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
TorchMD-Net provides state-of-the-art graph neural networks and equivariant transformer neural networks potentials for learning molecular potentials

TorchMD-net TorchMD-Net provides state-of-the-art graph neural networks and equivariant transformer neural networks potentials for learning molecular

TorchMD 104 Jan 03, 2023
A keras implementation of ENet (abandoned for the foreseeable future)

ENet-keras This is an implementation of ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation, ported from ENet-training (lua-t

Pavlos 115 Nov 23, 2021
Open standard for machine learning interoperability

Open Neural Network Exchange (ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides

Open Neural Network Exchange 13.9k Dec 30, 2022
All course materials for the Zero to Mastery Deep Learning with TensorFlow course.

All course materials for the Zero to Mastery Deep Learning with TensorFlow course.

Daniel Bourke 3.4k Jan 07, 2023
FIRA: Fine-Grained Graph-Based Code Change Representation for Automated Commit Message Generation

FIRA is a learning-based commit message generation approach, which first represents code changes via fine-grained graphs and then learns to generate commit messages automatically.

Van 21 Dec 30, 2022
.NET bindings for the Pytorch engine

TorchSharp TorchSharp is a .NET library that provides access to the library that powers PyTorch. It is a work in progress, but already provides a .NET

Matteo Interlandi 17 Aug 30, 2021
Script utilizando OpenCV e modelo Machine Learning para detectar o uso de máscaras.

Reconhecendo máscaras Este repositório contém um script em Python3 que reconhece se um rosto está ou não portando uma máscara! O código utiliza da bib

Maria Eduarda de Azevedo Silva 168 Oct 20, 2022
LWCC: A LightWeight Crowd Counting library for Python that includes several pretrained state-of-the-art models.

LWCC: A LightWeight Crowd Counting library for Python LWCC is a lightweight crowd counting framework for Python. It wraps four state-of-the-art models

Matija Teršek 39 Dec 28, 2022
Back to Event Basics: SSL of Image Reconstruction for Event Cameras

Back to Event Basics: SSL of Image Reconstruction for Event Cameras Minimal code for Back to Event Basics: Self-Supervised Learning of Image Reconstru

TU Delft 42 Dec 26, 2022
Simple Pixelbot for Diablo 2 Resurrected written in python and opencv.

Simple Pixelbot for Diablo 2 Resurrected written in python and opencv. Obviously only use it in offline mode as it is against the TOS of Blizzard to use it in online mode!

468 Jan 03, 2023
Joint Versus Independent Multiview Hashing for Cross-View Retrieval[J] (IEEE TCYB 2021, PyTorch Code)

Thanks to the low storage cost and high query speed, cross-view hashing (CVH) has been successfully used for similarity search in multimedia retrieval. However, most existing CVH methods use all view

4 Nov 19, 2022
bio_inspired_min_nets_improve_the_performance_and_robustness_of_deep_networks

Code Submission for: Bio-inspired Min-Nets Improve the Performance and Robustness of Deep Networks Run with docker To build a docker environment, chan

0 Dec 09, 2021
GNN4Traffic - This is the repository for the collection of Graph Neural Network for Traffic Forecasting

GNN4Traffic - This is the repository for the collection of Graph Neural Network for Traffic Forecasting

564 Jan 02, 2023
The repository for our EMNLP 2021 paper "Finnish Dialect Identification: The Effect of Audio and Text"

Finnish Dialect Identification The repository for our EMNLP 2021 paper "Finnish Dialect Identification: The Effect of Audio and Text". We present a te

Rootroo Ltd 2 Dec 25, 2021
Bringing sanity to world of messed-up data

Sanitize sanitize is a Python module for making sure various things (e.g. HTML) are safe to use. It was originally written by Mark Pilgrim and is dist

Alireza Savand 63 Oct 26, 2021
Array Camera Ptychography

Array Camera Ptychography This repository provides the code for the following papers: Schulz, Timothy J., David J. Brady, and Chengyu Wang. "Photon-li

Brady lab in Optical Sciences 1 Nov 15, 2021
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
Repository for training material for the 2022 SDSC HPC/CI User Training Course

hpc-training-2022 Repository for training material for the 2022 SDSC HPC/CI Training Series HPC/CI Training Series home https://www.sdsc.edu/event_ite

sdsc-hpc-training-org 21 Jul 27, 2022
Fast, general, and tested differentiable structured prediction in PyTorch

Fast, general, and tested differentiable structured prediction in PyTorch

HNLP 1.1k Dec 16, 2022
Code and models for ICCV2021 paper "Robust Object Detection via Instance-Level Temporal Cycle Confusion".

Robust Object Detection via Instance-Level Temporal Cycle Confusion This repo contains the implementation of the ICCV 2021 paper, Robust Object Detect

Xin Wang 69 Oct 13, 2022