R

Roberta Base Nli Stsb Bg

Developed by rmihaylov
This is a multilingual Roberta model that can generate sentence embeddings for Bulgarian, inspired by Sentence-BERT.
Downloads 607
Release Time : 4/18/2022

Model Overview

The model maps translated sentences to the same vector space as the original sentences, primarily used for sentence similarity tasks.

Model Features

Multilingual support
Supports sentence embedding generation for Bulgarian and English
Case-sensitive
Can distinguish between word cases (e.g., 'bulgarian' vs. 'Bulgarian')
Based on Sentence-BERT principles
Uses Sentence-BERT training methodology to map translation pairs to the same vector space

Model Capabilities

Sentence embedding generation
Cross-lingual sentence similarity calculation
Bulgarian text processing

Use Cases

Information retrieval
Related question matching
Finding the most relevant questions in FAQ systems based on user queries
As shown in the example, it can accurately match 'Какви са съставките на бисквитките?' with related questions
Cross-lingual applications
Cross-lingual document retrieval
Retrieving similar content between Bulgarian and English documents
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase