Fact-or-Opinion-XLMR-EL Open-Source Model - Free Deployment for Fact-Opinion Classification of English and Spanish Sentences

Fact Or Opinion Xlmr El

Developed by lighteternal

This is a binary classification model based on the XLM-Roberta-base architecture, capable of classifying sentences as facts or opinions. It supports English and Greek, and features zero-shot learning capability.

Text Classification

Transformers

Supports Multiple LanguagesOpen Source License:Apache-2.0 #Multilingual fact-checking #English-Greek hybrid training #Zero-shot transfer

Downloads 1,051

Release Time : 3/2/2022

Model Overview

This model is designed for text classification tasks, specifically to distinguish factual statements from subjective opinions. Jointly developed by the Hellenic Army Academy and the Technical University of Crete, it is trained on a mixed English-Greek annotated corpus.

Model Features

Bilingual training

The model is trained on a mixed English and Greek dataset, enabling bilingual processing capabilities

Zero-shot learning

Supports classification tasks in any language supported by XLM-R without language-specific training

High accuracy

Achieves an F1 score of 0.952 on test sets, demonstrating excellent performance

Model Capabilities

Text classification

Fact-checking

Opinion recognition

Multilingual processing

Use Cases

Content moderation

News fact-checking

Automatically identifies factual statements and opinion expressions in news content

Improves efficiency in verifying news authenticity

Academic research

Literature analysis

Distinguishes objective facts from subjective opinions in academic literature

Assists researchers in quickly locating key information

🚀 Fact vs. opinion binary classifier, trained on a mixed EN-EL annotated corpus.

This is a binary classifier model trained on a mixed English - Greek annotated corpus, which can classify sentences as facts or opinions.

🚀 Quick Start

This is an XLM - Roberta - base model with a binary classification head. Given a sentence, it can classify it either as a fact or an opinion based on its content.

You can use this model in any of the XLM - R supported languages for the same task, taking advantage of its 0 - shot learning capabilities. However, the model was trained only using English and Greek sentences.

Legend of HuggingFace API labels

Label 0: Opinion/Subjective sentence
Label 1: Fact/Objective sentence

✨ Features

Multilingual Support: Supports multiple languages in the XLM - R language family, leveraging 0 - shot learning capabilities.
Binary Classification: Accurately classifies sentences as facts or opinions.

📦 Installation

The README does not provide installation steps, so this section is skipped.

💻 Usage Examples

The README does not provide code examples, so this section is skipped.

📚 Documentation

Dataset training info

The original dataset (available here: https://github.com/1024er/cbert_aug/tree/crayon/datasets/subj) contained approximately 9000 annotated sentences (classified as subjective or objective). It was translated to Greek using Google Translate. The Greek version was then concatenated with the original English one to create the mixed EN - EL dataset.

The model was trained for 5 epochs, using batch size = 8. Detailed metrics and hyperparameters are available on the "Metrics" tab.

Evaluation Results on test set

Property	Details
Accuracy	0.952
Precision	0.945
Recall	0.960
F1	0.952

Acknowledgement

The research work was supported by the Hellenic Foundation for Research and Innovation (HFRI) under the HFRI PhD Fellowship grant (Fellowship Number: 50, 2nd call)

📄 License

This project is licensed under the apache - 2.0 license.

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