Mt5 Small Jaquad Qg

🚀 Model Card of lmqg/mt5-small-jaquad-qg

This model is a fine - tuned version of google/mt5-small for the question generation task on the lmqg/qg_jaquad (dataset_name: default) via lmqg. It aims to generate high - quality questions based on given text, providing a useful tool for natural language processing applications.

✨ Features

• Language Model: Utilizes google/mt5-small as the base language model.
• Language Support: Specialized for the Japanese language (ja).
• Training Data: Trained on the lmqg/qg_jaquad dataset.
• Online Demo: An online demonstration is available at https://autoqg.net/.
• Repository: The source code and related information can be found in the GitHub repository.
• Paper: Refer to the research paper at https://arxiv.org/abs/2210.03992 for more details.

📦 Installation

There is no specific installation steps provided in the original README. If you want to use this model, you may need to install relevant libraries such as lmqg or transformers according to the usage examples.

💻 Usage Examples

Basic Usage

With lmqg

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="ja", model="lmqg/mt5-small-jaquad-qg")

# model prediction
questions = model.generate_q(list_context="フェルメールの作品では、17世紀のオランダの画家、ヨハネス・フェルメールの作品について記述する。フェルメールの作品は、疑問作も含め30数点しか現存しない。現存作品はすべて油彩画で、版画、下絵、素描などは残っていない。", list_answer="30数点")

With transformers

from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/mt5-small-jaquad-qg")
output = pipe("ゾフィーは貴族出身ではあったが王族出身ではなく、ハプスブルク家の皇位継承者であるフランツ・フェルディナントとの結婚は貴賤結婚となった。皇帝フランツ・ヨーゼフは、2人の間に生まれた子孫が皇位を継がないことを条件として結婚を承認していた。視察が予定されている<hl>6月28日<hl>は2人の14回目の結婚記念日であった。")

📚 Documentation

Evaluation

Metric (Question Generation)

The raw metric file can be found here.

Metric (Question & Answer Generation, Reference Answer)

Each question is generated from the gold answer. The raw metric file is available here.

Metric (Question & Answer Generation, Pipeline Approach)

Each question is generated on the answer generated by lmqg/mt5-small-jaquad-ae. The raw metric file can be accessed here.

Training hyperparameters

The following hyperparameters were used during fine - tuning:

• dataset_path: lmqg/qg_jaquad
• dataset_name: default
• input_types: ['paragraph_answer']
• output_types: ['question']
• prefix_types: None
• model: google/mt5-small
• max_length: 512
• max_length_output: 32
• epoch: 21
• batch: 64
• lr: 0.0005
• fp16: False
• random_seed: 1
• gradient_accumulation_steps: 1
• label_smoothing: 0.0

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

🔧 Technical Details

The model is fine - tuned from the base model google/mt5-small on the lmqg/qg_jaquad dataset. The fine - tuning process involves adjusting the model's parameters to optimize the question generation task. The hyperparameters are carefully selected to balance the training efficiency and the performance of the model.

📄 License

The model is licensed under cc-by-4.0.

📚 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",
}