ashokurlana / LTRC-MuP-COLING-2022

This repository shows the implementation of the Multi-perspective Scientific Documet Summarization. The code and data are available in the repo.

Multi-perspective Scientific Document Summarization Shared Task

We use a modified fork of huggingface transformers for our experiments.

Creating environment

If you are using conda use the following command:

conda env create -f environment.yml

Otherwise, for creating python environment use:

pip install requirements.txt

Data format:

• We used the dataset released in the MuP2022 shared task

• Make sure to create `train, dev, test' csv files with column names "text" and "summary"

Run the script

To fine-tune any huggingface model you can use the run.sh script. When running the different models described in the paper, ensure you pass the appropriate arguments.

sh run.sh

Trained Models

You can download the BART-large-cnn fine-tuned on MuP2022 dataset

MuP BART