[ACIIDS'24] The source code for the paper "CDER: Collaborative Evidence Retrieval for Document-level Relation Extraction"
To install requirements:
pip install requirements.txt
The DocRED dataset used in our model can be downloaded by following the instructions at this link.
You can find the current version of DocRED dataset and all .json
files in the meta
folder from their public repo.
Please note that the dev.json
file available in the current DocRED was modified in August 2021, and the updated version contains 998 documents. We use the original version of dev.json
, which includes 1000 documents.
The expected structure of files is:
|-- CDER
|-- dataset
|-- docred
|-- dev.json
|-- test.json
|-- train_annotated.json
|-- train_distant.json
|-- meta
|-- rel2id.json
|-- rel_info.json
Train CDER on DocRED with the following command:
>> sh scripts/train.sh
After training, testing CDER with the following command:
>> sh scripts/test.sh
Inferring CDER result for integrating to DocRE with the following command:
>> sh scripts/infer.sh
We utilize the GitHub repository of DREEAM model to integrate the extracted evidence results of CDER. To reproduce the results, simply replace DREEAM's evidence output with the evidence results of CDER.
If you make use of this code in your work, please kindly cite the following paper:
@inproceedings{tran2024cder,
title={CDER: Collaborative Evidence Retrieval for Document-Level Relation Extraction},
author={Tran, Khai Phan and Li, Xue},
booktitle={Asian Conference on Intelligent Information and Database Systems},
pages={28--39},
year={2024},
organization={Springer}
}
[1] Wenxuan Zhou, Kevin Huang, Tengyu Ma, and Jing Huang. 2021. Document-level relation extraction with adaptive thresholding and localized context pool- ing. In Proceedings of the AAAI Conference on Arti- ficial Intelligence.
[2] Yiqing Xie, Jiaming Shen, Sha Li, Yuning Mao, and Jiawei Han. 2022. Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion. In Findings of the Association for Computational Linguistics: ACL 2022, pages 257–268, Dublin, Ireland. Association for Computational Linguistics.
[3] Youmi Ma, An Wang, and Naoaki Okazaki. 2023. DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1971–1983, Dubrovnik, Croatia. Association for Computational Linguistics.