mt5-base-itquad-qag / README.md
asahi417's picture
model update
d209811
---
license: cc-by-4.0
metrics:
- bleu4
- meteor
- rouge-l
- bertscore
- moverscore
language: it
datasets:
- lmqg/qag_itquad
pipeline_tag: text2text-generation
tags:
- questions and answers generation
widget:
- text: "Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento."
example_title: "Questions & Answers Generation Example 1"
model-index:
- name: lmqg/mt5-base-itquad-qag
results:
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qag_itquad
type: default
args: default
metrics:
- name: QAAlignedF1Score-BERTScore (Question & Answer Generation)
type: qa_aligned_f1_score_bertscore_question_answer_generation
value: 79.93
- name: QAAlignedRecall-BERTScore (Question & Answer Generation)
type: qa_aligned_recall_bertscore_question_answer_generation
value: 78.87
- name: QAAlignedPrecision-BERTScore (Question & Answer Generation)
type: qa_aligned_precision_bertscore_question_answer_generation
value: 81.06
- name: QAAlignedF1Score-MoverScore (Question & Answer Generation)
type: qa_aligned_f1_score_moverscore_question_answer_generation
value: 53.8
- name: QAAlignedRecall-MoverScore (Question & Answer Generation)
type: qa_aligned_recall_moverscore_question_answer_generation
value: 53.02
- name: QAAlignedPrecision-MoverScore (Question & Answer Generation)
type: qa_aligned_precision_moverscore_question_answer_generation
value: 54.64
---
# Model Card of `lmqg/mt5-base-itquad-qag`
This model is fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) for question & answer pair generation task on the [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
### Overview
- **Language model:** [google/mt5-base](https://huggingface.co/google/mt5-base)
- **Language:** it
- **Training data:** [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) (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="it", model="lmqg/mt5-base-itquad-qag")
# model prediction
question_answer_pairs = model.generate_qa("Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.")
```
- With `transformers`
```python
from transformers import pipeline
pipe = pipeline("text2text-generation", "lmqg/mt5-base-itquad-qag")
output = pipe("Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.")
```
## Evaluation
- ***Metric (Question & Answer Generation)***: [raw metric file](https://huggingface.co/lmqg/mt5-base-itquad-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_itquad.default.json)
| | Score | Type | Dataset |
|:--------------------------------|--------:|:--------|:-------------------------------------------------------------------|
| QAAlignedF1Score (BERTScore) | 79.93 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
| QAAlignedF1Score (MoverScore) | 53.8 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
| QAAlignedPrecision (BERTScore) | 81.06 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
| QAAlignedPrecision (MoverScore) | 54.64 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
| QAAlignedRecall (BERTScore) | 78.87 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
| QAAlignedRecall (MoverScore) | 53.02 | default | [lmqg/qag_itquad](https://huggingface.co/datasets/lmqg/qag_itquad) |
## Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qag_itquad
- dataset_name: default
- input_types: ['paragraph']
- output_types: ['questions_answers']
- prefix_types: None
- model: google/mt5-base
- max_length: 512
- max_length_output: 256
- epoch: 4
- batch: 2
- lr: 0.0005
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 32
- label_smoothing: 0.15
The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mt5-base-itquad-qag/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",
}
```