Papers by Tauhidur Rahman

    1 papers
    Start Simple: Progressive Difficulty Multitask Learning (2024.naacl-srw)

    Copied to clipboard

    Challenge: a novel neural network training strategy that trains neural networks using subtasks of progressive difficulty is proposed . this strategy could help us understand how neural networks learn, authors say .
    Approach: They propose a multitask learning strategy that employs progressive difficulty subtasks to train neural networks.
    Outcome: The proposed strategy can improve model performance across a range of NLP tasks and data sets.

    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