K

Ko Core News Lg

Developed by spacy
CPU-optimized Korean processing pipeline with complete NLP capabilities including tokenization, POS tagging, dependency parsing, named entity recognition, etc.
Downloads 52
Release Time : 5/2/2022

Model Overview

spaCy's large Korean processing model, trained on UD Korean Kaist and KLUE datasets, supporting full NLP processing pipeline including tokenization, POS tagging, dependency parsing, named entity recognition, and more.

Model Features

Complete Korean processing pipeline
Provides full NLP processing capabilities from tokenization to named entity recognition
CPU optimization
Specially optimized for CPU environments, suitable for resource-constrained scenarios
High-quality word vectors
Includes floret word vectors (200000, 300) for better semantic understanding
Multi-task processing
Simultaneously supports various NLP tasks including POS tagging, dependency parsing, and named entity recognition

Model Capabilities

Tokenization
POS tagging
Dependency parsing
Named entity recognition
Lemmatization
Sentence boundary detection

Use Cases

Text processing
Korean text analysis
Performs grammatical analysis and structural parsing of Korean news and social media content
Accurately identifies sentence components and grammatical relationships
Information extraction
Extracts named entities (person names, locations, organization names, etc.) from Korean text
Achieves F1 score of 85.19%
Linguistic research
Korean grammar research
Analyzes Korean syntactic structures and morphological features
Provides detailed POS tagging and dependency relationship analysis
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase