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
Co phrase search for related documents, hyperlinks ordered by date