dhdhagar / byokg

Zero-shot KGQA method based on curiosity-driven graph exploration. Agarwal et al., "Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA", NAACL 2024.

BYOKG

Bring Your Own KG: Self-Supervised Program Synthesis for Zero-shot KGQA

Camera-ready: https://aclanthology.org/2024.findings-naacl.57
Previous version (ArXiv): https://arxiv.org/abs/2311.07850

Announcements

• 24/04/01: Our source code (and MAIN REPO) is now at amazon-science/BYOKG-NAACL24!
• 24/03/20: We are in the final stages of adding a public repository to the Amazon Science GitHub. Thank you for your patience!
• 24/03/13: Accepted to NAACL 2024: Findings!
• 24/03/11: Accepted to ICLR 2024: LLM Agents Workshop!
• 23/11/16: We are working to make the code available very soon. Please stay tuned!

Citation

@inproceedings{agarwal-etal-2024-bring,
    title = "Bring Your Own {KG}: Self-Supervised Program Synthesis for Zero-Shot {KGQA}",
    author = "Agarwal, Dhruv  and
      Das, Rajarshi  and
      Khosla, Sopan  and
      Gangadharaiah, Rashmi",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-naacl.57",
    pages = "896--919"
}

byokg's Issues

When will the code be released?

Hello, the article is very interesting, I would really like to try the implementation. Is there a timeline/date for the release?