Implementing SimCSE(paper, official repository) using TensorFlow 2 and KR-BERT.

Overview

KR-BERT-SimCSE

Implementing SimCSE(paper, official repository) using TensorFlow 2 and KR-BERT.

Training

Unsupervised

python train_unsupervised.py --mixed_precision

I used Korean Wikipedia Corpus that is divided into sentences in advance. (Check out tfds-korean catalog page for details)

  • Settings
    • KR-BERT character
    • peak learning rate 3e-5
    • batch size 64
    • Total steps: 25,000
    • 0.05 warmup rate, and linear decay learning rate scheduler
    • temperature 0.05
    • evalaute on KLUE STS and KorSTS every 250 steps
    • max sequence length 64
    • Use pooled outputs for training, and [CLS] token's representations for inference

The hyperparameters were not tuned and mostly followed the values in the paper.

Supervised

python train_supervised.py --mixed_precision

I used KorNLI for supervised training. (Check out tfds-korean catalog page)

  • Settings
    • KR-BERT character
    • batch size 128
    • epoch 3
    • peak learning rate 5e-5
    • 0.05 warmup rate, and linear decay learning rate scheduler
    • temperature 0.05
    • evalaute on KLUE STS and KorSTS every 125 steps
    • max sequence length 48
    • Use pooled outputs for training, and [CLS] token's representations for inference

The hyperparameters were not tuned and mostly followed the values in the paper.

Results

KorSTS (dev set results)

model 100 X Spearman correlation
KR-BERT base
SimCSE
unsupervised bi encoding 79.99
KR-BERT base
SimCSE-supervised
trained on KorNLI bi encoding 84.88
SRoBERTa base* unsupervised bi encoding 63.34
SRoBERTa base* trained on KorNLI bi encoding 76.48
SRoBERTa base* trained on KorSTS bi encoding 83.68
SRoBERTa base* trained on KorNLI -> KorSTS bi encoding 83.54
SRoBERTa large* trained on KorNLI bi encoding 77.95
SRoBERTa large* trained on KorSTS bi encoding 84.74
SRoBERTa large* trained on KorNLI -> KorSTS bi encoding 84.21

KorSTS (test set results)

model 100 X Spearman correlation
KR-BERT base
SimCSE
unsupervised bi encoding 73.25
KR-BERT base
SimCSE-supervised
trained on KorNLI bi encoding 80.72
SRoBERTa base* unsupervised bi encoding 48.96
SRoBERTa base* trained on KorNLI bi encoding 74.19
SRoBERTa base* trained on KorSTS bi encoding 78.94
SRoBERTa base* trained on KorNLI -> KorSTS bi encoding 80.29
SRoBERTa large* trained on KorNLI bi encoding 75.46
SRoBERTa large* trained on KorSTS bi encoding 79.55
SRoBERTa large* trained on KorNLI -> KorSTS bi encoding 80.49
SRoBERTa base* trained on KorSTS cross encoding 83.00
SRoBERTa large* trained on KorSTS cross encoding 85.27

KLUE STS (dev set results)

model 100 X Pearson's correlation
KR-BERT base
SimCSE
unsupervised bi encoding 74.45
KR-BERT base
SimCSE-supervised
trained on KorNLI bi encoding 79.42
KR-BERT base* supervised cross encoding 87.50

References

@misc{gao2021simcse,
    title={SimCSE: Simple Contrastive Learning of Sentence Embeddings},
    author={Tianyu Gao and Xingcheng Yao and Danqi Chen},
    year={2021},
    eprint={2104.08821},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}
@misc{ham2020kornli,
    title={KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding},
    author={Jiyeon Ham and Yo Joong Choe and Kyubyong Park and Ilji Choi and Hyungjoon Soh},
    year={2020},
    eprint={2004.03289},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}
@misc{park2021klue,
    title={KLUE: Korean Language Understanding Evaluation},
    author={Sungjoon Park and Jihyung Moon and Sungdong Kim and Won Ik Cho and Jiyoon Han and Jangwon Park and Chisung Song and Junseong Kim and Yongsook Song and Taehwan Oh and Joohong Lee and Juhyun Oh and Sungwon Lyu and Younghoon Jeong and Inkwon Lee and Sangwoo Seo and Dongjun Lee and Hyunwoo Kim and Myeonghwa Lee and Seongbo Jang and Seungwon Do and Sunkyoung Kim and Kyungtae Lim and Jongwon Lee and Kyumin Park and Jamin Shin and Seonghyun Kim and Lucy Park and Alice Oh and Jung-Woo Ha and Kyunghyun Cho},
    year={2021},
    eprint={2105.09680},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}
Owner
Jeong Ukjae
Jeong Ukjae
Script to download some free japanese lessons in portuguse from NHK

