Show, Write, and Retrieve: Entity-aware Article Generation and Retrieval

ENGINE is an entity-aware model for article generation and retrieval. This repository contains the implementation of our paper. If you find this code useful in your research, please consider citing:

@inproceedings{
    zhang2023show,
    title={Show, Write, and Retrieve: Entity-aware Article Generation and Retrieval},
    author={Zhongping Zhang and Yiwen Gu and Bryan A. Plummer},
    booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
    year={2023},
    url={https://openreview.net/forum?id=SlL3dr0Xa9}
    }

Setting up the environment

The requirements for ENGINE can be installed by

pip install -r requirements.txt

The PyTorch library is installed on CUDA 11.1 platform and the Python version is 3.8.8.

If you have multiple projects to address in a single machine, you might need to create an independent Anaconda environment for ENGINE

conda create -n engine python=3.8.8 &&
conda activate engine && 
pip install -r requirements.txt

Note: If you would like to implement the Clip-based NER in our paper, you will need to set up the CLIP environment by

pip install -r requirements_clip.txt

Datasets:

We performed our experiments on three datasets, GoodNews, VisualNews, and WikiText. We provided the versions we employed for model training and evaluation through the following links. Compared to the original version, we removed broken links and non-English articles.

Datasets	Google Drive Link
GoodNews	GoodNews Link
VisualNews	VisualNews Link
WikiText	WikiText Link

If you would like to obtain the original data, please consider collect the data from their official websites: GoodNews & VisualNews & WikiText

Train & Evaluate the ENGINE model

Train and Evaluate PPL

Run the following script to finetune and evaluate GPT2:

cd code &
sh scripts/run_train_gpt2_goodnews.sh & 
sh scripts/run_eval_gpt2_goodnews.sh

Run the following script to finetune and evaluate ENGINE:

sh scripts/run_train_gpt2_goodnwes_NEboth_wcap.sh & 
sh scripts/run_eval_gpt2_goodnews_NEboth_wcap.sh

Article Generation

Run the following script to generate articles.

sh scripts/EXP1_NEboth_art_gen_goodnews.sh

Experiments on VisualNews

Experiments on VisualNews can be performed by simply modifying the file paths in our goodnews scripts.

Models Weights

Download ENGINE weights in this http URL.