Repository for the paper titled: "When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer"

Related tags

Deep Learningmultilingualtransformerszero-shotcross-lingualmultilingual-bert
Overview

When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer

This repository contains code for our paper titled "When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer". [arXiv]

Table of contents

  1. Paper in a nutshell
  2. Installation
  3. Data and models
  4. Repository usage
  5. Links to experiments and results
  6. Citation

Paper in a nutshell

While recent work on multilingual language models has demonstrated their capacity for cross-lingual zero-shot transfer on downstream tasks, there is a lack of consensus in the community as to what shared properties between languages enable such transfer. Analyses involving pairs of natural languages are often inconclusive and contradictory since languages simultaneously differ in many linguistic aspects. In this paper, we perform a large-scale empirical study to isolate the effects of various linguistic properties by measuring zero-shot transfer between four diverse natural languages and their counterparts constructed by modifying aspects such as the script, word order, and syntax. Among other things, our experiments show that the absence of sub-word overlap significantly affects zero-shot transfer when languages differ in their word order, and there is a strong correlation between transfer performance and word embedding alignment between languages (e.g., Spearman's R=0.94 on the task of NLI). Our results call for focus in multilingual models on explicitly improving word embedding alignment between languages rather than relying on its implicit emergence.

Installation instructions

  1. Step 1: Install from the conda .yml file.
conda env create -f installation/multilingual.yml
  1. Step 2: Install transformers in an editable way.
pip install -e transformers/
pip install -r transformers/examples/language-modeling/requirements.txt
pip install -r transformers/examples/token-classification/requirements.txt

Repository usage

For the commands we used to get the reported numbers in the paper, click here. This file contains common instructions used. This file can automatically generate commands for your use case.

Bilingual pre-training

  1. For bilingual pre-training on original and derived language pairs, use the flag --invert_word_order for the Inversion transformation, --permute_words for Permutation and --one_to_one_mapping for Transliteration. Example command for bilingual pre-training for English with Inversion transformation to create the derived language pair.
nohup  python transformers/examples/xla_spawn.py --num_cores 8 transformers/examples/language-modeling/run_mlm_synthetic.py --warmup_steps 10000 --learning_rate 1e-4 --save_steps -1 --max_seq_length 512 --logging_steps 50 --overwrite_output_dir --model_type roberta --config_name config/en/roberta_8/config.json --tokenizer_name config/en/roberta_8/ --do_train --do_eval --max_steps 500000 --per_device_train_batch_size 16 --per_device_eval_batch_size 16 --train_file ../../bucket/pretrain_data/en/train.txt --validation_file ../../bucket/pretrain_data/en/valid.txt --output_dir ../../bucket/model_outputs/en/inverted_order_500K/mlm --run_name inverted_en_500K_mlm --invert_word_order --word_modification add &
  1. For Syntax transformations, the train file used in the following command ([email protected][email protected]) means that it is the concatenation of French corpus with French modified to English verb and noun order ([email protected][email protected]).
nohup python transformers/examples/xla_spawn.py --num_cores 8 transformers/examples/language-modeling/run_mlm_synthetic.py --warmup_steps 10000 --learning_rate 1e-4 --save_steps -1 --max_seq_length 512 --logging_steps 50 --overwrite_output_dir --model_type roberta --config_name config/fr/roberta_8/config.json --tokenizer_name config/fr/roberta_8/ --do_train --do_eval --max_steps 500000 --per_device_train_batch_size 16 --per_device_eval_batch_size 16 --train_file ../../bucket/pretrain_data/fr/synthetic/[email protected][email protected] --validation_file ../../bucket/pretrain_data/fr/synthetic/[email protected][email protected] --output_dir ../../bucket/model_outputs/fr/syntax_modif_en/mlm --run_name fr_syntax_modif_en_500K_mlm &
  1. For composed transformations, apply multiple transformations by using multiple flags, e.g., --one_to_one_mapping --invert_word_order.
nohup python transformers/examples/xla_spawn.py --num_cores 8 transformers/examples/language-modeling/run_mlm_synthetic.py --warmup_steps 10000 --learning_rate 1e-4 --save_steps -1 --max_seq_length 512 --logging_steps 50 --overwrite_output_dir --model_type roberta --config_name config/en/roberta_8/config.json --tokenizer_name config/en/roberta_8/ --do_train --do_eval --max_steps 500000 --per_device_train_batch_size 16 --per_device_eval_batch_size 16 --train_file ../../bucket/pretrain_data/en/train.txt --validation_file ../../bucket/pretrain_data/en/valid.txt --output_dir ../../bucket/model_outputs/en/one_to_one_inverted/mlm --run_name en_one_to_one_inverted --one_to_one_mapping --invert_word_order --word_modification add &
  1. Using different domains for the original and derived language.
nohup python transformers/examples/xla_spawn.py --num_cores 8 transformers/examples/language-modeling/run_mlm_synthetic_transitive.py --warmup_steps 10000 --learning_rate 1e-4 --save_steps -1 --max_seq_length 512 --logging_steps 50 --overwrite_output_dir --model_type roberta --config_name config/en/roberta_8/config.json --tokenizer_name config/en/roberta_8/ --do_train --do_eval --max_steps 500000 --per_device_train_batch_size 16 --per_device_eval_batch_size 16 --train_file ../../bucket/pretrain_data/en/train_split_1.txt --transitive_file ../../bucket/pretrain_data/en/train_split_2.txt --validation_file ../../bucket/pretrain_data/en/valid.txt --output_dir ../../bucket/model_outputs/en/one_to_one_diff_source_100_more_steps/mlm --run_name en_one_to_one_diff_source_100_more_steps --one_to_one_mapping --word_modification add &

