|
|
|
--- |
|
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-08 |
|
- 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](https://huggingface.co/google/mt5-small) for question generation task on the |
|
[lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation). |
|
|
|
|
|
Please cite our paper if you use the model ([https://arxiv.org/abs/2210.03992](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](https://huggingface.co/google/mt5-small) |
|
- **Language:** en |
|
- **Training data:** [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) (default) |
|
- **Online Demo:** [https://autoqg.net/](https://autoqg.net/) |
|
- **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation) |
|
- **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992) |
|
|
|
### Usage |
|
- With [`lmqg`](https://github.com/asahi417/lm-question-generation#lmqg-language-model-for-question-generation-) |
|
```python |
|
|
|
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` |
|
```python |
|
|
|
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](https://huggingface.co/datasets/lmqg/qg_squad) | default | 0.217 | 0.489 | 0.238 | 0.9 | 0.627 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_squad.default.json) | |
|
|
|
|
|
|
|
### Out-of-domain Metrics |
|
|
|
| Dataset | Type | BLEU4 | ROUGE-L | METEOR | BERTScore | MoverScore | Link | |
|
|:--------|:-----|------:|--------:|-------:|----------:|-----------:|-----:| |
|
| [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | default | 0.005 | 0.05 | 0.059 | 0.726 | 0.502 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_itquad.default.json) | |
|
| [lmqg/qg_jaquad](https://huggingface.co/datasets/lmqg/qg_jaquad) | default | 0.0 | 0.061 | 0.005 | 0.661 | 0.465 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_jaquad.default.json) | |
|
| [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) | default | 0.0 | 0.01 | 0.018 | 0.709 | 0.491 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_ruquad.default.json) | |
|
| [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | default | 0.0 | 0.016 | 0.048 | 0.735 | 0.504 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_dequad.default.json) | |
|
| [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) | default | 0.006 | 0.052 | 0.06 | 0.749 | 0.506 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_esquad.default.json) | |
|
| [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | default | 0.017 | 0.158 | 0.082 | 0.729 | 0.51 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_frquad.default.json) | |
|
| [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) | default | 0.0 | 0.001 | 0.007 | 0.663 | 0.459 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_koquad.default.json) | |
|
|
|
|
|
## 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](https://huggingface.co/lmqg/mt5-small-squad/raw/main/trainer_config.json). |
|
|
|
## 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", |
|
} |
|
|
|
``` |
|
|
