R

Roberta Ko Small Tsdae

Developed by smartmind
This is a Korean small RoBERTa model based on sentence-transformers, capable of mapping sentences and paragraphs into a 256-dimensional dense vector space, suitable for tasks such as clustering or semantic search.
Downloads 39
Release Time : 9/19/2022

Model Overview

The model adopts the TSDAE pre-training method, with the same architecture as lassl/roberta-ko-small but uses a different tokenizer. It can be directly used for calculating sentence similarity or fine-tuned for specific tasks.

Model Features

TSDAE Pre-training
Utilizes TSDAE (Transformer-based Sequential Denoising Auto-Encoder) pre-training method, enhancing the model's semantic understanding capabilities.
256-dimensional dense vectors
Can map sentences and paragraphs into a 256-dimensional dense vector space, facilitating subsequent similarity calculations and clustering analysis.
Korean optimization
A model specifically optimized for Korean, using a Korean-specific tokenizer.
Lightweight
A small RoBERTa model with lower computational resource requirements.

Model Capabilities

Sentence vectorization
Semantic similarity calculation
Text clustering
Semantic search

Use Cases

Information retrieval
Similar document retrieval
Find documents semantically similar to the query sentence in a document library.
Text analysis
Sentence clustering
Automatically group semantically similar sentences.
Question answering systems
Similar question matching
Match standard questions semantically similar to user queries in FAQ systems.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Ā© 2025AIbase