Applying "Load What You Need: Smaller Versions of Multilingual BERT" to LaBSE

Related tags

Text Data & NLPbertpaper-implementationssentence-embeddings
Overview

smaller-LaBSE

LaBSE(Language-agnostic BERT Sentence Embedding) is a very good method to get sentence embeddings across languages. But it is hard to fine-tune due to the parameter size(~=471M) of this model. For instance, if I fine-tune this model with Adam optimizer, I need the GPU that has VRAM at least 7.5GB = 471M * (parameters 4 bytes + gradients 4 bytes + momentums 4 bytes + variances 4 bytes). So I applied "Load What You Need: Smaller Multilingual Transformers" method to LaBSE to reduce parameter size since most of this model's parameter is the word embedding table(~=385M).

The smaller version of LaBSE is evaluated for 14 languages using tatoeba dataset. It shows we can reduce LaBSE's parameters to 47% without a big performance drop.

If you need the PyTorch version, see https://github.com/Geotrend-research/smaller-transformers. I followed most of the steps in the paper.

Model #param(transformer) #param(word embedding) #param(model) vocab size
tfhub_LaBSE 85.1M 384.9M 470.9M 501,153
15lang_LaBSE 85.1M 133.1M 219.2M 173,347

Used Languages

  • English (en or eng)
  • French (fr or fra)
  • Spanish (es or spa)
  • German (de or deu)
  • Chinese (zh, zh_classical or cmn)
  • Arabic (ar or ara)
  • Italian (it or ita)
  • Japanese (ja or jpn)
  • Korean (ko or kor)
  • Dutch (nl or nld)
  • Polish (pl or pol)
  • Portuguese (pt or por)
  • Thai (th or tha)
  • Turkish (tr or tur)
  • Russian (ru or rus)

I selected the languages multilingual-USE supports.

Scripts

A smaller version of the vocab was constructed based on the frequency of tokens using Wikipedia dump data. I followed most of the algorithms in the paper to extract proper vocab for each language and rewrite it for TensorFlow.

Convert weight

mkdir -p downloads/labse-2
curl -L https://tfhub.dev/google/LaBSE/2?tf-hub-format=compressed -o downloads/labse-2.tar.gz
tar -xf downloads/labse-2.tar.gz -C downloads/labse-2/
python save_as_weight_from_saved_model.py

Select vocabs

./download_dataset.sh
python select_vocab.py

Make smaller LaBSE

./make_smaller_labse.py

Evaluate tatoeba

./download_tatoeba_dataset.sh
# evaluate TFHub LaBSE
./evaluate_tatoeba.sh
# evaluate the smaller LaBSE
./evaluate_tatoeba.sh \
    --model models/LaBSE_en-fr-es-de-zh-ar-zh_classical-it-ja-ko-nl-pl-pt-th-tr-ru/1/ \
    --preprocess models/LaBSE_en-fr-es-de-zh-ar-zh_classical-it-ja-ko-nl-pl-pt-th-tr-ru_preprocess/1/

Results

Tatoeba

Model fr es de zh ar it ja ko nl pl pt th tr ru avg
tfHub_LaBSE(en→xx) 95.90 98.10 99.30 96.10 90.70 95.30 96.40 94.10 97.50 97.90 95.70 82.85 98.30 95.30 95.25
tfHub_LaBSE(xx→en) 96.00 98.80 99.40 96.30 91.20 94.00 96.50 92.90 97.00 97.80 95.40 83.58 98.50 95.30 95.19
15lang_LaBSE(en→xx) 95.20 98.00 99.20 96.10 90.50 95.20 96.30 93.50 97.50 97.90 95.80 82.85 98.30 95.40 95.13
15lang_LaBSE(xx→en) 95.40 98.70 99.40 96.30 91.10 94.00 96.30 92.70 96.70 97.80 95.40 83.58 98.50 95.20 95.08
  • Accuracy(%) of the Tatoeba datasets.
  • If the strategy to select vocabs is changed or the corpus used in the selection step is changed to the corpus similar to the evaluation dataset, it is expected to reduce the performance drop.

References

You might also like...
Comments
  • Training time and Machine configuration

    Training time and Machine configuration

    Hi, thanks for your sharing model. I want to make a smaller model, just contains two languages(en, zh). And I want to know the kind of machine GPU and how long does it need to cost?

    opened by QzzIsCoding 2
  • Publish model to HuggingFace Model Hub?

    Publish model to HuggingFace Model Hub?

    I migrated the full LaBSE model from TF to PyTorch and uploaded them to the HuggingFace model hub. I saw this model on the TF hub and started migrating it for uploading to the HF Hub. I realized then that this wasn't published by Google but by @jeongukjae, so wanted to check with you before uploading it.

    I have exported the model locally. I'm happy to check the changes in and upload the exported model if that's fine for you :).

    opened by setu4993 2
Owner
Jeong Ukjae
Jeong Ukjae
GitHub Repository
Machine learning models from Singapore's NLP research community

SG-NLP Machine learning models from Singapore's natural language processing (NLP) research community. sgnlp is a Python package that allows you to eas

AI Singapore | AI Makerspace 21 Dec 17, 2022
Production First and Production Ready End-to-End Keyword Spotting Toolkit

Production First and Production Ready End-to-End Keyword Spotting Toolkit

223 Jan 02, 2023
Toward Model Interpretability in Medical NLP

Toward Model Interpretability in Medical NLP LING380: Topics in Computational Linguistics Final Project James Cross ( 1 Mar 04, 2022

Score-Based Point Cloud Denoising (ICCV'21)

Score-Based Point Cloud Denoising (ICCV'21) [Paper] https://arxiv.org/abs/2107.10981 Installation Recommended Environment The code has been tested in

Shitong Luo 79 Dec 26, 2022
BERT, LDA, and TFIDF based keyword extraction in Python

BERT, LDA, and TFIDF based keyword extraction in Python kwx is a toolkit for multilingual keyword extraction based on Google's BERT and Latent Dirichl

Andrew Tavis McAllister 41 Dec 27, 2022
Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers

beyond masking Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers The code is coming Figure 1: Pipeline of token-based pre-

Yunjie Tian 23 Sep 27, 2022
A PyTorch Implementation of End-to-End Models for Speech-to-Text

speech Speech is an open-source package to build end-to-end models for automatic speech recognition. Sequence-to-sequence models with attention, Conne

Awni Hannun 647 Dec 25, 2022
The Easy-to-use Dialogue Response Selection Toolkit for Researchers

The Easy-to-use Dialogue Response Selection Toolkit for Researchers

GMFTBY 32 Nov 13, 2022
Sequence modeling benchmarks and temporal convolutional networks

Sequence Modeling Benchmarks and Temporal Convolutional Networks (TCN) This repository contains the experiments done in the work An Empirical Evaluati

CMU Locus Lab 3.5k Jan 03, 2023
Pretrain CPM - 大规模预训练语言模型的预训练代码

CPM-Pretrain 版本更新记录 为了促进中文自然语言处理研究的发展，本项目提供了大规模预训练语言模型的预训练代码。项目主要基于DeepSpeed、Megatron实现，可以支持数据并行、模型加速、流水并行的代码。 安装 1、首先安装pytorch等基础依赖，再安装APEX以支持fp16。 p

Tsinghua AI 37 Dec 06, 2022
Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning

GenSen Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning Sandeep Subramanian, Adam Trischler, Yoshua B

Maluuba Inc. 309 Oct 19, 2022
Yet Another Sequence Encoder - Encode sequences to vector of vector in python !

Yase Yet Another Sequence Encoder - encode sequences to vector of vectors in python ! Why Yase ? Yase enable you to encode any sequence which can be r

Pierre PACI 12 Aug 19, 2021
FB ID CLONER WUTHOT CHECKPOINT, FACEBOOK ID CLONE FROM FILE

* MY SOCIAL MEDIA : Programming And Memes Want to contact Mr. Error ? CONTACT : [ema

Mr. Error 9 Jun 17, 2021
TalkNet: Audio-visual active speaker detection Model

Is someone talking? TalkNet: Audio-visual active speaker detection Model This repository contains the code for our ACM MM 2021 paper, TalkNet, an acti

142 Dec 14, 2022
Learning Spatio-Temporal Transformer for Visual Tracking

STARK The official implementation of the paper Learning Spatio-Temporal Transformer for Visual Tracking Highlights The strongest performances Tracker

Multimedia Research 485 Jan 04, 2023
PyTorch source code of NAACL 2019 paper "An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models"

This repository contains source code for NAACL 2019 paper "An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models" (P

Alexandra Chronopoulou 89 Aug 12, 2022
A simple word search made in python

Word Search Puzzle A simple word search made in python Usage $ python3 main.py -h usage: main.py [-h] [-c] [-f FILE] Generates a word s

Magoninho 16 Mar 10, 2022
Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge This is an implementation of the paper,

Mutian He 19 Oct 14, 2022
A benchmark for evaluation and comparison of various NLP tasks in Persian language.

Persian NLP Benchmark The repository aims to track existing natural language processing models and evaluate their performance on well-known datasets.

Mofid AI 68 Dec 19, 2022
Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition

SEW (Squeezed and Efficient Wav2vec) The repo contains the code of the paper "Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speec

ASAPP Research 67 Dec 01, 2022