Fine-tuning and evaluation

This directory contains scripts used for downstream fine-tuning and evaluation.

  1. Transliteration, Inversion, and Permutation
  2. Syntax
  3. Composed transformations
  4. Using different domains for original and derived languages

Embedding alignment

Use this script to calculate embedding alignment for any model which uses Transliteration as one of the transformations.

Data and models

All the data used for our experiments, hosted on Google Cloud Bucket.

  1. Pre-training data - pretrain_data
  2. Downstream data - supervised_data
  3. Model files - model_outputs

Links to experiments and results

  1. Spreadsheets with run descriptions, commands, and weights and biases link
  2. Spreadsheet with all results
  3. Links to pre-training runs
  4. Link to fine-tuning and analysis

Citation

Please consider citing if you used our paper in your work!

To be updated soon!
Owner
Princeton Natural Language Processing
Princeton Natural Language Processing
GitHub Repository
Code for the paper "M2m: Imbalanced Classification via Major-to-minor Translation" (CVPR 2020)

M2m: Imbalanced Classification via Major-to-minor Translation This repository contains code for the paper "M2m: Imbalanced Classification via Major-to

79 Oct 13, 2022
Github for the conference paper GLOD-Gaussian Likelihood OOD detector

FOOD - Fast OOD Detector Pytorch implamentation of the confernce peper FOOD arxiv link. Abstract Deep neural networks (DNNs) perform well at classifyi

17 Jun 19, 2022
PyTorch implementation of neural style randomization for data augmentation

README Augment training images for deep neural networks by randomizing their visual style, as described in our paper: https://arxiv.org/abs/1809.05375

84 Nov 23, 2022
The official PyTorch implementation for the paper "sMGC: A Complex-Valued Graph Convolutional Network via Magnetic Laplacian for Directed Graphs".

Magnetic Graph Convolutional Networks About The official PyTorch implementation for the paper sMGC: A Complex-Valued Graph Convolutional Network via M

3 Feb 25, 2022
Existing Literature about Machine Unlearning

Machine Unlearning Papers 2021 Brophy and Lowd. Machine Unlearning for Random Forests. In ICML 2021. Bourtoule et al. Machine Unlearning. In IEEE Symp

Jonathan Brophy 213 Jan 08, 2023
Magic tool for managing internet connection in local network by @zalexdev

Megacut ✂️ A new powerful Python3 tool for managing internet on a local network Installation git clone https://github.com/stryker-project/megacut cd m

Stryker 12 Dec 15, 2022
Modular Gaussian Processes

Modular Gaussian Processes for Transfer Learning 🧩 Introduction This repository contains the implementation of our paper Modular Gaussian Processes f

Pablo Moreno-Muñoz 10 Mar 15, 2022
Centroid-UNet is deep neural network model to detect centroids from satellite images.

