Papers with quatization-aware training

    1 papers
    On-device Structured and Context Partitioned Projection Networks (P19-1)

    Copied to clipboard

    Challenge: A challenge in on-device text classification is to build highly accurate models that fit in small memory footprint and have low latency.
    Approach: They propose an on-device neural network which learns compact projection vectors from raw text using structured and context-dependent partition projections.
    Outcome: The proposed model outperforms baseline models and surpasses RNN, CNN and BiLSTM models on dialog act and intent prediction.

    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