metadata
license: cc-by-4.0
metrics:
- bleu4
- meteor
- rouge-l
- bertscore
- moverscore
language: en
datasets:
- lmqg/qg_squad
pipeline_tag: text2text-generation
tags:
- question generation
widget:
- text: >-
<hl> Beyonce <hl> further expanded her acting career, starring as blues
singer Etta James in the 2008 musical biopic, Cadillac Records.
example_title: Question Generation Example 1
- text: >-
Beyonce further expanded her acting career, starring as blues singer <hl>
Etta James <hl> in the 2008 musical biopic, Cadillac Records.
example_title: Question Generation Example 2
- text: >-
Beyonce further expanded her acting career, starring as blues singer Etta
James in the 2008 musical biopic, <hl> Cadillac Records <hl> .
example_title: Question Generation Example 3
model-index:
- name: lmqg/mt5-small-squad
results:
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_squad
type: default
args: default
metrics:
- name: BLEU4
type: bleu4
value: 0.21650505934418166
- name: ROUGE-L
type: rouge-l
value: 0.489464328982525
- name: METEOR
type: meteor
value: 0.23833897056449205
- name: BERTScore
type: bertscore
value: 0.9000723844397448
- name: MoverScore
type: moverscore
value: 0.62747065964027
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_itquad
type: default
args: default
metrics:
- name: BLEU4
type: bleu4
value: 0.005438910607183992
- name: ROUGE-L
type: rouge-l
value: 0.05010570221421983
- name: METEOR
type: meteor
value: 0.05890828426558759
- name: BERTScore
type: bertscore
value: 0.7260160158030385
- name: MoverScore
type: moverscore
value: 0.5023119088393686
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_jaquad
type: default
args: default
metrics:
- name: BLEU4
type: bleu4
value: 4.4114578660129224e-8
- name: ROUGE-L
type: rouge-l
value: 0.06084267343290677
- name: METEOR
type: meteor
value: 0.005149267426183168
- name: BERTScore
type: bertscore
value: 0.6608093198082075
- name: MoverScore
type: moverscore
value: 0.46526108687696893
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_ruquad
type: default
args: default
metrics:
- name: BLEU4
type: bleu4
value: 4.229109829516021e-12
- name: ROUGE-L
type: rouge-l
value: 0.009881091250723615
- name: METEOR
type: meteor
value: 0.017796529053904556
- name: BERTScore
type: bertscore
value: 0.7089446693028568
- name: MoverScore
type: moverscore
value: 0.49098728551715626
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_dequad
type: default
args: default
metrics:
- name: BLEU4
type: bleu4
value: 9.242783121165897e-12
- name: ROUGE-L
type: rouge-l
value: 0.01556150764938016
- name: METEOR
type: meteor
value: 0.04809700451843158
- name: BERTScore
type: bertscore
value: 0.7353078946893743
- name: MoverScore
type: moverscore
value: 0.5036973829954939
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_esquad
type: default
args: default
metrics:
- name: BLEU4
type: bleu4
value: 0.0059191752064594125
- name: ROUGE-L
type: rouge-l
value: 0.05208940592236566
- name: METEOR
type: meteor
value: 0.06021086135293597
- name: BERTScore
type: bertscore
value: 0.7494422899749911
- name: MoverScore
type: moverscore
value: 0.5062373132800192
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_frquad
type: default
args: default
metrics:
- name: BLEU4
type: bleu4
value: 0.0171464639522496
- name: ROUGE-L
type: rouge-l
value: 0.1583673053928925
- name: METEOR
type: meteor
value: 0.08244973027319356
- name: BERTScore
type: bertscore
value: 0.7291012183458674
- name: MoverScore
type: moverscore
value: 0.509610854598101
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_koquad
type: default
args: default
metrics:
- name: BLEU4
type: bleu4
value: 1.4750917137316939e-12
- name: ROUGE-L
type: rouge-l
value: 0.0006466767450454226
- name: METEOR
type: meteor
value: 0.007310046912436679
- name: BERTScore
type: bertscore
value: 0.6634288882769679
- name: MoverScore
type: moverscore
value: 0.4586124640357038
Model Card of lmqg/mt5-small-squad
This model is fine-tuned version of google/mt5-small for question generation task on the
lmqg/qg_squad (dataset_name: default) via lmqg.
Please cite our paper if you use the model (https://arxiv.org/abs/2210.03992).
@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",
}
Overview
- Language model: google/mt5-small
- 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/mt5-small-squad')
# model prediction
question = 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
# initialize model
pipe = pipeline("text2text-generation", 'lmqg/mt5-small-squad')
# question generation
question = pipe('<hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.')
Evaluation Metrics
Metrics
| Dataset | Type | BLEU4 | ROUGE-L | METEOR | BERTScore | MoverScore | Link |
|---|---|---|---|---|---|---|---|
| lmqg/qg_squad | default | 0.217 | 0.489 | 0.238 | 0.9 | 0.627 | link |
Out-of-domain Metrics
| Dataset | Type | BLEU4 | ROUGE-L | METEOR | BERTScore | MoverScore | Link |
|---|---|---|---|---|---|---|---|
| lmqg/qg_itquad | default | 0.005 | 0.05 | 0.059 | 0.726 | 0.502 | link |
| lmqg/qg_jaquad | default | 0.0 | 0.061 | 0.005 | 0.661 | 0.465 | link |
| lmqg/qg_ruquad | default | 0.0 | 0.01 | 0.018 | 0.709 | 0.491 | link |
| lmqg/qg_dequad | default | 0.0 | 0.016 | 0.048 | 0.735 | 0.504 | link |
| lmqg/qg_esquad | default | 0.006 | 0.052 | 0.06 | 0.749 | 0.506 | link |
| lmqg/qg_frquad | default | 0.017 | 0.158 | 0.082 | 0.729 | 0.51 | link |
| lmqg/qg_koquad | default | 0.0 | 0.001 | 0.007 | 0.663 | 0.459 | link |
Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qg_squad
- 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: 15
- batch: 64
- lr: 0.0005
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 1
- 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",
}