Centroid UNet - Locating Object Centroids in Aerial/Serial Images Introduction Centroid-UNet is deep neural network model to detect centroids from Aer

GIC-AIT 19 Dec 08, 2022
Amazing-Python-Scripts - 🚀 Curated collection of Amazing Python scripts from Basics to Advance with automation task scripts.

📑 Introduction A curated collection of Amazing Python scripts from Basics to Advance with automation task scripts. This is your Personal space to fin

Avinash Ranjan 1.1k Dec 29, 2022
Ludwig is a toolbox that allows to train and evaluate deep learning models without the need to write code.

Translated in 🇰🇷 Korean/ Ludwig is a toolbox that allows users to train and test deep learning models without the need to write code. It is built on

<

Ludwig 8.7k Jan 05, 2023
Repo for EchoVPR: Echo State Networks for Visual Place Recognition

EchoVPR Repo for EchoVPR: Echo State Networks for Visual Place Recognition Currently under development Dirs: data: pre-collected hidden representation

Anil Ozdemir 4 Oct 04, 2022
这个开源项目主要是对经典的时间序列预测算法论文进行复现，模型主要参考自GluonTS，框架主要参考自Informer

Time Series Research with Torch 这个开源项目主要是对经典的时间序列预测算法论文进行复现，模型主要参考自GluonTS，框架主要参考自Informer。 建立原因 相较于mxnet和TF，Torch框架中的神经网络层需要提前指定输入维度： # 建立线性层 TensorF

Chi Zhang 85 Dec 29, 2022
A list of Machine Learning Art Colabs

ML Visual Art Colabs A list of cool Colabs on Machine Learning Imagemaking or other artistic purposes 3D Ken Burns Effect Ken Burns Effect by Manuel R

Derrick Schultz (he/him) 789 Dec 12, 2022
pq is a jq-like Pickle file viewer

pq PQ is a jq-like viewer/processing tool for pickle files. howto # pq '' file.pkl {'other': 456, 'test': 123} # pq 'table' file.pkl |other|test| | 45

3 Mar 15, 2022
Supporting code for the paper "Dangers of Bayesian Model Averaging under Covariate Shift"

Dangers of Bayesian Model Averaging under Covariate Shift This repository contains the code to reproduce the experiments in the paper Dangers of Bayes

Pavel Izmailov 25 Sep 21, 2022
wgan, wgan2(improved, gp), infogan, and dcgan implementation in lasagne, keras, pytorch

Generative Adversarial Notebooks Collection of my Generative Adversarial Network implementations Most codes are for python3, most notebooks works on C

tjwei 1.5k Dec 16, 2022
Ansible Automation Example: JSNAPY PRE/POST Upgrade Validation

Ansible Automation Example: JSNAPY PRE/POST Upgrade Validation Overview This example will show how to validate the status of our firewall before and a

Calvin Remsburg 1 Jan 07, 2022
A reimplementation of DCGAN in PyTorch

DCGAN in PyTorch A reimplementation of DCGAN in PyTorch. Although there is an abundant source of code and examples found online (as well as an officia

Diego Porres 6 Jan 08, 2022
I have created this Virtual Paint Program, in this you can paint(draw) on your screen using hand gestures, created in Python-3 using OpenCV and Mediapipe library. Gestures :- Index Finger for drawing and Index+Middle Finger for changing position and objects.

Virtual-Paint I have created this Virtual Paint Program, in this you can paint(draw) on your screen using hand gestures, created in Python-3. Gestures

Tejas Prajapati 6 Sep 22, 2021
This code is the implementation of the paper "Coherence-Based Distributed Document Representation Learning for Scientific Documents".

Introduction This code is the implementation of the paper "Coherence-Based Distributed Document Representation Learning for Scientific Documents". If

tsc 0 Jan 11, 2022