For encoding a text longer than 512 tokens, for example 800. Set max_pos to 800 during both preprocessing and training.

Last update: Nov 02, 2022

Related tags

Deep Learning SciBERTSUM

Overview

LongScientificFormer

For encoding a text longer than 512 tokens, for example 800. Set max_pos to 800 during both preprocessing and training.

Some codes are borrowed from ONMT(https://github.com/OpenNMT/OpenNMT-py)

Data Preparation

Option 1: download the processed data

Pre-processed data

Put all files into raw_data directory

Step 2. Download Stanford CoreNLP

We will need Stanford CoreNLP to tokenize the data. Download it here and unzip it. Then add the following command to your bash_profile:

export CLASSPATH=/path/to/stanford-corenlp-4.2.2/stanford-corenlp-4.2.2.jar

replacing /path/to/ with the path to where you saved the stanford-corenlp-4.2.2 directory.

step 3. extracting sections from GROBID XML files

python preprocess.py -mode extract_pdf_sections -log_file ../logs/extract_section.log

step 4. extracting text from TIKA XML files

python preprocess.py -mode get_text_clean_tika -log_file ../logs/extract_tika_text.log

step 5. Tokenize texts from papers and slides using stanfordCoreNLP

python preprocess.py -mode tokenize  -save_path ../temp -log_file ../logs/tokenize_by_corenlp.log

Step 6. Extract source, section, and target from tokenized files

python preprocess.py -mode clean_paper_jsons -save_path ../json_data/  -n_cpus 10 -log_file ../logs/build_json.log

Step 7. Generate BERT `.pt` files from source, sections and targets

python preprocess.py -mode format_to_bert -raw_path ../json_data/ -save_path ../bert_data  -lower -n_cpus 40 -log_file ../logs/build_bert_files.log

Model Training

First run: For the first time, you should use single-GPU, so the code can download the BERT model. Use -visible_gpus -1, after downloading, you could kill the process and rerun the code with multi-GPUs.

Train

python train.py  -ext_dropout 0.1 -lr 2e-3  -visible_gpus 1,2,3 -report_every 200 -save_checkpoint_steps 1000 -batch_size 1 -train_steps 100000 -accum_count 2  -log_file ../logs/ext_bert -use_interval true -warmup_steps 10000

To continue training from a checkpoint

python train.py  -ext_dropout 0.1 -lr 2e-3  -train_from ../models/model_step_99000.pt -visible_gpus 1,2,3 -report_every 200 -save_checkpoint_steps 1000 -batch_size 1 -train_steps 100000 -accum_count 2  -log_file ../logs/ext_bert -use_interval true -warmup_steps 10000

Test

python train.py -mode test  -test_batch_size 1 -bert_data_path ../bert_data -log_file ../logs/ext_bert_test -test_from ../models/model_step_99000.pt -model_path ../models -sep_optim true -use_interval true -visible_gpus 1,2,3 -alpha 0.95 -result_path ../results/ext

For encoding a text longer than 512 tokens, for example 800. Set max_pos to 800 during both preprocessing and training.

Related tags

Overview

LongScientificFormer

Data Preparation

Option 1: download the processed data

Step 2. Download Stanford CoreNLP

step 3. extracting sections from GROBID XML files

step 4. extracting text from TIKA XML files

step 5. Tokenize texts from papers and slides using stanfordCoreNLP

Step 6. Extract source, section, and target from tokenized files

Step 7. Generate BERT `.pt` files from source, sections and targets

Model Training

Train

Test

Owner

Athar Sefid

Official PyTorch implementation of "Synthesis of Screentone Patterns of Manga Characters"

Cours d'Algorithmique Appliquée avec Python pour BTS SIO SISR

Shape-Adaptive Selection and Measurement for Oriented Object Detection

A tool for calculating distortion parameters in coordination complexes.

BOOKSUM: A Collection of Datasets for Long-form Narrative Summarization

Annotate datasets with a semi-trained or fully trained YOLOv5 model

E-Ink Magic Calendar that automatically syncs to Google Calendar and runs off a battery powered Raspberry Pi Zero

Multi Task Vision and Language

TensorFlow code for the neural network presented in the paper: "Structural Language Models of Code" (ICML'2020)

Code for the ICCV2021 paper "Personalized Image Semantic Segmentation"

Auto HMM: Automatic Discrete and Continous HMM including Model selection

PyTorch implementations of the paper: "DR.VIC: Decomposition and Reasoning for Video Individual Counting, CVPR, 2022"

Easy and comprehensive assessment of predictive power, with support for neuroimaging features

Import Python modules from dicts and JSON formatted documents.

COVID-VIT: Classification of Covid-19 from CT chest images based on vision transformer models

When are Iterative GPs Numerically Accurate?

Mosaic of Object-centric Images as Scene-centric Images (MosaicOS) for long-tailed object detection and instance segmentation.

Docker containers of baseline agents for the Crafter environment

L-Verse: Bidirectional Generation Between Image and Text

Powerful unsupervised domain adaptation method for dense retrieval.

For encoding a text longer than 512 tokens, for example 800. Set max_pos to 800 during both preprocessing and training.

Related tags

Overview

LongScientificFormer

Data Preparation

Option 1: download the processed data

Step 2. Download Stanford CoreNLP

step 3. extracting sections from GROBID XML files

step 4. extracting text from TIKA XML files

step 5. Tokenize texts from papers and slides using stanfordCoreNLP

Step 6. Extract source, section, and target from tokenized files

Step 7. Generate BERT .pt files from source, sections and targets

Model Training

Train

Test

Owner

Athar Sefid

Official PyTorch implementation of "Synthesis of Screentone Patterns of Manga Characters"

Cours d'Algorithmique Appliquée avec Python pour BTS SIO SISR

Shape-Adaptive Selection and Measurement for Oriented Object Detection

A tool for calculating distortion parameters in coordination complexes.

BOOKSUM: A Collection of Datasets for Long-form Narrative Summarization

Annotate datasets with a semi-trained or fully trained YOLOv5 model

E-Ink Magic Calendar that automatically syncs to Google Calendar and runs off a battery powered Raspberry Pi Zero

Multi Task Vision and Language

TensorFlow code for the neural network presented in the paper: "Structural Language Models of Code" (ICML'2020)

Code for the ICCV2021 paper "Personalized Image Semantic Segmentation"

Auto HMM: Automatic Discrete and Continous HMM including Model selection

PyTorch implementations of the paper: "DR.VIC: Decomposition and Reasoning for Video Individual Counting, CVPR, 2022"

Easy and comprehensive assessment of predictive power, with support for neuroimaging features

Import Python modules from dicts and JSON formatted documents.

COVID-VIT: Classification of Covid-19 from CT chest images based on vision transformer models

When are Iterative GPs Numerically Accurate?

Mosaic of Object-centric Images as Scene-centric Images (MosaicOS) for long-tailed object detection and instance segmentation.

Docker containers of baseline agents for the Crafter environment

L-Verse: Bidirectional Generation Between Image and Text

Powerful unsupervised domain adaptation method for dense retrieval.

Step 7. Generate BERT `.pt` files from source, sections and targets