Home

Awesome

Data Augmentation for Abstractive Query-Focused Multi-Document Summarization (AAAI 2021)

This is the implementation of the paper Data Augmentation for Abstractive Query-Focused Multi-Document Summarization.

Prerequisites

Usage

To train the model:

DATASET=[CNNDM/WIKI] MODEL_TYPE=[hier/he/order/query/heq/heo/hero] bash run_experiments.sh 

To test the model:

DATASET=[CNNDM/WIKI] MODEL_TYPE=[hier/he/order/query/heq/heo/hero] bash test.sh 

Few points to note:

Reference

If you find this code helpful, please consider citing the following paper:

@inproceedings{pasunuru2021data,
    title={Data Augmentation for Abstractive Query-Focused Multi-Document Summarization},
    author={Pasunuru, Ramakanth and Celikyilmaz, Asli and Galley, Michel and Xiong, Chenyan and Zhang, Yizhe and Bansal, Mohit and Gao, Jianfeng},
    booktitle={AAAI},
    year={2021}
}