Papers with hit-at-one (

    1 papers
    Leveraging WordNet Paths for Neural Hypernym Prediction (2020.coling-main)

    Copied to clipboard

    Challenge: Existing work on lexical relations based on distributed representations has differed widely.
    Approach: They propose a model that generates taxonomy paths for hypernym prediction using WordNet sequences.
    Outcome: The hypo2path model outperforms the best model by 4.11 points in hit-at-one (H@1) The proposed model outpersforms previous models by a factor of 0.9.

    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