# Korean NLP

A compact and efficient Transformer model designed specifically for Korean language processing tasks, utilizing syllable-level tokenization

Korean grammar correction model based on KOBART-v2, trained using the National Institute of Korean Language's spelling correction corpus

A classification model for detecting the authenticity of Korean news, capable of identifying false or misleading content

A Korean sentiment analysis model fine-tuned based on KcELECTRA-base-v2022, which achieved good results on the evaluation set.

KoSimCSE-BERT-multitask is a high-performance Korean sentence embedding model based on BERT architecture and optimized with multi-task learning strategy, specifically designed for generating high-quality Korean sentence embeddings.

CPU-optimized Korean processing pipeline with complete NLP capabilities including tokenization, POS tagging, dependency parsing, named entity recognition, etc.

CPU-optimized Korean processing pipeline with complete NLP functions including tokenization, part-of-speech tagging, dependency parsing, named entity recognition, etc.

Korean processing pipeline optimized for CPU, including tokenization, part-of-speech tagging, dependency parsing, named entity recognition, etc.

This is a Korean sentence embedding model based on sentence-transformers, capable of mapping sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

Albert base model trained on 70GB Korean text dataset, using 42,000 lowercase subword units

A RoBERTa model pretrained on Korean, suitable for various Korean natural language processing tasks.

Korean pre-trained model based on BART architecture, optimized for teachable natural language processing

Stanza is an efficient multilingual linguistic analysis toolkit that provides functionalities from raw text processing to syntactic parsing and named entity recognition.

This is a Korean sentence transformer model based on KLUE-RoBERTa-small, specifically designed for sentence similarity calculation and natural language inference tasks.

Korean BERT base model trained on a 70GB Korean text dataset, using 42,000 lowercase subword units.

RoBERTa model trained on Korean dataset for sentence intent understanding tasks

A Korean intent classification model fine-tuned based on KLUE's RoBERTa-small model, designed to recognize 7 different intent types.