ESRA: Explainable Scientific Research Assistant

ESRA is an explainable literature discovery platform which utilizes a knowledge graph and modern Natural Language Processing (NLP) techniques. Our paper has been accepted in the system demonstration track at ACL-IJCNLP 2021.

Project Repositories

1. ESRA-Extractor

Information extraction from scientific documents

2. ESRA-Graph-database

Scientific knowledge graph construction from the extracted information

3. ESRA-Frontend

Web application frontend developed with React

4. ESRA-Backend

Web application backend containing ranking with elasticsearch

Citing

If you find this project helpful, feel free to cite our publication.

@inproceedings{hongwimol-etal-2021-esra,
    title = "{ESRA}: Explainable Scientific Research Assistant",
    author = "Hongwimol, Pollawat  and
      Kehasukcharoen, Peeranuth  and
      Laohawarutchai, Pasit  and
      Lertvittayakumjorn, Piyawat  and
      Ng, Aik Beng  and
      Lai, Zhangsheng  and
      Liu, Timothy  and
      Vateekul, Peerapon",
    booktitle = "Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
      url = "https://aclanthology.org/2021.acl-demo.14",
    pages = "114--121",   
}

Acknowledgements

The ESRA project is in a collaboration between the Department of Computer Engineering, Chulalongkorn University and NVIDIA AI Technology Center (NVAITC), Singapore.