T5 Base Table Question Generator

🚀 T5-base Table Question Generation Model

A finetuned t5-base model for generating questions from tables using the WikiSQL dataset.

🚀 Quick Start

This model is finetuned based on t5-base. It uses the WikiSQL dataset and is trained to take the SQL, answer, and column header of a table as input to generate questions. For more details, refer to our T3QA paper from EMNLP 2021.

✨ Features

• Model Type: t5-base
• Language: English
• Task: Table Question Generation
• Training Data: WikiSQL

📚 Documentation

Intended Use

One can use this model to generate questions given a table.

Limitations

Biases associated with pre - training of T5 and the WikiSQL dataset may be present.

Usage

One can use this model directly in the PrimeQA framework as shown in this example notebook.

📄 License

This project is licensed under the Apache-2.0 license.

📚 Citation

@inproceedings{chemmengath2021topic,
  title={Topic Transferable Table Question Answering},
  author={Chemmengath, Saneem and Kumar, Vishwajeet and
          Bharadwaj, Samarth and Sen, Jaydeep and
          Canim, Mustafa and Chakrabarti, Soumen and
          Gliozzo, Alfio and Sankaranarayanan, Karthik},
  booktitle={Proceedings of the 2021 Conference on 
      Empirical Methods in Natural Language Processing},
  pages={4159--4172},
  year={2021}
}