asahi417's picture
commit files to HF hub
84e523f
---
license: cc-by-4.0
metrics:
- bleu4
- meteor
- rouge-l
- bertscore
- moverscore
language: es
datasets:
- lmqg/qg_esquad
pipeline_tag: text2text-generation
tags:
- question generation
widget:
- text: "del <hl> Ministerio de Desarrollo Urbano <hl> , Gobierno de la India."
example_title: "Question Generation Example 1"
- text: "a <hl> noviembre <hl> , que es también la estación lluviosa."
example_title: "Question Generation Example 2"
- text: "como <hl> el gobierno de Abbott <hl> que asumió el cargo el 18 de septiembre de 2013."
example_title: "Question Generation Example 3"
model-index:
- name: vocabtrimmer/mt5-small-trimmed-es-5000-esquad-qg
results:
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_esquad
type: default
args: default
metrics:
- name: BLEU4 (Question Generation)
type: bleu4_question_generation
value: 9.41
- name: ROUGE-L (Question Generation)
type: rouge_l_question_generation
value: 23.51
- name: METEOR (Question Generation)
type: meteor_question_generation
value: 21.88
- name: BERTScore (Question Generation)
type: bertscore_question_generation
value: 84.07
- name: MoverScore (Question Generation)
type: moverscore_question_generation
value: 58.84
---
# Model Card of `vocabtrimmer/mt5-small-trimmed-es-5000-esquad-qg`
This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-es-5000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-es-5000) for question generation task on the [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
### Overview
- **Language model:** [vocabtrimmer/mt5-small-trimmed-es-5000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-es-5000)
- **Language:** es
- **Training data:** [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) (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="es", model="vocabtrimmer/mt5-small-trimmed-es-5000-esquad-qg")
# model prediction
questions = model.generate_q(list_context="a noviembre , que es también la estación lluviosa.", list_answer="noviembre")
```
- With `transformers`
```python
from transformers import pipeline
pipe = pipeline("text2text-generation", "vocabtrimmer/mt5-small-trimmed-es-5000-esquad-qg")
output = pipe("del <hl> Ministerio de Desarrollo Urbano <hl> , Gobierno de la India.")
```
## Evaluation
- ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-es-5000-esquad-qg/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_esquad.default.json)
| | Score | Type | Dataset |
|:-----------|--------:|:--------|:-----------------------------------------------------------------|
| BERTScore | 84.07 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
| Bleu_1 | 25.67 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
| Bleu_2 | 17.4 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
| Bleu_3 | 12.59 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
| Bleu_4 | 9.41 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
| METEOR | 21.88 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
| MoverScore | 58.84 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
| ROUGE_L | 23.51 | default | [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) |
## Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qg_esquad
- dataset_name: default
- input_types: paragraph_answer
- output_types: question
- prefix_types: None
- model: vocabtrimmer/mt5-small-trimmed-es-5000
- max_length: 512
- max_length_output: 32
- epoch: 12
- batch: 16
- lr: 0.001
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 4
- label_smoothing: 0.15
The full configuration can be found at [fine-tuning config file](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-es-5000-esquad-qg/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",
}
```