Model Card of research-backup/t5-base-squadshifts-vanilla-amazon-qg

This model is fine-tuned version of t5-base for question generation task on the lmqg/qg_squadshifts (dataset_name: amazon) via lmqg.

Overview

• Language model: t5-base
• Language: en
• Training data: lmqg/qg_squadshifts (amazon)
• Online Demo: https://autoqg.net/
• Repository: https://github.com/asahi417/lm-question-generation
• Paper: https://arxiv.org/abs/2210.03992

Usage

• With lmqg

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="en", model="research-backup/t5-base-squadshifts-vanilla-amazon-qg")

# model prediction
questions = model.generate_q(list_context="William Turner was an English painter who specialised in watercolour landscapes", list_answer="William Turner")

• With transformers

from transformers import pipeline

pipe = pipeline("text2text-generation", "research-backup/t5-base-squadshifts-vanilla-amazon-qg")
output = pipe("generate question: <hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")

Evaluation

• Metric (Question Generation): raw metric file

	Score	Type	Dataset
BERTScore	91.41	amazon	lmqg/qg_squadshifts
Bleu_1	25	amazon	lmqg/qg_squadshifts
Bleu_2	16.21	amazon	lmqg/qg_squadshifts
Bleu_3	10.74	amazon	lmqg/qg_squadshifts
Bleu_4	7.42	amazon	lmqg/qg_squadshifts
METEOR	20.54	amazon	lmqg/qg_squadshifts
MoverScore	61.26	amazon	lmqg/qg_squadshifts
ROUGE_L	25.43	amazon	lmqg/qg_squadshifts

Training hyperparameters

The following hyperparameters were used during fine-tuning:

• dataset_path: lmqg/qg_squadshifts
• dataset_name: amazon
• input_types: ['paragraph_answer']
• output_types: ['question']
• prefix_types: ['qg']
• model: t5-base
• max_length: 512
• max_length_output: 32
• epoch: 7
• batch: 8
• lr: 0.0001
• fp16: False
• random_seed: 1
• gradient_accumulation_steps: 8
• label_smoothing: 0.15

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

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",
}