Model Card of research-backup/t5-large-squadshifts-vanilla-new_wiki-qg

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

Overview

• Language model: t5-large
• Language: en
• Training data: lmqg/qg_squadshifts (new_wiki)
• 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-large-squadshifts-vanilla-new_wiki-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-large-squadshifts-vanilla-new_wiki-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	92.34	new_wiki	lmqg/qg_squadshifts
Bleu_1	27.41	new_wiki	lmqg/qg_squadshifts
Bleu_2	18.35	new_wiki	lmqg/qg_squadshifts
Bleu_3	13.17	new_wiki	lmqg/qg_squadshifts
Bleu_4	9.88	new_wiki	lmqg/qg_squadshifts
METEOR	24.41	new_wiki	lmqg/qg_squadshifts
MoverScore	64.07	new_wiki	lmqg/qg_squadshifts
ROUGE_L	26.95	new_wiki	lmqg/qg_squadshifts

Training hyperparameters

The following hyperparameters were used during fine-tuning:

• dataset_path: lmqg/qg_squadshifts
• dataset_name: new_wiki
• input_types: ['paragraph_answer']
• output_types: ['question']
• prefix_types: ['qg']
• model: t5-large
• max_length: 512
• max_length_output: 32
• epoch: 7
• batch: 16
• lr: 0.0001
• fp16: False
• random_seed: 1
• gradient_accumulation_steps: 4
• 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",
}