Edit model card

Model Card of lmqg/bart-base-squadshifts-nyt-qg

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

Overview

Usage

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="en", model="lmqg/bart-base-squadshifts-nyt-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", "lmqg/bart-base-squadshifts-nyt-qg")
output = pipe("<hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")

Evaluation

Score Type Dataset
BERTScore 92.86 nyt lmqg/qg_squadshifts
Bleu_1 25.26 nyt lmqg/qg_squadshifts
Bleu_2 16.85 nyt lmqg/qg_squadshifts
Bleu_3 11.93 nyt lmqg/qg_squadshifts
Bleu_4 8.78 nyt lmqg/qg_squadshifts
METEOR 25.13 nyt lmqg/qg_squadshifts
MoverScore 64.99 nyt lmqg/qg_squadshifts
ROUGE_L 24.85 nyt lmqg/qg_squadshifts

Training hyperparameters

The following hyperparameters were used during fine-tuning:

  • dataset_path: lmqg/qg_squadshifts
  • dataset_name: nyt
  • input_types: ['paragraph_answer']
  • output_types: ['question']
  • prefix_types: None
  • model: lmqg/bart-base-squad
  • max_length: 512
  • max_length_output: 32
  • epoch: 4
  • batch: 8
  • lr: 0.0001
  • fp16: False
  • random_seed: 1
  • gradient_accumulation_steps: 16
  • 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",
}
Downloads last month
5

Dataset used to train research-backup/bart-base-squadshifts-nyt-qg

Evaluation results

  • BLEU4 (Question Generation) on lmqg/qg_squadshifts
    self-reported
    8.780
  • ROUGE-L (Question Generation) on lmqg/qg_squadshifts
    self-reported
    24.850
  • METEOR (Question Generation) on lmqg/qg_squadshifts
    self-reported
    25.130
  • BERTScore (Question Generation) on lmqg/qg_squadshifts
    self-reported
    92.860
  • MoverScore (Question Generation) on lmqg/qg_squadshifts
    self-reported
    64.990