The Concept of System for Automated Scientific Literature Reviews Generation
| Autor: | Anton B. Teslyuk |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0303 health sciences
Information retrieval Computer science Scientific literature 010501 environmental sciences 01 natural sciences Autoencoder Automatic summarization Sketch 03 medical and health sciences Encoder 030304 developmental biology 0105 earth and related environmental sciences Transformer (machine learning model) |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783030504199 ICCS (3) |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|