Papers with latent indicator layer

    1 papers
    Recurrent Neural Networks with Mixed Hierarchical Structures and EM Algorithm for Natural Language Processing (2022.lrec-1)

    Copied to clipboard

    Challenge: A variety of hierarchical RNN models have been proposed to incorporate hierarchically-based hierarchic information in modeling languages in the literature.
    Approach: They propose a latent indicator layer approach to identify and learn hierarchical information and develop an EM algorithm to handle the latent indicators layer in training.
    Outcome: The proposed approach outperforms other RNN-based models in document classification 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