M

Mmlw Roberta Large

Developed by sdadas
A large-scale Polish sentence transformation model based on the RoBERTa architecture, focusing on sentence similarity calculation and feature extraction tasks.
Downloads 5,007
Release Time : 11/17/2023

Model Overview

This model is a Polish pre-trained model based on the RoBERTa architecture, primarily used for sentence similarity calculation, feature extraction, and related natural language processing tasks. It performs exceptionally well in the MTEB Polish benchmark tests.

Model Features

Polish language optimization
Specially optimized for Polish, excelling in Polish NLP tasks
Multi-task capability
Supports various NLP tasks including sentence similarity calculation, clustering, classification, and retrieval
MTEB benchmark validation
Achieved excellent results in multiple MTEB Polish benchmark tests

Model Capabilities

Sentence similarity calculation
Text feature extraction
Text clustering
Text classification
Information retrieval

Use Cases

Text analysis
Review classification
Performing sentiment or topic classification on Polish product reviews
Achieved 47.5% accuracy on the AllegroReviews dataset
Semantic similarity judgment
Determining the semantic similarity between two Polish sentences
Achieved a Spearman correlation coefficient of 92.5 on the CDSC-R dataset
Information retrieval
Question answering system
Building semantic retrieval components for Polish question-answering systems
Achieved MAP@10 of 62.6 on the HotpotQA-PL dataset
Document retrieval
Semantic-based retrieval of Polish documents
Achieved MRR@10 of 73.6 on the DBPedia-PL dataset
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase