Superpal

🚀 SuperPAL model

Summary-Source Proposition-level Alignment: Task, Datasets and Supervised Baseline

This project focuses on the task of summary - source proposition - level alignment, providing relevant datasets and a supervised baseline.

🚀 Quick Start

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
  
tokenizer = AutoTokenizer.from_pretrained("biu-nlp/superpal")

model = AutoModelForSequenceClassification.from_pretrained("biu-nlp/superpal")

📚 Documentation

The widget text is as follows:

widget:
- text: "Prime Minister Hun Sen insisted that talks take place in Cambodia. </s><s> Cambodian leader Hun Sen rejected opposition parties' demands for talks outside the country."

The paper is written by Ori Ernst, Ori Shapira, Ramakanth Pasunuru, Michael Lepioshkin, Jacob Goldberger, Mohit Bansal, Ido Dagan in 2021. You can access the PDF here.

The original repo is here.

📄 License

If you find our work useful, please cite the paper as:

@inproceedings{ernst-etal-2021-summary,
  title = "Summary-Source Proposition-level Alignment: Task, Datasets and Supervised Baseline",
  author = "Ernst, Ori  and Shapira, Ori  and Pasunuru, Ramakanth  and Lepioshkin, Michael  and Goldberger, Jacob  and Bansal, Mohit  and Dagan, Ido", 
  booktitle = "Proceedings of the 25th Conference on Computational Natural Language Learning", 
  month = nov, 
  year = "2021", 
  publisher = "Association for Computational Linguistics", 
  url = "https://aclanthology.org/2021.conll-1.25", 
  pages = "310--322"
}