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
Use MATLAB to simulate the signal and extract features. Use PyTorch to build and train deep network to do spectrum sensing.

Deep-Learning-based-Spectrum-Sensing Use MATLAB to simulate the signal and extract features. Use PyTorch to build and train deep network to do spectru

10 Dec 14, 2022
Dirty Pixels: Towards End-to-End Image Processing and Perception

Dirty Pixels: Towards End-to-End Image Processing and Perception This repository contains the code for the paper Dirty Pixels: Towards End-to-End Imag

50 Nov 18, 2022
Speed-Test - You can check your intenet speed using this tool

Speed-Test Tool By Hez_X AVAILABLE ON : Termux & Kali linux & Ubuntu (Linux E

Hez-X 3 Feb 17, 2022
Chainer implementation of recent GAN variants

Chainer-GAN-lib This repository collects chainer implementation of state-of-the-art GAN algorithms. These codes are evaluated with the inception score

399 Oct 23, 2022
Prediction of MBA refinance Index (Mortgage prepayment)

Prediction of MBA refinance Index (Mortgage prepayment) Deep Neural Network based Model The ability to predict mortgage prepayment is of critical use

Ruchil Barya 1 Jan 16, 2022
Fast and simple implementation of RL algorithms, designed to run fully on GPU.

RSL RL Fast and simple implementation of RL algorithms, designed to run fully on GPU. This code is an evolution of rl-pytorch provided with NVIDIA's I

Robotic Systems Lab - Legged Robotics at ETH Zürich 68 Dec 29, 2022
Quickly and easily create / train a custom DeepDream model

Dream-Creator This project aims to simplify the process of creating a custom DeepDream model by using pretrained GoogleNet models and custom image dat

55 Dec 27, 2022
A project studying the influence of communication in multi-objective normal-form games

Communication in Multi-Objective Normal-Form Games This repo consists of five different types of agents that we have used in our study of communicatio

Willem Röpke 0 Dec 17, 2021
AutoDeeplab / auto-deeplab / AutoML for semantic segmentation, implemented in Pytorch

AutoML for Image Semantic Segmentation Currently this repo contains the only working open-source implementation of Auto-Deeplab which, by the way out-

AI Necromancer 299 Dec 17, 2022
The comma.ai Calibration Challenge!

Welcome to the comma.ai Calibration Challenge! Your goal is to predict the direction of travel (in camera frame) from provided dashcam video. This rep

comma.ai 697 Jan 05, 2023
Official repository for the ICCV 2021 paper: UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model.

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model Official repository for the ICCV 2021 paper: UltraPose: Syn

MomoAILab 92 Dec 21, 2022
Official Implementation of DDOD (Disentangle your Dense Object Detector), ACM MM2021

Disentangle Your Dense Object Detector This repo contains the supported code and configuration files to reproduce object detection results of Disentan

loveSnowBest 51 Jan 07, 2023
Official code for "Stereo Waterdrop Removal with Row-wise Dilated Attention (IROS2021)"

Stereo-Waterdrop-Removal-with-Row-wise-Dilated-Attention This repository includes official codes for "Stereo Waterdrop Removal with Row-wise Dilated A

29 Oct 01, 2022
This repository contains an implementation of ConvMixer for the ICLR 2022 submission "Patches Are All You Need?".

Patches Are All You Need? 🤷 This repository contains an implementation of ConvMixer for the ICLR 2022 submission "Patches Are All You Need?". Code ov

ICLR 2022 Author 934 Dec 30, 2022
This is the official implementation for the paper "Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization" in NeurIPS 2021.

MPMAB_BEACON This is code used for the paper "Decentralized Multi-player Multi-armed Bandits: Beyond Linear Reward Functions", Neurips 2021. Requireme

Cong Shen Research Group 0 Oct 26, 2021
Exploring the Dual-task Correlation for Pose Guided Person Image Generation

Dual-task Pose Transformer Network The source code for our paper "Exploring Dual-task Correlation for Pose Guided Person Image Generation“ (CVPR2022)

63 Dec 15, 2022
Event queue (Equeue) dialect is an MLIR Dialect that models concurrent devices in terms of control and structure.

Event Queue Dialect Event queue (Equeue) dialect is an MLIR Dialect that models concurrent devices in terms of control and structure. Motivation The m

Cornell Capra 23 Dec 08, 2022
A Deep Reinforcement Learning Framework for Stock Market Trading

DQN-Trading This is a framework based on deep reinforcement learning for stock market trading. This project is the implementation code for the two pap

61 Jan 01, 2023
TorchGRL is the source code for our paper Graph Convolution-Based Deep Reinforcement Learning for Multi-Agent Decision-Making in Mixed Traffic Environments for IV 2022.

TorchGRL TorchGRL is the source code for our paper Graph Convolution-Based Deep Reinforcement Learning for Multi-Agent Decision-Making in Mixed Traffi

XXQQ 42 Dec 09, 2022
Select, weight and analyze complex sample data

Sample Analytics In large-scale surveys, often complex random mechanisms are used to select samples. Estimates derived from such samples must reflect

samplics 37 Dec 15, 2022