MQDD Pretrained

🚀 MQDD - Multimodal Question Duplicity Detection

This repository offers a pre - trained model for multimodal question duplicity detection in the software engineering domain, facilitating more efficient question - related tasks.

🚀 Quick Start

This repository publishes a pre - trained model for the paper MQDD – Pre-training of Multimodal Question Duplicity Detection for Software Engineering Domain. For more details, refer to the paper.

The Stack Overflow Datasets (SOD) and Stack Overflow Duplicity Dataset (SODD) presented in the paper can be obtained from our Stack Overflow Dataset repository.

To get the fine - tuned model, visit [UWB - AIR/MQDD - duplicate](https://huggingface.co/UWB - AIR/MQDD - duplicates).

The MQDD model, based on a Longformer architecture, is pre - trained on 218.5M training examples. The model was trained using the MLM training objective, along with our novel Same Post (SP) and Question Answer (QA) learning objectives, specifically targeting the duplicate detection task.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("UWB-AIR/MQDD-pretrained")
model = AutoModel.from_pretrained("UWB-AIR/MQDD-pretrained")

📄 License

This work is licensed under a Creative Commons Attribution - NonCommercial - ShareAlike 4.0 International License. http://creativecommons.org/licenses/by - nc - sa/4.0/

📚 Documentation

How should I cite the MQDD?

For now, please cite the Arxiv paper:

@misc{https://doi.org/10.48550/arxiv.2203.14093,
  doi = {10.48550/ARXIV.2203.14093},
  url = {https://arxiv.org/abs/2203.14093},
  author = {Pašek, Jan and Sido, Jakub and Konopík, Miloslav and Pražák, Ondřej},
  title = {MQDD -- Pre-training of Multimodal Question Duplicity Detection for Software Engineering Domain},
  publisher = {arXiv},
  year = {2022},
  copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}