Mt5 Cpe Kmutt Thai Sentence Sum

🚀 mt5-cpe-kmutt-thai-sentence-sum

This repository provides a fine - tuned mT5 - base model for Thai sentence summarization, offering an effective solution for summarizing Thai sentences.

🚀 Quick Start

This repository contains the finetuned mT5 - base model for Thai sentence summarization. The architecture of the model is based on the mT5 model and fine - tuned on text - summarization pairs in Thai. Also, this project is a Senior Project of a Computer Engineering Student at King Mongkut’s University of Technology Thonburi.

💻 Usage Examples

Basic Usage

from simpletransformers.t5 import T5Model, T5Args
from torch import cuda

model = T5Model("t5", "thanathorn/mt5-cpe-kmutt-thai-sentence-sum", use_cuda=cuda.is_available())

sentence = "simplify: ถ้าพูดถึงขนมหวานในตำนานที่ชื่นใจที่สุดแล้วละก็ต้องไม่พ้น น้ำแข็งใส แน่เพราะว่าเป็นอะไรที่ชื่นใจสุด"
prediction = model.predict([sentence])
print(prediction[0])

(See the example on Google Colab)

Score

• ROUGE - 1: 61.7805
• ROUGE - 2: 45.9689
• ROUGE - L: 59.3542

Intended uses & limitations

• You can use this model for Thai sentence text summarization.
• Not intended to use with paragraph text.