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
Tensorflow Implementation of ECCV'18 paper: Multimodal Human Motion Synthesis

MT-VAE for Multimodal Human Motion Synthesis This is the code for ECCV 2018 paper MT-VAE: Learning Motion Transformations to Generate Multimodal Human

Xinchen Yan 36 Oct 02, 2022
PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition"

R2Plus1D-PyTorch PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal

Irhum Shafkat 342 Dec 16, 2022
Citation Intent Classification in scientific papers using the Scicite dataset an Pytorch

Citation Intent Classification Table of Contents About the Project Built With Installation Usage Acknowledgments About The Project Citation Intent Cla

Federico Nocentini 4 Mar 04, 2022
Based on the given clinical dataset, Predict whether the patient having Heart Disease or Not having Heart Disease

Heart_Disease_Classification Based on the given clinical dataset, Predict whether the patient having Heart Disease or Not having Heart Disease Dataset

Ashish 1 Jan 30, 2022
HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision

HugsVision is an open-source and easy to use all-in-one huggingface wrapper for computer vision. The goal is to create a fast, flexible and user-frien

Labrak Yanis 166 Nov 27, 2022
Voice Gender Recognition

In this project it was used some different Machine Learning models to identify the gender of a voice (Female or Male) based on some specific speech and voice attributes.

Anne Livia 1 Jan 27, 2022
LIMEcraft: Handcrafted superpixel selectionand inspection for Visual eXplanations

LIMEcraft LIMEcraft: Handcrafted superpixel selectionand inspection for Visual eXplanations The LIMEcraft algorithm is an explanatory method based on

MI^2 DataLab 4 Aug 01, 2022
3D Pose Estimation for Vehicles

3D Pose Estimation for Vehicles Introduction This work generates 4 key-points and 2 key-edges from vertices and edges of vehicles as ground truth. The

Jingyi Wang 1 Nov 01, 2021
Neural network for recognizing the gender of people in photos

Neural Network For Gender Recognition How to test it? Install requirements.txt file using pip install -r requirements.txt command Run nn.py using pyth

Valery Chapman 1 Sep 18, 2022
Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

Real-ESRGAN Colab Demo for Real-ESRGAN . Portable Windows executable file. You can find more information here. Real-ESRGAN aims at developing Practica

Xintao 17.2k Jan 02, 2023
A map update dataset and benchmark

MUNO21 MUNO21 is a dataset and benchmark for machine learning methods that automatically update and maintain digital street map datasets. Previous dat

16 Nov 30, 2022
This project is a re-implementation of MASTER: Multi-Aspect Non-local Network for Scene Text Recognition by MMOCR

This project is a re-implementation of MASTER: Multi-Aspect Non-local Network for Scene Text Recognition by MMOCR，which is an open-source toolbox based on PyTorch. The overall architecture will be sh

Jianquan Ye 82 Nov 17, 2022
A new video text spotting framework with Transformer

TransVTSpotter: End-to-end Video Text Spotter with Transformer Introduction A Multilingual, Open World Video Text Dataset and End-to-end Video Text Sp

weijiawu 67 Jan 03, 2023
codes for "Scheduled Sampling Based on Decoding Steps for Neural Machine Translation" (long paper of EMNLP-2022)

Scheduled Sampling Based on Decoding Steps for Neural Machine Translation (EMNLP-2021 main conference) Contents Overview Background Quick to Use Furth

Adaxry 13 Jul 25, 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
A fast model to compute optical flow between two input images.

DCVNet: Dilated Cost Volumes for Fast Optical Flow This repository contains our implementation of the paper: @InProceedings{jiang2021dcvnet, title={

Huaizu Jiang 8 Sep 27, 2021
Reviatalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation

Reviatalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation This is the implementation of the approach describ

Taosha Fan 47 Nov 15, 2022
Collaborative forensic timeline analysis

Timesketch Table of Contents About Timesketch Getting started Community Contributing About Timesketch Timesketch is an open-source tool for collaborat

Google 2.1k Dec 28, 2022
Privacy as Code for DSAR Orchestration: Privacy Request automation to fulfill GDPR, CCPA, and LGPD data subject requests.

Meet Fidesops: Privacy as Code for DSAR Orchestration A part of the greater Fides ecosystem. ⚡ Overview Fidesops (fee-dez-äps, combination of the Lati

Ethyca 44 Dec 06, 2022
Implementation of a Transformer using ReLA (Rectified Linear Attention)

ReLA (Rectified Linear Attention) Transformer Implementation of a Transformer using ReLA (Rectified Linear Attention). It will also contain an attempt

Phil Wang 49 Oct 14, 2022