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
Open-World Entity Segmentation

Open-World Entity Segmentation Project Website Lu Qi*, Jason Kuen*, Yi Wang, Jiuxiang Gu, Hengshuang Zhao, Zhe Lin, Philip Torr, Jiaya Jia This projec

DV Lab 410 Jan 03, 2023
[ICCV 2021 Oral] NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo

NerfingMVS Project Page | Paper | Video | Data NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo Yi Wei, Shaohui

Yi Wei 369 Dec 24, 2022
Physics-informed Neural Operator for Learning Partial Differential Equation

PINO Physics-informed Neural Operator for Learning Partial Differential Equation Abstract: Machine learning methods have recently shown promise in sol

107 Jan 02, 2023
A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis

A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis This is the pytorch implementation for our MICCAI 2021 paper. A Mul

Jiarong Ye 7 Apr 04, 2022
CSKG is a commonsense knowledge graph that combines seven popular sources into a consolidated representation

CSKG: The CommonSense Knowledge Graph CSKG is a commonsense knowledge graph that combines seven popular sources into a consolidated representation: AT

USC ISI I2 85 Dec 12, 2022
CLIPImageClassifier wraps clip image model from transformers

CLIPImageClassifier CLIPImageClassifier wraps clip image model from transformers. CLIPImageClassifier is initialized with the argument classes, these

Jina AI 6 Sep 12, 2022
From a body shape, infer the anatomic skeleton.

OSSO: Obtaining Skeletal Shape from Outside (CVPR 2022) This repository contains the official implementation of the skeleton inference from: OSSO: Obt

Marilyn Keller 166 Dec 28, 2022
Code for the paper "Next Generation Reservoir Computing"

Next Generation Reservoir Computing This is the code for the results and figures in our paper "Next Generation Reservoir Computing". They are written

OSU QuantInfo Lab 105 Dec 20, 2022
Predicting Tweet Sentiment Maching Learning and streamlit

Predicting-Tweet-Sentiment-Maching-Learning-and-streamlit (I prefere using Visual Studio Code ) Open the folder in VS Code Run the first cell in requi

1 Nov 20, 2021
ColossalAI-Benchmark - Performance benchmarking with ColossalAI

Benchmark for Tuning Accuracy and Efficiency Overview The benchmark includes our

HPC-AI Tech 31 Oct 07, 2022
PyTorch Implementation of SSTNs for hyperspectral image classifications from the IEEE T-GRS paper "Spectral-Spatial Transformer Network for Hyperspectral Image Classification: A FAS Framework."

PyTorch Implementation of SSTN for Hyperspectral Image Classification Paper links: SSTN published on IEEE T-GRS. Also, you can directly find the imple

Zilong Zhong 54 Dec 19, 2022
Playing around with FastAPI and streamlit to create a YoloV5 object detector

FastAPI-Streamlit-based-YoloV5-detector Playing around with FastAPI and streamlit to create a YoloV5 object detector It turns out that a User Interfac

2 Jan 20, 2022
CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensors

CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensors   In order to facilitate the res

yujmo 11 Dec 12, 2022
Unofficial PyTorch implementation of MobileViT.

MobileViT Overview This is a PyTorch implementation of MobileViT specified in "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Tr

Chin-Hsuan Wu 348 Dec 23, 2022
Official PyTorch Implementation of GAN-Supervised Dense Visual Alignment

GAN-Supervised Dense Visual Alignment — Official PyTorch Implementation Paper | Project Page | Video This repo contains training, evaluation and visua

944 Jan 07, 2023
A collection of SOTA Image Classification Models in PyTorch

A collection of SOTA Image Classification Models in PyTorch

sithu3 85 Dec 30, 2022
Educational 2D SLAM implementation based on ICP and Pose Graph

slam-playground Educational 2D SLAM implementation based on ICP and Pose Graph How to use: Use keyboard arrow keys to navigate robot. Press 'r' to vie

Kirill 19 Dec 17, 2022
This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".

A Memory-saving Training Framework for Transformers This is the official PyTorch implementation for Mesa: A Memory-saving Training Framework for Trans

Zhuang AI Group 105 Dec 06, 2022
Fast image augmentation library and an easy-to-use wrapper around other libraries

Albumentations Albumentations is a Python library for image augmentation. Image augmentation is used in deep learning and computer vision tasks to inc

11.4k Jan 09, 2023
A deep learning tabular classification architecture inspired by TabTransformer with integrated gated multilayer perceptron.

The GatedTabTransformer. A deep learning tabular classification architecture inspired by TabTransformer with integrated gated multilayer perceptron. C

Radi Cho 60 Dec 15, 2022