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
[TOG 2021] PyTorch implementation for the paper: SofGAN: A Portrait Image Generator with Dynamic Styling.

This repository contains the official PyTorch implementation for the paper: SofGAN: A Portrait Image Generator with Dynamic Styling. We propose a SofGAN image generator to decouple the latent space o

Anpei Chen 694 Dec 23, 2022
Grounding Representation Similarity with Statistical Testing

Grounding Representation Similarity with Statistical Testing This repo contains code to replicate the results in our paper, which evaluates representa

26 Dec 02, 2022
TorchCV: A PyTorch-Based Framework for Deep Learning in Computer Vision

TorchCV: A PyTorch-Based Framework for Deep Learning in Computer Vision @misc{you2019torchcv, author = {Ansheng You and Xiangtai Li and Zhen Zhu a

Donny You 2.2k Jan 06, 2023
Self-Supervised Image Denoising via Iterative Data Refinement

Self-Supervised Image Denoising via Iterative Data Refinement Yi Zhang1, Dasong Li1, Ka Lung Law2, Xiaogang Wang1, Hongwei Qin2, Hongsheng Li1 1CUHK-S

Zhang Yi 72 Jan 01, 2023
Clustering is a popular approach to detect patterns in unlabeled data

Visual Clustering Clustering is a popular approach to detect patterns in unlabeled data. Existing clustering methods typically treat samples in a data

Tarek Naous 24 Nov 11, 2022
Python Auto-ML Package for Tabular Datasets

Tabular-AutoML AutoML Package for tabular datasets Tabular dataset tuning is now hassle free! Run one liner command and get best tuning and processed

Sagnik Roy 18 Nov 20, 2022
A Dataset for Direct Quotation Extraction and Attribution in News Articles.

DirectQuote - A Dataset for Direct Quotation Extraction and Attribution in News Articles DirectQuote is a corpus containing 19,760 paragraphs and 10,3

THUNLP-MT 9 Sep 23, 2022
Image Captioning using CNN ,LSTM and Attention

Image Captioning using CNN ,LSTM and Attention This is a deeplearning model which tries to summarize an image into a text . Installation Install this

ASUTOSH GHANTO 1 Dec 16, 2021
Repo for the Tutorials of Day1-Day3 of the Nordic Probabilistic AI School 2021 (https://probabilistic.ai/)

ProbAI 2021 - Probabilistic Programming and Variational Inference Tutorial with Pryo Day 1 (June 14) Slides Notebook: students_PPLs_Intro Notebook: so

PGM-Lab 46 Nov 01, 2022
Pervasive Attention: 2D Convolutional Networks for Sequence-to-Sequence Prediction

This is a fork of Fairseq(-py) with implementations of the following models: Pervasive Attention - 2D Convolutional Neural Networks for Sequence-to-Se

Maha 490 Dec 15, 2022
Security evaluation module with onnx, pytorch, and SecML.

🚀 🐼 🔥 PandaVision Integrate and automate security evaluations with onnx, pytorch, and SecML! Installation Starting the server without Docker If you

Maura Pintor 11 Apr 12, 2022
An implementation of DeepMind's Relational Recurrent Neural Networks in PyTorch.

relational-rnn-pytorch An implementation of DeepMind's Relational Recurrent Neural Networks (Santoro et al. 2018) in PyTorch. Relational Memory Core (

Sang-gil Lee 241 Nov 18, 2022
Official pytorch code for SSC-GAN: Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation(ICCV 2021)

SSC-GAN_repo Pytorch implementation for 'Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation'.PDF SSC-GAN:Sem

tyty 4 Aug 28, 2022
PyTorch implementation of DreamerV2 model-based RL algorithm

PyDreamer Reimplementation of DreamerV2 model-based RL algorithm in PyTorch. The official DreamerV2 implementation can be found here. Features ... Run

118 Dec 15, 2022
Semantic Segmentation in Pytorch

PyTorch Semantic Segmentation Introduction This repository is a PyTorch implementation for semantic segmentation / scene parsing. The code is easy to

Hengshuang Zhao 1.2k Jan 01, 2023
Brain tumor detection using CNN (InceptionResNetV2 Model)

Brain-Tumor-Detection Building a detection model using a convolutional neural network in Tensorflow & Keras. Used brain MRI images. InceptionResNetV2

1 Feb 13, 2022
Code for SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations

The Second Situated Interactive MultiModal Conversations (SIMMC 2.0) Challenge 2021 Welcome to the Second Situated Interactive Multimodal Conversation

Facebook Research 81 Nov 22, 2022
This is the dataset and code release of the OpenRooms Dataset.

This is the dataset and code release of the OpenRooms Dataset.

Visual Intelligence Lab of UCSD 95 Jan 08, 2023
A new benchmark for Icon Question Answering (IconQA) and a large-scale icon dataset Icon645.

IconQA About IconQA is a new diverse abstract visual question answering dataset that highlights the importance of abstract diagram understanding and c

Pan Lu 24 Dec 30, 2022
PyTorch implementation for COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction (CVPR 2021)

Completer: Incomplete Multi-view Clustering via Contrastive Prediction This repo contains the code and data of the following paper accepted by CVPR 20

XLearning Group 72 Dec 07, 2022