Improving Machine Translation Systems via Isotopic Replacement

Related tags

Deep LearningCAT
Overview

CAT (Improving Machine Translation Systems via Isotopic Replacement)

Machine translation plays an essential role in people’s daily international communication. However, machine translation systems are far from perfect. To tackle this problem, researchers have proposed several approaches to testing machine translation. A promising trend among these approaches is to use word replacement, where only one word in the original sentence is replaced with another word to form a sentence pair. However, precise control of the impact of word replacement remains an outstanding issue in these approaches.

To address this issue, we propose CAT, a novel word-replacement-based approach, whose basic idea is to identify word replacement with controlled impact (referred to as isotopic replacement). To achieve this purpose, we use a neural-based language model to encode the sentence context, and design a neural-network-based algorithm to evaluate context-aware semantic similarity between two words. Furthermore, similar to TransRepair, a state-of-the-art word-replacement-based approach, CAT also provides automatic fixing of revealed bugs without model retraining.

Our evaluation on Google Translate and Transformer indicates that CAT achieves significant improvements over TransRepair. In particular, 1) CAT detects seven more types of bugs than TransRepair; 2) CAT detects 129% more translation bugs than TransRepair; 3) CAT repairs twice more bugs than TransRepair, many of which may bring serious consequences if left unfixed; and 4) CAT has better efficiency than TransRepair in input generation (0.01s v.s. 0.41s) and comparable efficiency with TransRepair in bug repair (1.92s v.s. 1.34s).

The main file tree of CAT

.
├── Labeled data
│   ├── RQ1 Test Input Generation
│   ├── RQ2 Bug Detection
│   ├── RQ3 Bug Repair
│   └── Extended Analysis
├── TS
├── MutantGen-Test.py
├── MutantGen-Repair.py
├── Repair.py
├── Testing.py
├── NewThres
│   ├── TestGenerator-NMT
│   └── TestGenerator-NMTRep
└── NMT_zh_en0-8Mu
    ├── padTrans
    └── repair-new

The manual assessment results are in the Labeled data folder.

For Testing:

python3 Testing.py

After it, the results are in the NMT_zh_en0-8Mu/padTrans folder.

For Repair:

python3 Repair.py

After it, the results are in the TS/quickstart0/repair-NEW folder.

Data

The LookUpTable.txt used in NMT_zh_en_0-8Mu/padTrans and NMT_zh_en_0-8Mu/repair-new is available at https://drive.google.com/file/d/1fjGpryzGohla0ZA4u7KDgRJeAHegy0A1/view?usp=sharing

Dependenices

NLTK 3.2.1
Pytorch 1.6.1
Python 3.7
Ubuntu 16.04
Transformers 3.3.0
Owner
Zeyu Sun
A Ph.D. student.
Zeyu Sun
Data and analysis code for an MS on SK VOC genomes phenotyping/neutralisation assays

Description Summary of phylogenomic methods and analyses used in "Immunogenicity of convalescent and vaccinated sera against clinical isolates of ance

Finlay Maguire 1 Jan 06, 2022
A Lighting Pytorch Framework for Recommendation System, Easy-to-use and Easy-to-extend.

Torch-RecHub A Lighting Pytorch Framework for Recommendation Models, Easy-to-use and Easy-to-extend. 安装 pip install torch-rechub 主要特性 scikit-learn风格易用

Mincai Lai 67 Jan 04, 2023
BiSeNet based on pytorch

BiSeNet BiSeNet based on pytorch 0.4.1 and python 3.6 Dataset Download CamVid dataset from Google Drive or Baidu Yun(6xw4). Pretrained model Download

367 Dec 26, 2022
SimpleDepthEstimation - An unified codebase for NN-based monocular depth estimation methods

SimpleDepthEstimation Introduction This is an unified codebase for NN-based monocular depth estimation methods, the framework is based on detectron2 (

8 Dec 13, 2022
Repository for self-supervised landmark discovery

self-supervised-landmarks Repository for self-supervised landmark discovery Requirements pytorch pynrrd (for 3d images) Usage The use of this models i

Riddhish Bhalodia 2 Apr 18, 2022
A flexible framework of neural networks for deep learning

Chainer: A deep learning framework Website | Docs | Install Guide | Tutorials (ja) | Examples (Official, External) | Concepts | ChainerX Forum (en, ja

Chainer 5.8k Jan 06, 2023
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

dm_control: DeepMind Infrastructure for Physics-Based Simulation. DeepMind's software stack for physics-based simulation and Reinforcement Learning en

DeepMind 3k Dec 31, 2022
Dataset Condensation with Contrastive Signals

Dataset Condensation with Contrastive Signals This repository is the official implementation of Dataset Condensation with Contrastive Signals (DCC). T

3 May 19, 2022
Styled Handwritten Text Generation with Transformers (ICCV 21)

⚡ Handwriting Transformers [PDF] Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan & Mubarak Shah Abstract: We

Ankan Kumar Bhunia 85 Dec 22, 2022
FairMOT - A simple baseline for one-shot multi-object tracking

FairMOT - A simple baseline for one-shot multi-object tracking

Yifu Zhang 3.6k Jan 08, 2023
Hierarchical Few-Shot Generative Models

Hierarchical Few-Shot Generative Models Giorgio Giannone, Ole Winther This repo contains code and experiments for the paper Hierarchical Few-Shot Gene

Giorgio Giannone 6 Dec 12, 2022
Towhee is a flexible machine learning framework currently focused on computing deep learning embeddings over unstructured data.

Towhee is a flexible machine learning framework currently focused on computing deep learning embeddings over unstructured data.

1.7k Jan 08, 2023
Keras implementations of Generative Adversarial Networks.

This repository has gone stale as I unfortunately do not have the time to maintain it anymore. If you would like to continue the development of it as

Erik Linder-Norén 8.9k Jan 04, 2023
Registration Loss Learning for Deep Probabilistic Point Set Registration

RLLReg This repository contains a Pytorch implementation of the point set registration method RLLReg. Details about the method can be found in the 3DV

Felix Järemo Lawin 35 Nov 02, 2022
XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale

XtremeDistilTransformers for Distilling Massive Multilingual Neural Networks ACL 2020 Microsoft Research [Paper] [Video] Releasing [XtremeDistilTransf

Microsoft 125 Jan 04, 2023
El-Gamal on Elliptic Curve (Python)

El-Gamal-on-EC El-Gamal on Elliptic Curve (Python) References: https://docsdrive.com/pdfs/ansinet/itj/2005/299-306.pdf https://arxiv.org/ftp/arxiv/pap

3 May 04, 2022
This is a Python Module For Encryption, Hashing And Other stuff

EnroCrypt This is a Python Module For Encryption, Hashing And Other Basic Stuff You Need, With Secure Encryption And Strong Salted Hashing You Can Do

5 Sep 15, 2022
Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection

Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection Main requirements torch = 1.0 torchvision = 0.2.0 Python 3 Environm

15 Apr 04, 2022
Latent Execution for Neural Program Synthesis

Latent Execution for Neural Program Synthesis This repo provides the code to replicate the experiments in the paper Xinyun Chen, Dawn Song, Yuandong T

Xinyun Chen 16 Oct 02, 2022
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

Tensorpack is a neural network training interface based on TensorFlow. Features: It's Yet Another TF high-level API, with speed, and flexibility built

Tensorpack 6.2k Jan 01, 2023