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
DRIFT is a tool for Diachronic Analysis of Scientific Literature.

About DRIFT is a tool for Diachronic Analysis of Scientific Literature. The application offers user-friendly and customizable utilities for two modes:

Rajaswa Patil 108 Dec 12, 2022
Official code implementation for "Personalized Federated Learning using Hypernetworks"

Personalized Federated Learning using Hypernetworks This is an official implementation of Personalized Federated Learning using Hypernetworks paper. [

Aviv Shamsian 121 Dec 25, 2022
Implementation of CVPR 2021 paper "Spatially-invariant Style-codes Controlled Makeup Transfer"

SCGAN Implementation of CVPR 2021 paper "Spatially-invariant Style-codes Controlled Makeup Transfer" Prepare The pre-trained model is avaiable at http

118 Dec 12, 2022
Pytorch implementation of 'Fingerprint Presentation Attack Detector Using Global-Local Model'

RTK-PAD This is an official pytorch implementation of 'Fingerprint Presentation Attack Detector Using Global-Local Model', which is accepted by IEEE T

6 Aug 01, 2022
docTR by Mindee (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

docTR by Mindee (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

Mindee 1.5k Jan 01, 2023
This is a Machine Learning Based Hand Detector Project, It Uses Machine Learning Models and Modules Like Mediapipe, Developed By Google!

Machine Learning Hand Detector This is a Machine Learning Based Hand Detector Project, It Uses Machine Learning Models and Modules Like Mediapipe, Dev

Popstar Idhant 3 Feb 25, 2022
A PyTorch implementation of the Relational Graph Convolutional Network (RGCN).

Torch-RGCN Torch-RGCN is a PyTorch implementation of the RGCN, originally proposed by Schlichtkrull et al. in Modeling Relational Data with Graph Conv

Thiviyan Singam 66 Nov 30, 2022
Tensorflow implementation of ID-Unet: Iterative Soft and Hard Deformation for View Synthesis.

ID-Unet: Iterative-view-synthesis(CVPR2021 Oral) Tensorflow implementation of ID-Unet: Iterative Soft and Hard Deformation for View Synthesis. Overvie

17 Aug 23, 2022
Binary Passage Retriever (BPR) - an efficient passage retriever for open-domain question answering

BPR Binary Passage Retriever (BPR) is an efficient neural retrieval model for open-domain question answering. BPR integrates a learning-to-hash techni

Studio Ousia 147 Dec 07, 2022
Prototype-based Incremental Few-Shot Semantic Segmentation

Prototype-based Incremental Few-Shot Semantic Segmentation Fabio Cermelli, Massimiliano Mancini, Yongqin Xian, Zeynep Akata, Barbara Caputo -- BMVC 20

Fabio Cermelli 21 Dec 29, 2022
UniFormer - official implementation of UniFormer

UniFormer This repo is the official implementation of "Uniformer: Unified Transformer for Efficient Spatiotemporal Representation Learning". It curren

SenseTime X-Lab 573 Jan 04, 2023
TensorFlow implementation of original paper : https://github.com/hszhao/PSPNet

Keras implementation of PSPNet(caffe) Implemented Architecture of Pyramid Scene Parsing Network in Keras. For the best compability please use Python3.

VladKry 386 Dec 29, 2022
Code for You Only Cut Once: Boosting Data Augmentation with a Single Cut

You Only Cut Once (YOCO) YOCO is a simple method/strategy of performing augmenta

88 Dec 28, 2022
Unicorn can be used for performance analyses of highly configurable systems with causal reasoning

Unicorn can be used for performance analyses of highly configurable systems with causal reasoning. Users or developers can query Unicorn for a performance task.

AISys Lab 27 Jan 05, 2023
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features

Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features | paper | Official PyTorch implementation for Mul

48 Dec 28, 2022
Only a Matter of Style: Age Transformation Using a Style-Based Regression Model

Only a Matter of Style: Age Transformation Using a Style-Based Regression Model The task of age transformation illustrates the change of an individual

444 Dec 30, 2022
Repository for the electrical and ICT benchmark model developed in the ERIGrid 2.0 project.

Benchmark Model Electrical and ICT System This repository contains the documentation, code, and models for the electrical and ICT benchmark model deve

ERIGrid 2.0 1 Nov 29, 2021
Genetic feature selection module for scikit-learn

sklearn-genetic Genetic feature selection module for scikit-learn Genetic algorithms mimic the process of natural selection to search for optimal valu

Manuel Calzolari 260 Dec 14, 2022
Research into Forex price prediction from price history using Deep Sequence Modeling with Stacked LSTMs.

Forex Data Prediction via Recurrent Neural Network Deep Sequence Modeling Research Paper Our research paper can be viewed here Installation Clone the

Alex Taradachuk 2 Aug 07, 2022
The materials used in the SaxonJS tutorial presented at Declarative Amsterdam, 2021

SaxonJS-Tutorial-2021, version 1.0.4 Last updated on 4 November, 2021. Table of contents Background Prerequisites Starting a web server Running a Java

Saxonica 11 Oct 23, 2022