KoBERT and DistilKoBERT
About KoBERT
SKTBrain/KoBERT
Korean BERT pre-trained cased (KoBERT)
KoBERT is a tool for anyone working with the Korean language who needs to understand meaning or categorize text. It takes raw Korean text as input and helps identify sentiment, recognize named entities like organizations or product names, or compare sentence meanings. This is ideal for natural language processing specialists, data scientists, or researchers focused on Korean text analysis.
About DistilKoBERT
monologg/DistilKoBERT
Distillation of KoBERT from SKTBrain (Lightweight KoBERT)
This project offers a more efficient version of KoBERT, a powerful language model for Korean text. It takes raw Korean text as input and processes it for tasks like sentiment analysis, named entity recognition, or question answering, but with significantly faster performance and smaller resource usage. Anyone working with Korean language data and building applications like chatbots, content analysis tools, or information retrieval systems would find this useful.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work