idt5-qa-qg / README.md
muchad's picture
Update README.md
7420269
---
language: id
datasets:
- SQuADv2.0
tags:
- question-generation
- multitask-model
- idt5
widget:
- text: "generate question: <hl> Dua orang <hl> pengembara berjalan di sepanjang jalan yang berdebu dan tandus di hari yang sangat panas. Tidak lama kemudian, mereka menemukan sebuah pohon besar. </s>"
- text: "question: Siapa pemimpin Kerajaan Tarumanegara? context: Raja Purnawarman mulai memerintah Kerajaan Tarumanegara pada tahun 395 M. </s>"
license: apache-2.0
---
# idT5 for Indonesian Question Generation and Question Answering
[idT5](https://huggingface.co/muchad/idt5-base) (Indonesian version of [mT5](https://huggingface.co/google/mt5-base)) is fine-tuned on 30% of [translated SQuAD v2.0](https://github.com/Wikidepia/indonesian_datasets/tree/master/question-answering/squad) for **Question Generation** and **Question Answering** tasks.
## Live Demo
* **Question Generation:** [ai.muchad.com/qg](https://ai.muchad.com/qg/)
* **Question Answering:** [t.me/caritahubot](https://t.me/caritahubot)
## Requirements
```
!pip install transformers==4.4.2
!pip install sentencepiece==0.1.95
!git clone https://github.com/muchad/qaqg.git
%cd qaqg/
```
## Usage ๐Ÿš€
#### Question Generation
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/muchad/qaqg/blob/main/idT5_Question_Generation.ipynb)
```
from pipeline_qg import pipeline #pipeline_qg.py script in the cloned repo
qg = pipeline()
#sample
qg("Raja Purnawarman mulai memerintah Kerajaan Tarumanegara pada tahun 395 M.")
#output
=> [{'answer': 'Raja Purnawarman','question': 'Siapa yang memerintah Kerajaan Tarumanegara?'}, {'answer': '395 M','question': 'Kapan Raja Purnawarman memerintah Kerajaan Tarumanegara?'}]
```
#### Question Answering
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/muchad/qaqg/blob/main/idT5_Question_Answering.ipynb)
```
from pipeline_qa import pipeline #pipeline_qa.py script in the cloned repo
qa = pipeline()
#sample
qa({"context":"Raja Purnawarman mulai memerintah Kerajaan Tarumanegara pada tahun 395 M.","question":"Siapa pemimpin Kerajaan Tarumanegara?"})
#output
=> Raja Purnawarman
```
#### Citation
Paper: [idT5: Indonesian Version of Multilingual T5 Transformer](https://arxiv.org/abs/2302.00856)
```
@misc{https://doi.org/10.48550/arxiv.2302.00856,
doi = {10.48550/ARXIV.2302.00856},
url = {https://arxiv.org/abs/2302.00856},
author = {Fuadi, Mukhlish and Wibawa, Adhi Dharma and Sumpeno, Surya},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences, I.2.7},
title = {idT5: Indonesian Version of Multilingual T5 Transformer},
publisher = {arXiv},
year = {2023}
}
```