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
KITTI-360 Annotation Tool is a framework that developed based on python(cherrypy + jinja2 + sqlite3) as the server end and javascript + WebGL as the front end.

KITTI-360 Annotation Tool is a framework that developed based on python(cherrypy + jinja2 + sqlite3) as the server end and javascript + WebGL as the front end.

86 Dec 12, 2022
The deployment framework aims to provide a simple, lightweight, fast integrated, pipelined deployment framework that ensures reliability, high concurrency and scalability of services.

savior是一个能够进行快速集成算法模块并支持高性能部署的轻量开发框架。能够帮助将团队进行快速想法验证（PoC），避免重复的去github上找模型然后复现模型；能够帮助团队将功能进行流程拆解，很方便的提高分布式执行效率；能够有效减少代码冗余，减少不必要负担。

Tao Luo 125 Dec 22, 2022
TensorFlow, PyTorch and Numpy layers for generating Orthogonal Polynomials

OrthNet TensorFlow, PyTorch and Numpy layers for generating multi-dimensional Orthogonal Polynomials 1. Installation 2. Usage 3. Polynomials 4. Base C

Chuan 29 May 25, 2022
Kinetics-Data-Preprocessing

Kinetics-Data-Preprocessing Kinetics-400 and Kinetics-600 are common video recognition datasets used by popular video understanding projects like Slow

Kaihua Tang 7 Oct 27, 2022
This repository is for the preprint "A generative nonparametric Bayesian model for whole genomes"

BEAR Overview This repository contains code associated with the preprint A generative nonparametric Bayesian model for whole genomes (2021), which pro

Debora Marks Lab 10 Sep 18, 2022
Repositório criado para abrigar os notebooks com a listas de exercícios propostos pelo professor Gustavo Guanabara do canal Curso em Vídeo do YouTube durante o Curso de Python 3

Curso em Vídeo - Exercícios de Python 3 Sobre o repositório Este repositório contém os notebooks com a listas de exercícios propostos pelo professor G

João Pedro Pereira 9 Oct 15, 2022
A library for augmentation of a YOLO-formated dataset

YOLO Dataset Augmentation lib Инструкция по использованию этой библиотеки Запуск всех файлов осуществлять из консоли. GoogleCrawl_to_Dataset.py Это ск

Egor Orel 1 Dec 10, 2022
A Python Library for Graph Outlier Detection (Anomaly Detection)

PyGOD is a Python library for graph outlier detection (anomaly detection). This exciting yet challenging field has many key applications, e.g., detect

PyGOD Team 757 Jan 04, 2023
DeepRec is a recommendation engine based on TensorFlow.

DeepRec Introduction DeepRec is a recommendation engine based on TensorFlow 1.15, Intel-TensorFlow and NVIDIA-TensorFlow. Background Sparse model is a

Alibaba 676 Jan 03, 2023
Deep Residual Learning for Image Recognition

Deep Residual Learning for Image Recognition This is a Torch implementation of "Deep Residual Learning for Image Recognition",Kaiming He, Xiangyu Zhan

Kimmy 561 Dec 01, 2022
Cancer Drug Response Prediction via a Hybrid Graph Convolutional Network

DeepCDR Cancer Drug Response Prediction via a Hybrid Graph Convolutional Network This work has been accepted to ECCB2020 and was also published in the

Qiao Liu 50 Dec 18, 2022
Implementation of CVPR 2020 Dual Super-Resolution Learning for Semantic Segmentation

Dual super-resolution learning for semantic segmentation 2021-01-02 Subpixel Update Happy new year! The 2020-12-29 update of SISR with subpixel conv p

Sam 79 Nov 24, 2022
Blender Add-On for slicing meshes with planes

MeshSlicer Blender Add-On for slicing meshes with multiple overlapping planes at once. This is a simple Blender addon to slice a silmple mesh with mul

52 Dec 12, 2022
Dense matching library based on PyTorch

Dense Matching A general dense matching library based on PyTorch. For any questions, issues or recommendations, please contact Prune at

Prune Truong 399 Dec 28, 2022
Official Repository for "Robust On-Policy Data Collection for Data Efficient Policy Evaluation" (NeurIPS 2021 Workshop on OfflineRL).

Robust On-Policy Data Collection for Data-Efficient Policy Evaluation Source code of Robust On-Policy Data Collection for Data-Efficient Policy Evalua

Autonomous Agents Research Group (University of Edinburgh) 2 Oct 09, 2022
An Implementation of SiameseRPN with Feature Pyramid Networks

SiameseRPN with FPN This project is mainly based on HelloRicky123/Siamese-RPN. What I've done is just add a Feature Pyramid Network method to the orig

3 Apr 16, 2022
ToFFi - Toolbox for Frequency-based Fingerprinting of Brain Signals

ToFFi Toolbox This repository contains "before peer review" version of the software related to the preprint of the publication ToFFi - Toolbox for Fre

4 Aug 31, 2022
Code-free deep segmentation for computational pathology

NoCodeSeg: Deep segmentation made easy! This is the official repository for the manuscript "Code-free development and deployment of deep segmentation

André Pedersen 26 Nov 23, 2022
Source-to-Source Debuggable Derivatives in Pure Python

Tangent Tangent is a new, free, and open-source Python library for automatic differentiation. Existing libraries implement automatic differentiation b

Google 2.2k Jan 01, 2023
NaijaSenti is an open-source sentiment and emotion corpora for four major Nigerian languages

NaijaSenti is an open-source sentiment and emotion corpora for four major Nigerian languages. This project was supported by lacuna-fund initiatives. Jump straight to one of the sections below, or jus

Hausa Natural Language Processing 14 Dec 20, 2022