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
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics

[AAAI2022] Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics Overall pipeline of OCN. Paper Link: [arXiv] [AAAI

13 Nov 21, 2022
PyTorch implementation of the Crafting Better Contrastive Views for Siamese Representation Learning

Crafting Better Contrastive Views for Siamese Representation Learning This is the official PyTorch implementation of the ContrastiveCrop paper: @artic

249 Dec 28, 2022
PyTorch Implement of Context Encoders: Feature Learning by Inpainting

Context Encoders: Feature Learning by Inpainting This is the Pytorch implement of CVPR 2016 paper on Context Encoders 1) Semantic Inpainting Demo Inst

321 Dec 25, 2022
A Flexible Generative Framework for Graph-based Semi-supervised Learning (NeurIPS 2019)

G3NN This repo provides a pytorch implementation for the 4 instantiations of the flexible generative framework as described in the following paper: A

Jiaqi Ma 14 Oct 11, 2022
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

PyTorch Image Models Sponsors What's New Introduction Models Features Results Getting Started (Documentation) Train, Validation, Inference Scripts Awe

Ross Wightman 22.9k Jan 09, 2023
House3D: A Rich and Realistic 3D Environment

House3D: A Rich and Realistic 3D Environment Yi Wu, Yuxin Wu, Georgia Gkioxari and Yuandong Tian House3D is a virtual 3D environment which consists of

Meta Research 1.1k Dec 14, 2022
Official Pytorch Implementation of Length-Adaptive Transformer (ACL 2021)

Length-Adaptive Transformer This is the official Pytorch implementation of Length-Adaptive Transformer. For detailed information about the method, ple

Clova AI Research 93 Dec 28, 2022
Locally Enhanced Self-Attention: Rethinking Self-Attention as Local and Context Terms

LESA Introduction This repository contains the official implementation of Locally Enhanced Self-Attention: Rethinking Self-Attention as Local and Cont

Chenglin Yang 20 Dec 31, 2021
This is the workbook I created while I was studying for the Qiskit Associate Developer exam. I hope this becomes useful to others as it was for me :)

A Workbook for the Qiskit Developer Certification Exam Hello everyone! This is Bartu, a fellow Qiskitter. I have recently taken the Certification exam

Bartu Bisgin 66 Dec 10, 2022
the code for our CVPR 2021 paper Bilateral Grid Learning for Stereo Matching Network [BGNet]

BGNet This repository contains the code for our CVPR 2021 paper Bilateral Grid Learning for Stereo Matching Network [BGNet] Environment Python 3.6.* C

3DCV developer 87 Nov 29, 2022
Code for the paper BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks

Biomedical Entity Linking This repo provides the code for the paper BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Res

Tuan Manh Lai 24 Oct 24, 2022
Complete U-net Implementation with keras

U Net Lowered with Keras Complete U-net Implementation with keras Original Paper Link : https://arxiv.org/abs/1505.04597 Special Implementations : The

Sagnik Roy 14 Oct 10, 2022
Tensorflow Implementation of SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE

SMU A Tensorflow Implementation of SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE arXiv https://arxiv.org/abs/211

Fuhang 5 Jan 18, 2022
Ağ tarayıcı.Gönderdiği paketler ile ağa bağlı olan cihazların IP adreslerini gösterir.

NetScanner.py Ağ tarayıcı.Gönderdiği paketler ile ağa bağlı olan cihazların IP adreslerini gösterir. Linux'da Kullanımı: git clone https://github.com/

4 Aug 23, 2021
Bayesian optimization in PyTorch

BoTorch is a library for Bayesian Optimization built on PyTorch. BoTorch is currently in beta and under active development! Why BoTorch ? BoTorch Prov

2.5k Dec 31, 2022
WSDM2022 Challenge - Large scale temporal graph link prediction

WSDM 2022 Large-scale Temporal Graph Link Prediction - Baseline and Initial Test Set WSDM Cup Website link Link to this challenge This branch offers A

Deep Graph Library 34 Dec 29, 2022
Simple object detection app with streamlit

object-detection-app Simple object detection app with streamlit. Upload an image and perform object detection. Adjust the confidence threshold to see

Robin Cole 68 Jan 02, 2023
[NeurIPS 2021 Spotlight] Aligning Pretraining for Detection via Object-Level Contrastive Learning

SoCo [NeurIPS 2021 Spotlight] Aligning Pretraining for Detection via Object-Level Contrastive Learning By Fangyun Wei*, Yue Gao*, Zhirong Wu, Han Hu,

Yue Gao 139 Dec 14, 2022
Implements pytorch code for the Accelerated SGD algorithm.

AccSGD This is the code associated with Accelerated SGD algorithm used in the paper On the insufficiency of existing momentum schemes for Stochastic O

205 Jan 02, 2023
[ICCV 2021] Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation

ADDS-DepthNet This is the official implementation of the paper Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation I

LIU_LINA 52 Nov 24, 2022