Papers by Abhinav Kommula

    1 papers
    OpenPI2.0: An Improved Dataset for Entity Tracking in Texts (2024.eacl-long)

    Copied to clipboard

    Challenge: Recent work shows that explicit modeling entity states benefits LMs in procedural tasks.
    Approach: They propose a dataset where entities and attributes are fully canonicalized and additional entity salience annotations are added.
    Outcome: The proposed dataset outperforms existing models on question answering and classical planning tasks.

    What is GenGO?

    GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

    Information

    About
    Limitations