KoBERT and KoBigBird

KoBERT

Established

KoBigBird

Emerging

Maintenance 2/25

Adoption 10/25

Maturity 16/25

Community 25/25

Maintenance 0/25

Adoption 10/25

Maturity 16/25

Community 14/25

Stars: 1,407

Forks: 380

Downloads: —

Commits (30d): 0

Language: Python

License: Apache-2.0

Stars: 201

Forks: 21

Downloads: —

Commits (30d): 0

Language: Python

License: Apache-2.0

Stale 6m No Package No Dependents

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.

Korean-language-processing text-analytics sentiment-analysis named-entity-recognition semantic-search

About KoBigBird

monologg/KoBigBird

🦅 Pretrained BigBird Model for Korean (up to 4096 tokens)

KoBigBird helps you process and understand very long pieces of Korean text, such as extensive reports, articles, or conversations. It takes lengthy Korean text as input and helps you extract information or classify the content with higher accuracy than standard methods. This tool is for researchers and data scientists working with complex Korean language data.

Korean-NLP text-summarization information-extraction sentiment-analysis document-classification

Related comparisons

KoBERT and KoBERT-Transformers KoBERT and KoBERT-KorQuAD KoBERT and DistilKoBERT

Scores updated daily from GitHub, PyPI, and npm data. How scores work