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
Context Axial Reverse Attention Network for Small Medical Objects Segmentation

CaraNet: Context Axial Reverse Attention Network for Small Medical Objects Segmentation This repository contains the implementation of a novel attenti

401 Dec 23, 2022
Densely Connected Search Space for More Flexible Neural Architecture Search (CVPR2020)

DenseNAS The code of the CVPR2020 paper Densely Connected Search Space for More Flexible Neural Architecture Search. Neural architecture search (NAS)

Jamin Fong 291 Nov 18, 2022
FedML: A Research Library and Benchmark for Federated Machine Learning

FedML: A Research Library and Benchmark for Federated Machine Learning 📄 https://arxiv.org/abs/2007.13518 News 2021-02-01 (Award): #NeurIPS 2020# Fed

FedML-AI 2.3k Jan 08, 2023
Repository containing detailed experiments related to the paper "Memotion Analysis through the Lens of Joint Embedding".

Memotion Analysis Through The Lens Of Joint Embedding This repository contains the experiments conducted as described in the paper 'Memotion Analysis

Nethra Gunti 1 Mar 16, 2022
Official implementation of the paper WAV2CLIP: LEARNING ROBUST AUDIO REPRESENTATIONS FROM CLIP

Wav2CLIP 🚧 WIP 🚧 Official implementation of the paper WAV2CLIP: LEARNING ROBUST AUDIO REPRESENTATIONS FROM CLIP 📄 🔗 Ho-Hsiang Wu, Prem Seetharaman

Descript 240 Dec 13, 2022
A large-scale video dataset for the training and evaluation of 3D human pose estimation models

ASPset-510 (Australian Sports Pose Dataset) is a large-scale video dataset for the training and evaluation of 3D human pose estimation models. It contains 17 different amateur subjects performing 30

Aiden Nibali 25 Jun 20, 2021
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
BED: A Real-Time Object Detection System for Edge Devices

BED: A Real-Time Object Detection System for Edge Devices About this project Thi

Data Analytics Lab at Texas A&M University 44 Nov 18, 2022
A modular, research-friendly framework for high-performance and inference of sequence models at many scales

T5X T5X is a modular, composable, research-friendly framework for high-performance, configurable, self-service training, evaluation, and inference of

Google Research 1.1k Jan 08, 2023
Code for Two-stage Identifier: "Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition"

Code for Two-stage Identifier: "Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition", accepted at ACL 2021. For details of the model and experiments, please see our paper.

tricktreat 87 Dec 16, 2022
[AAAI 2022] Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification

Sparse Structure Learning via Graph Neural Networks for inductive document classification Make graph dataset create co-occurrence graph for datasets.

16 Dec 22, 2022
The repository is for safe reinforcement learning baselines.

Safe-Reinforcement-Learning-Baseline The repository is for Safe Reinforcement Learning (RL) research, in which we investigate various safe RL baseline

172 Dec 19, 2022
An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.

CPC_audio This code implements the Contrast Predictive Coding algorithm on audio data, as described in the paper Unsupervised Pretraining Transfers we

Meta Research 283 Dec 30, 2022
STRIVE: Scene Text Replacement In Videos

STRIVE: Scene Text Replacement In Videos Dataset Types: RoboText SynthText RealWorld videos RoboText : Videos of texts collected using navigation robo

15 Jul 11, 2022
Pytorch Implementation of "Desigining Network Design Spaces", Radosavovic et al. CVPR 2020.

RegNet Pytorch Implementation of "Desigining Network Design Spaces", Radosavovic et al. CVPR 2020. Paper | Official Implementation RegNet offer a very

Vishal R 2 Feb 11, 2022
Classic Papers for Beginners and Impact Scope for Authors.

There have been billions of academic papers around the world. However, maybe only 0.0...01% among them are valuable or are worth reading. Since our limited life has never been forever, TopPaper provi

Qiulin Zhang 228 Dec 18, 2022
A curated list of awesome Active Learning

Awesome Active Learning 🤩 A curated list of awesome Active Learning ! 🤩 Background (image source: Settles, Burr) What is Active Learning? Active lea

BAI Fan 431 Jan 03, 2023
Generating Videos with Scene Dynamics

Generating Videos with Scene Dynamics This repository contains an implementation of Generating Videos with Scene Dynamics by Carl Vondrick, Hamed Pirs

Carl Vondrick 706 Jan 04, 2023
Neuralnetwork - Basic Multilayer Perceptron Neural Network for deep learning

Neural Network Just a basic Neural Network module Usage Example Importing Module

andreecy 0 Nov 01, 2022
Code to generate datasets used in "How Useful is Self-Supervised Pretraining for Visual Tasks?"

Synthetic dataset rendering Framework for producing the synthetic datasets used in: How Useful is Self-Supervised Pretraining for Visual Tasks? Alejan

Princeton Vision & Learning Lab 21 Apr 29, 2022