Distilbart Ftn Wiki Lingua

🚀 Pre-trained BART Model fine-tune on WikiLingua dataset

This repository contains a fine-tuned BART model (by sshleifer) using the English wiki_lingua dataset, aiming to examine the performance of the fine-tuned model for research purposes.

🚀 Quick Start

This is a repository for a fine - tuned BART model using the wiki_lingua dataset (English).

📚 Documentation

Purpose

Examine the performance of a fine - tuned model for research purposes.

Observation

• The pre - trained model was trained on the XSum dataset, which is designed to summarize not - too - long documents into one - liner summaries.
• Fine - tuning this model using WikiLingua is appropriate since the summaries for that dataset are also short.
• However, in the end, the model cannot capture much clearer key points. Instead, it mostly extracts the opening sentence.
• Some data pre - processing and the models' hyperparameters also need to be tuned more properly.

📄 License

This project is licensed under the MIT license.