Model Card of lmqg/bart-base-squad-qg-ae
This model is fine-tuned version of facebook/bart-base for question generation and answer extraction jointly on the lmqg/qg_squad (dataset_name: default) via lmqg
.
Overview
- Language model: facebook/bart-base
- Language: en
- Training data: lmqg/qg_squad (default)
- 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="lmqg/bart-base-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/bart-base-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.")
Evaluation
- Metric (Question Generation): raw metric file
Score | Type | Dataset | |
---|---|---|---|
BERTScore | 90.65 | default | lmqg/qg_squad |
Bleu_1 | 56.53 | default | lmqg/qg_squad |
Bleu_2 | 40.97 | default | lmqg/qg_squad |
Bleu_3 | 31.71 | default | lmqg/qg_squad |
Bleu_4 | 25.07 | default | lmqg/qg_squad |
METEOR | 25.87 | default | lmqg/qg_squad |
MoverScore | 64.49 | default | lmqg/qg_squad |
ROUGE_L | 52.79 | default | lmqg/qg_squad |
- Metric (Question & Answer Generation): raw metric file
Score | Type | Dataset | |
---|---|---|---|
QAAlignedF1Score (BERTScore) | 93.45 | default | lmqg/qg_squad |
QAAlignedF1Score (MoverScore) | 64.47 | default | lmqg/qg_squad |
QAAlignedPrecision (BERTScore) | 92.78 | default | lmqg/qg_squad |
QAAlignedPrecision (MoverScore) | 63.55 | default | lmqg/qg_squad |
QAAlignedRecall (BERTScore) | 94.14 | default | lmqg/qg_squad |
QAAlignedRecall (MoverScore) | 65.49 | default | lmqg/qg_squad |
- Metric (Answer Extraction): raw metric file
Score | Type | Dataset | |
---|---|---|---|
AnswerExactMatch | 57.58 | default | lmqg/qg_squad |
AnswerF1Score | 69.14 | default | lmqg/qg_squad |
BERTScore | 91.86 | default | lmqg/qg_squad |
Bleu_1 | 65.9 | default | lmqg/qg_squad |
Bleu_2 | 63.06 | default | lmqg/qg_squad |
Bleu_3 | 60.47 | default | lmqg/qg_squad |
Bleu_4 | 58.31 | default | lmqg/qg_squad |
METEOR | 41.39 | default | lmqg/qg_squad |
MoverScore | 81.95 | default | lmqg/qg_squad |
ROUGE_L | 68.38 | default | lmqg/qg_squad |
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: facebook/bart-base
- max_length: 512
- max_length_output: 32
- epoch: 3
- batch: 32
- lr: 5e-05
- 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",
}