T5 Small Squad Qg Ae

🚀 Model Card of lmqg/t5-small-squad-qg-ae

This model is a fine - tuned version of t5 - small for joint question generation and answer extraction. It is trained on the lmqg/qg_squad (dataset_name: default) via lmqg.

🚀 Quick Start

Overview

✨ Features

This model supports both question generation and answer extraction tasks, which can be useful in various natural language processing applications such as information retrieval and question - answering systems.

📦 Installation

The model can be used with the following libraries. You need to install the corresponding libraries first. For example, you can use pip to install lmqg and transformers:

pip install lmqg transformers

💻 Usage Examples

Basic Usage

• With lmqg

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="en", model="lmqg/t5-small-squad-qg-ae")

# model prediction
question_answer_pairs = model.generate_qa("William Turner was an English painter who specialised in watercolour landscapes")

• With transformers

from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/t5-small-squad-qg-ae")

# answer extraction
answer = pipe("generate question: <hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")

# question generation
question = pipe("extract answers: <hl> Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records. <hl> Her performance in the film received praise from critics, and she garnered several nominations for her portrayal of James, including a Satellite Award nomination for Best Supporting Actress, and a NAACP Image Award nomination for Outstanding Supporting Actress.")

📚 Documentation

Evaluation

• Metric (Question Generation): raw metric file

• Metric (Question & Answer Generation): raw metric file

• Metric (Answer Extraction): raw metric file

Training hyperparameters

The following hyperparameters were used during fine - tuning:

• dataset_path: lmqg/qg_squad
• dataset_name: default
• input_types: ['paragraph_answer', 'paragraph_sentence']
• output_types: ['question', 'answer']
• prefix_types: ['qg', 'ae']
• model: t5 - small
• max_length: 512
• max_length_output: 32
• epoch: 7
• batch: 64
• lr: 0.0001
• fp16: False
• random_seed: 1
• gradient_accumulation_steps: 1
• label_smoothing: 0.15

The full configuration can be found at fine - tuning config file.

🔧 Technical Details

The model is based on the t5 - small architecture and is fine - tuned on the lmqg/qg_squad dataset. The fine - tuning process involves optimizing the model for both question generation and answer extraction tasks using specific hyperparameters.

📄 License

This model is released under the CC - BY - 4.0 license.

Citation

@inproceedings{ushio-etal-2022-generative,
    title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
    author = "Ushio, Asahi  and
        Alva-Manchego, Fernando  and
        Camacho-Collados, Jose",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, U.A.E.",
    publisher = "Association for Computational Linguistics",
}