roberta-base-ca Open-source Natural Language Inference Model

Home

Roberta Base Ca Finetuned Hate Speech Offensive Catalan

Developed by JonatanGk

Natural language inference model fine-tuned on MNLI task based on Catalan RoBERTa model

Text Classification

Transformers

Open Source License:Apache-2.0 #Catalan language inference #High-accuracy NLI #Multi-round fine-tuning optimization

Downloads 16

Release Time : 3/2/2022

Model Overview

This model is a fine-tuned version of BSC-TeMU's Catalan RoBERTa base model on the MNLI (Multi-Genre Natural Language Inference) task, specifically designed for textual entailment recognition tasks.

Model Features

Catalan language optimization

Pre-trained model specifically optimized for Catalan language

High accuracy

Achieves 87.78% accuracy on evaluation sets

MNLI task fine-tuning

Specifically optimized for multi-genre natural language inference tasks

Model Capabilities

Textual entailment recognition

Natural language inference

Text classification

Use Cases

Natural Language Processing

Textual entailment judgment

Determine the logical relationship between two sentences (entailment, contradiction or neutral)

Evaluation accuracy 87.78%

Question answering system support

Provide logical reasoning support for QA systems

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3699	1.0	1255	0.3712	0.8669
0.3082	2.0	2510	0.3401	0.8766
0.2375	3.0	3765	0.4137	0.8778
0.1889	4.0	5020	0.4671	0.8733
0.1486	5.0	6275	0.5205	0.8749

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Roberta Base Ca Finetuned Hate Speech Offensive Catalan

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 roberta-base-ca-finetuned-mnli

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

🔧 Technical Details

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License