Pre-training BERT masked language models with custom vocabulary

Last update: Nov 2, 2022

Related tags

Overview

Pre-training BERT Masked Language Models (MLM)

This repository contains the method to pre-train a BERT model using custom vocabulary. It was used to pre-train JuriBERT presented in [https://arxiv.org/abs/2110.01485].

It also contains the code of the classification task that was used to evaluate JuriBERT.

Our models can be found at [http://master2-bigdata.polytechnique.fr/FrenchLinguisticResources/resources#juribert] and downloaded upon request.

Instructions

To pre-train a new BERT model you need the path to a dataset containing raw text. You can also specify an existing tokenizer for the model. Paths for saving the model and the checkpoints are required.

python pretrain.py \
      --files /path/to/text \
      --model_path /path/to/save/model \
      --checkpoint /path/to/save/checkpoints \
      --epochs 30 \
      --hidden_layers 2 \
      --hidden_size 128 \
      --attention_heads 2 \
      --save_steps 10 \
      --save_limit 0 \
      --min_freq 0

To finetune on a classification task you need the path to the pre-trained model and a CSV file containing the classification dataset. You need to specify the columns containing the category and the text as well as the path for saving the final model and the checkpoints.

python classification.py \
  --model "custom" \
  --pretrained_path /path/to/model.bin \
  --tokenizer_path /path/to/tokenizer.json \
  --data /path/to/data.csv \
  --category "category-column" \
  --text "text-column" \
  --model_path /path/to/save/model \
  --checkpoint /path/to/save/checkpoints

You can use --help to see all the available commands.

To test the masked language model use:

fill_mask = pipeline(
    "fill-mask",
    model="/path/to/model",
    tokenizer=tokenizer
)

fill_mask("Paris est la capitale de la <mask>.")

LV-BERT: Exploiting Layer Variety for BERT (Findings of ACL 2021)

LV-BERT Introduction In this repo, we introduce LV-BERT by exploiting layer variety for BERT. For detailed description and experimental results, pleas

14 Aug 24, 2022

VD-BERT: A Unified Vision and Dialog Transformer with BERT

VD-BERT: A Unified Vision and Dialog Transformer with BERT PyTorch Code for the following paper at EMNLP2020: Title: VD-BERT: A Unified Vision and Dia

44 Nov 1, 2022

Pytorch-version BERT-flow: One can apply BERT-flow to any PLM within Pytorch framework.

59 Dec 1, 2022

Universal End2End Training Platform, including pre-training, classification tasks, machine translation, and etc.

背景安装教程快速上手（一）预训练模型（二）机器翻译（三）文本分类 TenTrans 进阶 1. 多语言机器翻译 2. 跨语言预训练背景 TrenTrans是一个统一的端到端的多语言多任务预训练平台，支持多种预训练方式，以及序列生成和自然语言理解任务。安装教程 git clone git

Tencent Minority-Mandarin Translation Team

42 Dec 20, 2022

Natural language processing summarizer using 3 state of the art Transformer models: BERT, GPT2, and T5

NLP-Summarizer Natural language processing summarizer using 3 state of the art Transformer models: BERT, GPT2, and T5 This project aimed to provide in

1 Feb 7, 2022

TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset.

TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset. TunBERT was applied to three NLP downstream tasks: Sentiment Analysis (SA), Tunisian Dialect Identification (TDI) and Reading Comprehension Question-Answering (RCQA)

72 Dec 9, 2022

Comments

Access to JuriBERT model

Just a small thing : it seems that the URL in this project README is incorrect and should be replaced with :

http://nlp.polytechnique.fr/resources#juribert

Thank you for your work on JuriBERT and for publishing this repository, this is both really interesting and helpful.

opened by juba 1

Pre-training BERT masked language models with custom vocabulary

Related tags

Overview

Pre-training BERT Masked Language Models (MLM)

Instructions

You might also like...

LV-BERT: Exploiting Layer Variety for BERT (Findings of ACL 2021)

VD-BERT: A Unified Vision and Dialog Transformer with BERT

Pytorch-version BERT-flow: One can apply BERT-flow to any PLM within Pytorch framework.

Universal End2End Training Platform, including pre-training, classification tasks, machine translation, and etc.

Natural language processing summarizer using 3 state of the art Transformer models: BERT, GPT2, and T5

TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset.

RoNER is a Named Entity Recognition model based on a pre-trained BERT transformer model trained on RONECv2

Must-read papers on improving efficiency for pre-trained language models.

The repository for the paper: Multilingual Translation via Grafting Pre-trained Language Models

Comments

Access to JuriBERT model

Owner

Stella Douka

天池中药说明书实体识别挑战冠军方案；中文命名实体识别；NER; BERT-CRF & BERT-SPAN & BERT-MRC；Pytorch

ACL22 paper: Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost

Semi-automated vocabulary generation from semantic vector models

MILES is a multilingual text simplifier inspired by LSBert - A BERT-based lexical simplification approach proposed in 2018. Unlike LSBert, MILES uses the bert-base-multilingual-uncased model, as well as simple language-agnostic approaches to complex word identification (CWI) and candidate ranking.

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Ongoing research training transformer language models at scale, including: BERT & GPT-2

TaCL: Improve BERT Pre-training with Token-aware Contrastive Learning

iBOT: Image BERT Pre-Training with Online Tokenizer

Code and checkpoints for training the transformer-based Table QA models introduced in the paper TAPAS: Weakly Supervised Table Parsing via Pre-training.

An extension for asreview implements a version of the tf-idf feature extractor that saves the matrix and the vocabulary.