Selected article for: "loss function and propose model"

Author: Teslyuk, Anton
Title: The Concept of System for Automated Scientific Literature Reviews Generation
  • Cord-id: qd3xej8l
  • Document date: 2020_5_22
  • ID: qd3xej8l
    Snippet: We present a concept of system which is aimed to create a literature review of scientific articles having a small sketch of statements as the input. Key elements of the system include transformer-based BERT encoder, deep LSTM decoder and a loss function which combines auto-encoder loss and forces generated summaries to be in the input text domain. We propose to use PMC open access subset for model learning.
    Document: We present a concept of system which is aimed to create a literature review of scientific articles having a small sketch of statements as the input. Key elements of the system include transformer-based BERT encoder, deep LSTM decoder and a loss function which combines auto-encoder loss and forces generated summaries to be in the input text domain. We propose to use PMC open access subset for model learning.

    Search related documents:
    Co phrase search for related documents
    • Try single phrases listed below for: 1