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
[CVPR 2021] 'Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator'

[CVPR2021] Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator Overview This is the entire codebase for the paper

35 Dec 01, 2022
An efficient and easy-to-use deep learning model compression framework

TinyNeuralNetwork 简体中文 TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework, which contains features like neura

Alibaba 441 Dec 25, 2022
A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.

python_graphs This package is for computing graph representations of Python programs for machine learning applications. It includes the following modu

Google Research 258 Dec 29, 2022
Code for the paper "Next Generation Reservoir Computing"

Next Generation Reservoir Computing This is the code for the results and figures in our paper "Next Generation Reservoir Computing". They are written

OSU QuantInfo Lab 105 Dec 20, 2022
Self-attentive task GAN for space domain awareness data augmentation.

SATGAN TODO: update the article URL once published. Article about this implemention The self-attentive task generative adversarial network (SATGAN) le

Nathan 2 Mar 24, 2022
Pytorch code for paper "Image Compressed Sensing Using Non-local Neural Network" TMM 2021.

NL-CSNet-Pytorch Pytorch code for paper "Image Compressed Sensing Using Non-local Neural Network" TMM 2021. Note: this repo only shows the strategy of

WenxueCui 7 Nov 07, 2022
Get the partition that a file belongs and the percentage of space that consumes

tinos_eisai_sy Get the partition that a file belongs and the percentage of space that consumes (works only with OSes that use the df command) tinos_ei

Konstantinos Patronas 6 Jan 24, 2022
LIVECell - A large-scale dataset for label-free live cell segmentation

LIVECell dataset This document contains instructions of how to access the data associated with the submitted manuscript "LIVECell - A large-scale data

Sartorius Corporate Research 112 Jan 07, 2023
A general 3D Object Detection codebase in PyTorch.

Det3D is the first 3D Object Detection toolbox which provides off the box implementations of many 3D object detection algorithms such as PointPillars, SECOND, PIXOR, etc, as well as state-of-the-art

Benjin Zhu 1.4k Jan 05, 2023
This is code of book "Learn Deep Learning with PyTorch"

深度学习入门之PyTorch Learn Deep Learning with PyTorch 非常感谢您能够购买此书，这个github repository包含有深度学习入门之PyTorch的实例代码。由于本人水平有限，在写此书的时候参考了一些网上的资料，在这里对他们表示敬意。由于深度学习的技术在

Xingyu Liao 2.5k Jan 04, 2023
This project uses ViT to perform image classification tasks on DATA set CIFAR10.

Vision-Transformer-Multiprocess-DistributedDataParallel-Apex Introduction This project uses ViT to perform image classification tasks on DATA set CIFA

Kaicheng Yang 3 Jun 03, 2022
Compute FID scores with PyTorch.

FID score for PyTorch This is a port of the official implementation of Fréchet Inception Distance to PyTorch. See https://github.com/bioinf-jku/TTUR f

2.1k Jan 06, 2023
An implementation of IMLE-Net: An Interpretable Multi-level Multi-channel Model for ECG Classification

IMLE-Net: An Interpretable Multi-level Multi-channel Model for ECG Classification The repostiory consists of the code, results and data set links for

12 Dec 26, 2022
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Peter Lin 6.5k Jan 04, 2023
Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis

Readme File for "Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis" by Ham, Imai, and Janson. (2022) All scripts were written and

0 Jan 27, 2022
[CVPR'21] Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild

IVOS-W Paper Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild Zhaoyun Yin, Jia Zheng, Weixin Luo, Shenhan Qian, Hanli

SVIP Lab 38 Dec 12, 2022
Multi-Agent Reinforcement Learning (MARL) method to learn scalable control polices for multi-agent target tracking.

scalableMARL Scalable Reinforcement Learning Policies for Multi-Agent Control CD. Hsu, H. Jeong, GJ. Pappas, P. Chaudhari. "Scalable Reinforcement Lea

Christopher Hsu 17 Nov 17, 2022
Tensorflow2.0 🍎🍊 is delicious, just eat it! 😋😋

How to eat TensorFlow2 in 30 days ? 🔥 🔥 Click here for Chinese Version（中文版） 《10天吃掉那只pyspark》 🚀 github项目地址: https://github.com/lyhue1991/eat_pyspark

lyhue1991 9.7k Jan 01, 2023
Learning to Simulate Dynamic Environments with GameGAN (CVPR 2020)

Learning to Simulate Dynamic Environments with GameGAN PyTorch code for GameGAN Learning to Simulate Dynamic Environments with GameGAN Seung Wook Kim,

199 Dec 26, 2022
EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers

EntityQuestions This repository contains the EntityQuestions dataset as well as code to evaluate retrieval results from the the paper Simple Entity-ce

Princeton Natural Language Processing 119 Sep 28, 2022