimage, scikit-image, opencv, simpleitk, mayavi...and any libraries based on numpy

Introduction ImagePy is an open source image processing framework written in Python. Its UI interface, image data structure and table data structure a

ImagePy 1.2k Dec 29, 2022
HCQ: Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval

HCQ: Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval [toc] 1. Introduction This repository provides the code for our paper at

13 Dec 08, 2022
Framework to build and train RL algorithms

RayLink RayLink is a RL framework used to build and train RL algorithms. RayLink was used to build a RL framework, and tested in a large-scale multi-a

Bytedance Inc. 32 Oct 07, 2022
a generic C++ library for image analysis

VIGRA Computer Vision Library Copyright 1998-2013 by Ullrich Koethe This file is part of the VIGRA computer vision library. You may use,

Ullrich Koethe 378 Dec 30, 2022
MODALS: Modality-agnostic Automated Data Augmentation in the Latent Space

Update (20 Jan 2020): MODALS on text data is avialable MODALS MODALS: Modality-agnostic Automated Data Augmentation in the Latent Space Table of Conte

38 Dec 15, 2022
A PyTorch implementation of Mugs proposed by our paper "Mugs: A Multi-Granular Self-Supervised Learning Framework".

Mugs: A Multi-Granular Self-Supervised Learning Framework This is a PyTorch implementation of Mugs proposed by our paper "Mugs: A Multi-Granular Self-

Sea AI Lab 62 Nov 08, 2022
Pytoydl: A toy deep learning framework built upon numpy.

Documents: https://pytoydl.readthedocs.io/zh/latest/ Pytoydl A toy deep learning framework built upon numpy. You can star this repository to keep trac

28 Dec 10, 2022
A novel benchmark dataset for Monocular Layout prediction

AutoLay AutoLay: Benchmarking Monocular Layout Estimation Kaustubh Mani, N. Sai Shankar, J. Krishna Murthy, and K. Madhava Krishna Abstract In this pa

Kaustubh Mani 39 Apr 26, 2022
Official implementation of the MM'21 paper Constrained Graphic Layout Generation via Latent Optimization

[MM'21] Constrained Graphic Layout Generation via Latent Optimization This repository provides the official code for the paper "Constrained Graphic La

Kotaro Kikuchi 73 Dec 27, 2022
Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using coresets and data selection.

COResets and Data Subset selection Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order

decile-team 244 Jan 09, 2023
PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

PRIME: A Few Primitives Can Boost Robustness to Common Corruptions This is the official repository of PRIME, the data agumentation method introduced i

Apostolos Modas 34 Oct 30, 2022
Weakly supervised medical named entity classification

Trove Trove is a research framework for building weakly supervised (bio)medical named entity recognition (NER) and other entity attribute classifiers

60 Nov 18, 2022
Unofficial Tensorflow Implementation of ConvNeXt from A ConvNet for the 2020s

Tensorflow Implementation of "A ConvNet for the 2020s" This is the unofficial Tensorflow Implementation of ConvNeXt from "A ConvNet for the 2020s" pap

DK 11 Oct 12, 2022
TensorFlow implementation of "Learning from Simulated and Unsupervised Images through Adversarial Training"

Simulated+Unsupervised (S+U) Learning in TensorFlow TensorFlow implementation of Learning from Simulated and Unsupervised Images through Adversarial T

Taehoon Kim 569 Dec 29, 2022
Marine debris detection with commercial satellite imagery and deep learning.

Marine debris detection with commercial satellite imagery and deep learning. Floating marine debris is a global pollution problem which threatens mari

Inter Agency Implementation and Advanced Concepts 56 Dec 16, 2022
Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021.

Dense Contrastive Learning for Self-Supervised Visual Pre-Training This project hosts the code for implementing the DenseCL algorithm for se

Xinlong Wang 491 Jan 03, 2023
Bayesian regularization for functional graphical models.

BayesFGM Paper: Jiajing Niu, Andrew Brown. Bayesian regularization for functional graphical models. Requirements R version 3.6.3 and up Python 3.6 and

0 Oct 07, 2021
Using some basic methods to show linkages and transformations of robotic arms

roboticArmVisualizer Python GUI application to create custom linkages and adjust joint angles. In the future, I plan to add 2d inverse kinematics solv

Sandesh Banskota 1 Nov 19, 2021