T5 Large Ssm

🚀 Google's T5 for Closed Book Question Answering

This project utilizes Google's T5 for Closed Book Question Answering. It pre - trains the model using T5's denoising objective on C4 and further pre - trains it with REALM's salient span masking objective on Wikipedia.

🚀 Quick Start

This model should be fine - tuned on a question answering downstream task before it can be used for closed book question answering.

✨ Features

• The model was pre - trained on C4 using T5's denoising objective.
• Subsequently, it was additionally pre - trained on Wikipedia with REALM's salient span masking objective.
• It can implicitly store and retrieve knowledge using natural language queries.

📚 Documentation

Abstract

It has recently been observed that neural language models trained on unstructured text can implicitly store and retrieve knowledge using natural language queries. In this short paper, we measure the practical utility of this approach by fine - tuning pre - trained models to answer questions without access to any external context or knowledge. We show that this approach scales with model size and performs competitively with open - domain systems that explicitly retrieve answers from an external knowledge source when answering questions. To facilitate reproducibility and future work, we release our code and trained models at https://goo.gle/t5 - cbqa.

Other Information

• Other Community Checkpoints: here
• Paper: How Much Knowledge Can You Pack Into the Parameters of a Language Model?
• Authors: Adam Roberts, Colin Raffel, Noam Shazeer

📄 License

This project is licensed under the Apache - 2.0 license.

⚠️ Important Note

This model should be fine - tuned on a question answering downstream task before it is useable for closed book question answering.