kh-kim / simple-nmt
This repo contains a simple source code for advanced neural machine translation based on sequence-to-sequence.
☆144Updated 3 years ago
Alternatives and similar repositories for simple-nmt:
Users that are interested in simple-nmt are comparing it to the libraries listed below
- Korean Parallel Corpus☆145Updated last year
- The code and models for "An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks" (AACL-IJCNLP 2020)☆118Updated 4 years ago
- Transformer Implementation using PyTorch for Neural Machine Translation (Korean to English)☆69Updated 3 years ago
- PyTorch v1.2에서 생긴 Transformer API 를 이용한 간단한 Chitchat 챗봇☆49Updated 5 years ago
- 11.5기의 beyondBERT의 토론 내용을 정리하는 repository입니다.☆59Updated 4 years ago
- BERTScore for Korean☆76Updated last year
- MULTI GPU환경에서 ETRI 한국어 BERT모델 활용한 Korquad 학습 방법☆29Updated 5 years ago
- KoRean based BERT pre-trained models (KR-BERT) for Tensorflow and PyTorch☆207Updated 11 months ago
- https://ailabs.enliple.com/☆105Updated 4 years ago
- Kobart model on Huggingface transformers☆63Updated 3 years ago
- Subword-level Word Vector Representations for Korean (ACL 2018)☆107Updated 5 years ago
- ☆20Updated last year
- Korean MRC (KorQuAD) with KoBERT☆64Updated last year
- Open Korean NLP Dataset Curation for the Users All Around the Globe☆146Updated last year
- Distillation of KoBERT from SKTBrain (Lightweight KoBERT)☆193Updated last year
- Korean sejong corpus download and simple analysis☆141Updated 5 years ago
- 국내 자연어 처리 기술을 연구 및 개발하는 스타트업 목록☆166Updated 4 years ago
- Korean-English Bilingual Electra Models☆109Updated 3 years ago
- NLP Shared tasks (NER, SRL) using NSML☆178Updated 6 years ago
- [2021 훈민정음 한국어 음성•자연어 인공지능 경진대회] 대화요약 부문 알라꿍달라꿍 팀의 대화요약 학습 및 추론 코드를 공유하기 위한 레포입니다.☆127Updated 2 years ago
- HanBert on 🤗 Huggingface Transformers 🤗☆87Updated 4 years ago
- Finetuning Pipeline☆90Updated 3 years ago
- KU_NERDY 이동엽, 임희석 (2017 국어 정보 처리 시스템경진대회 금상) - 한글 및 한국어 정보처리 학술대회☆32Updated 6 years ago
- Universal Dependency Treebanks in Korean☆37Updated 3 years ago
- 🦅 Pretrained BigBird Model for Korean (up to 4096 tokens)☆203Updated last year
- KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding☆304Updated last year
- Character-level Korean ELECTRA Model (음절 단위 한국어 ELECTRA)☆54Updated last year
- ☆195Updated last year
- Korean Relation Extraction Gold Standard☆35Updated 3 years ago
- Data Augmentation Toolkit for Korean text.☆51Updated 3 years ago