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
Facebook AI Image Similarity Challenge: Descriptor Track

Facebook AI Image Similarity Challenge: Descriptor Track This repository contains the code for our solution to the Facebook AI Image Similarity Challe

Sergio MP 17 Dec 14, 2022
PushForKiCad - AISLER Push for KiCad EDA

AISLER Push for KiCad Push your layout to AISLER with just one click for instant

AISLER 31 Dec 29, 2022
PyTorch implementation of 1712.06087 "Zero-Shot" Super-Resolution using Deep Internal Learning

Unofficial PyTorch implementation of "Zero-Shot" Super-Resolution using Deep Internal Learning Unofficial Implementation of 1712.06087 "Zero-Shot" Sup

Jacob Gildenblat 196 Nov 27, 2022
Code release for NeX: Real-time View Synthesis with Neural Basis Expansion

NeX: Real-time View Synthesis with Neural Basis Expansion Project Page | Video | Paper | COLAB | Shiny Dataset We present NeX, a new approach to novel

538 Jan 09, 2023
Rule Based Classification Project For Python

Rule-Based-Classification-Project (ENG) Business Problem: A game company wants to create new level-based customer definitions (personas) by using some

Deniz Can OĞUZ 4 Oct 29, 2022
Off-policy continuous control in PyTorch, with RDPG, RTD3 & RSAC

arXiv technical report soon available. we are updating the readme to be as comprehensive as possible Please ask any questions in Issues, thanks. Intro

Zhihan 31 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
A series of Python scripts to access measurements from Fluke 28X meters. Fluke IR Remote Interface required.

Fluke289_data_access A series of Python scripts to access measurements from Fluke 28X meters. Fluke IR Remote Interface required. Created from informa

3 Dec 08, 2022
Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks

Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks arXiv preprint: https://arxiv.org/abs/2201.02143. Architec

19 Nov 30, 2022
A lightweight python AUTOmatic-arRAY library.

A lightweight python AUTOmatic-arRAY library. Write numeric code that works for: numpy cupy dask autograd jax mars tensorflow pytorch ... and indeed a

Johnnie Gray 62 Dec 27, 2022
Convolutional neural network that analyzes self-generated images in a variety of languages to find etymological similarities

This project is a convolutional neural network (CNN) that analyzes self-generated images in a variety of languages to find etymological similarities. Specifically, the goal is to prove that computer

1 Feb 03, 2022
Scalable and Elastic Deep Reinforcement Learning Using PyTorch. Please star. 🔥

ElegantRL “小雅”: Scalable and Elastic Deep Reinforcement Learning ElegantRL is developed for researchers and practitioners with the following advantage

AI4Finance Foundation 2.5k Jan 05, 2023
Implementation of QuickDraw - an online game developed by Google, combined with AirGesture - a simple gesture recognition application

QuickDraw - AirGesture Introduction Here is my python source code for QuickDraw - an online game developed by google, combined with AirGesture - a sim

Viet Nguyen 89 Dec 18, 2022
code for Image Manipulation Detection by Multi-View Multi-Scale Supervision

MVSS-Net Code and models for ICCV 2021 paper: Image Manipulation Detection by Multi-View Multi-Scale Supervision Update 22.02.17, Pretrained model for

dong_chengbo 131 Dec 30, 2022
WeakVRD-Captioning - Implementation of paper Improving Image Captioning with Better Use of Caption

WeakVRD-Captioning - Implementation of paper Improving Image Captioning with Better Use of Caption

30 Oct 28, 2022
Official PyTorch implementation of "Synthesis of Screentone Patterns of Manga Characters"

Manga Character Screentone Synthesis Official PyTorch implementation of "Synthesis of Screentone Patterns of Manga Characters" presented in IEEE ISM 2

Tsubota 2 Nov 20, 2021
Supercharging Imbalanced Data Learning WithCausal Representation Transfer

ECRT: Energy-based Causal Representation Transfer Code for Supercharging Imbalanced Data Learning With Energy-basedContrastive Representation Transfer

Zidi Xiu 11 May 02, 2022
CodeContests is a competitive programming dataset for machine-learning

CodeContests CodeContests is a competitive programming dataset for machine-learning. This dataset was used when training AlphaCode. It consists of pro

DeepMind 1.6k Jan 08, 2023
A neuroanatomy-based augmented reality experience powered by computer vision. Features 3D visuals of the Atlas Brain Map slices.

Brain Augmented Reality (AR) A neuroanatomy-based augmented reality experience powered by computer vision that features 3D visuals of the Atlas Brain

Yasmeen Brain 10 Oct 06, 2022
Semi-Supervised Learning for Fine-Grained Classification

Semi-Supervised Learning for Fine-Grained Classification This repo contains the code of: A Realistic Evaluation of Semi-Supervised Learning for Fine-G

25 Nov 08, 2022