qaqg

Indonesian Question Answering and Question Generation using Transformers

https://github.com/muchad/qaqg

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org, ieee.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (6.1%) to scientific vocabulary

Keywords

dataset deep-learning idt5 natural-language-generation natural-language-processing nlp question-answering question-generation t5 transformer
Last synced: 6 months ago · JSON representation ·

Repository

Indonesian Question Answering and Question Generation using Transformers

Basic Info
  • Host: GitHub
  • Owner: muchad
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 12.8 MB
Statistics
  • Stars: 9
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
dataset deep-learning idt5 natural-language-generation natural-language-processing nlp question-answering question-generation t5 transformer
Created over 3 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

Indonesian Question Answering and Question Generation using 🤗Transformers

idT5 for Question Generation and Question Answering

idT5 (Indonesian version of mT5) is fine-tuned on 30% of translated SQuAD v2.0 for Question Generation and Question Answering tasks.

idT5 Paper: 1. IEEE 2. arXiv

result

Live Demo

Question Generation: ai.muchad.com/qg
Question Answering: 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 🚀

Question Generation

Open In Colab

``` from pipelineqg import pipeline #pipelineqg.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

``` from pipelineqa import pipeline #pipelineqa.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 ```

Owner

  • Name: muchad
  • Login: muchad
  • Kind: user
  • Location: Malang Indonesia
  • Company: duatiga IT Solutions

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Fuadi"
  given-names: "Mukhlish"
  orcid: "https://orcid.org/0000-0002-7595-7646"
title: "Indonesian Question Answering and Question Generation using Transformers"
version: 1.0.0
date-released: 2022-09-27
url: "https://github.com/muchad/qaqg"

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2