Nihongo_nhk This is a script to download some free japanese lessons in portuguese from NHK. It can be executed by installing the packages with: pip in

Matheus Alves 2 Jan 06, 2022
Code for Text Prior Guided Scene Text Image Super-Resolution

Code for Text Prior Guided Scene Text Image Super-Resolution

82 Dec 26, 2022
Mlcode - Continuous ML API Integrations

mlcode Basic APIs for ML applications. Django REST Application Contains REST API

Sujith S 1 Jan 01, 2022
Library for fast text representation and classification.

fastText fastText is a library for efficient learning of word representations and sentence classification. Table of contents Resources Models Suppleme

Facebook Research 24.1k Jan 05, 2023
Phrase-Based & Neural Unsupervised Machine Translation

Unsupervised Machine Translation This repository contains the original implementation of the unsupervised PBSMT and NMT models presented in Phrase-Bas

Facebook Research 1.5k Dec 28, 2022
The entmax mapping and its loss, a family of sparse softmax alternatives.

entmax This package provides a pytorch implementation of entmax and entmax losses: a sparse family of probability mappings and corresponding loss func

DeepSPIN 330 Dec 22, 2022
Code for using and evaluating SpanBERT.

SpanBERT This repository contains code and models for the paper: SpanBERT: Improving Pre-training by Representing and Predicting Spans. If you prefer

Meta Research 798 Dec 30, 2022
SIGIR'22 paper: Axiomatically Regularized Pre-training for Ad hoc Search

Introduction This codebase contains source-code of the Python-based implementation (ARES) of our SIGIR 2022 paper. Chen, Jia, et al. "Axiomatically Re

Jia Chen 17 Nov 09, 2022
Wake: Context-Sensitive Automatic Keyword Extraction Using Word2vec

Wake Wake: Context-Sensitive Automatic Keyword Extraction Using Word2vec Abstract استخراج خودکار کلمات کلیدی متون کوتاه فارسی با استفاده از word2vec ب

Omid Hajipoor 1 Dec 17, 2021
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP

TextAttack 🐙 Generating adversarial examples for NLP models [TextAttack Documentation on ReadTheDocs] About • Setup • Usage • Design About TextAttack

QData 2.2k Jan 03, 2023
A python script that will use hydra to get user and password to login to ssh, ftp, and telnet

Hydra-Auto-Hack A python script that will use hydra to get user and password to login to ssh, ftp, and telnet Project Description This python script w

2 Jan 16, 2022
PyTorch original implementation of Cross-lingual Language Model Pretraining.

XLM NEW: Added XLM-R model. PyTorch original implementation of Cross-lingual Language Model Pretraining. Includes: Monolingual language model pretrain

Facebook Research 2.7k Dec 27, 2022
Extracting Summary Knowledge Graphs from Long Documents

GraphSum This repo contains the data and code for the G2G model in the paper: Extracting Summary Knowledge Graphs from Long Documents. The other basel

Zeqiu (Ellen) Wu 10 Oct 21, 2022
Basic yet complete Machine Learning pipeline for NLP tasks

Basic yet complete Machine Learning pipeline for NLP tasks This repository accompanies the article on building basic yet complete ML pipelines for sol

Ivan 20 Aug 22, 2022
Shellcode antivirus evasion framework

Schrodinger's Cat Schrodinger'sCat is a Shellcode antivirus evasion framework Technical principle Please visit my blog https://idiotc4t.com/ How to us

idiotc4t 27 Jul 09, 2022
Harvis is designed to automate your C2 Infrastructure.

Harvis Harvis is designed to automate your C2 Infrastructure, currently using Mythic C2. 📌 What is it? Harvis is a python tool to help you create mul

Thiago Mayllart 99 Oct 06, 2022
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context

LSTC: Boosting Atomic Action Detection with Long-Short-Term Context This Repository contains the code on AVA of our ACM MM 2021 paper: LSTC: Boosting

Tencent YouTu Research 9 Oct 11, 2022
Twitter-NLP-Analysis - Twitter Natural Language Processing Analysis

Twitter-NLP-Analysis Business Problem I got last @turk_politika 3000 tweets with

Çağrı Karadeniz 7 Mar 12, 2022
Google and Stanford University released a new pre-trained model called ELECTRA

Google and Stanford University released a new pre-trained model called ELECTRA, which has a much compact model size and relatively competitive performance compared to BERT and its variants. For furth

Yiming Cui 1.2k Dec 30, 2022
Chinese NER with albert/electra or other bert descendable model (keras)

Chinese NLP (albert/electra with Keras) Named Entity Recognization Project Structure ./ ├── NER │   ├── __init__.py │   ├── log

2 Nov 20, 2022