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
Official and maintained implementation of the paper "OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data" [BMVC 2021].

OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data Christoph Reich, Tim Prangemeier, Özdemir Cetin & Heinz Koeppl | Pr

Christoph Reich 23 Sep 21, 2022
We envision models that are pre-trained on a vast range of domain-relevant tasks to become key for molecule property prediction

We envision models that are pre-trained on a vast range of domain-relevant tasks to become key for molecule property prediction. This repository aims to give easy access to state-of-the-art pre-train

GMUM 90 Jan 08, 2023
ShuttleNet: Position-aware Fusion of Rally Progress and Player Styles for Stroke Forecasting in Badminton (AAAI 2022)

ShuttleNet: Position-aware Rally Progress and Player Styles Fusion for Stroke Forecasting in Badminton (AAAI 2022) Official code of the paper ShuttleN

Wei-Yao Wang 11 Nov 30, 2022
This repository implements Douzero's interface to IGCA.

douzero-interface-for-ICGA This repository implements Douzero's interface to ICGA. ./douzero: This directory stores Doudizhu AI projects. ./interface:

zhanggenjin 4 Aug 07, 2022
Codes for [NeurIPS'21] You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership.

You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership Codes for [NeurIPS'21] You are caught stealing my winni

VITA 8 Nov 01, 2022
git git《Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking》(CVPR 2021) GitHub:git2] 《Masksembles for Uncertainty Estimation》(CVPR 2021) GitHub:git3]

Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking Ning Wang, Wengang Zhou, Jie Wang, and Houqiang Li Accepted by CVPR

NingWang 236 Dec 22, 2022
(to be released) [NeurIPS'21] Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs

Higher-Order Transformers Kim J, Oh S, Hong S, Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs, NeurIPS 2021. [arxiv] W

Jinwoo Kim 44 Dec 28, 2022
A simple code to convert image format and channel as well as resizing and renaming multiple images.

Rename-Resize-and-convert-multiple-images A simple code to convert image format and channel as well as resizing and renaming multiple images. This cod

Happy N. Monday 3 Feb 15, 2022
The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral)

EMANet News The bug in loading the pretrained model is now fixed. I have updated the .pth. To use it, download it again. EMANet-101 gets 80.99 on the

Xia Li 李夏 663 Nov 30, 2022
MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images This repository contains the implementation of our paper MetaAvatar: Learni

sfwang 96 Dec 13, 2022
TAP: Text-Aware Pre-training for Text-VQA and Text-Caption, CVPR 2021 (Oral)

TAP: Text-Aware Pre-training TAP: Text-Aware Pre-training for Text-VQA and Text-Caption by Zhengyuan Yang, Yijuan Lu, Jianfeng Wang, Xi Yin, Dinei Flo

Microsoft 61 Nov 14, 2022
This is the official pytorch implementation for the paper: Instance Similarity Learning for Unsupervised Feature Representation.

ISL This is the official pytorch implementation for the paper: Instance Similarity Learning for Unsupervised Feature Representation, which is accepted

19 May 04, 2022
[CoRL 2021] A robotics benchmark for cross-embodiment imitation.

x-magical x-magical is a benchmark extension of MAGICAL specifically geared towards cross-embodiment imitation. The tasks still provide the Demo/Test

Kevin Zakka 36 Nov 26, 2022
Neural network for stock price prediction

neural_network_for_stock_price_prediction Neural networks for stock price predic

2 Feb 04, 2022
Implementation of the algorithm shown in the article "Modelo de Predicción de Éxito de Canciones Basado en Descriptores de Audio"

Success Predictor Implementation of the algorithm shown in the article "Modelo de Predicción de Éxito de Canciones Basado en Descriptores de Audio". B

Rodrigo Nazar Meier 4 Mar 17, 2022
Efficient-GlobalPointer - Pytorch Efficient GlobalPointer

引言 感谢苏神带来的模型，原文地址：https://spaces.ac.cn/archives/8877 如何运行 对应模型EfficientGlobalPoi

powerycy 40 Dec 14, 2022
Code for Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation (CVPR 2021)

Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation (CVPR 2021) Hang Zhou, Yasheng Sun, Wayne Wu, Chen Cha

Hang_Zhou 628 Dec 28, 2022
Official code for On Path Integration of Grid Cells: Group Representation and Isotropic Scaling (NeurIPS 2021)

On Path Integration of Grid Cells: Group Representation and Isotropic Scaling This repo contains the official implementation for the paper On Path Int

Ruiqi Gao 39 Nov 10, 2022
🌾 PASTIS 🌾 Panoptic Agricultural Satellite TIme Series

🌾 PASTIS 🌾 Panoptic Agricultural Satellite TIme Series (optical and radar) The PASTIS Dataset Dataset presentation PASTIS is a benchmark dataset for

86 Jan 04, 2023
TensorFlow implementation of "Variational Inference with Normalizing Flows"

[TensorFlow 2] Variational Inference with Normalizing Flows TensorFlow implementation of "Variational Inference with Normalizing Flows" [1] Concept Co

YeongHyeon Park 7 Jun 08, 2022