Thesis etd-01292018-145927 |
Link copiato negli appunti
Thesis type
Tesi di laurea magistrale
URN
etd-01292018-145927
Thesis title
Learning Tree Transductions by Deep Neural Networks
Department
INFORMATICA
Course of study
INFORMATICA
Supervisors
.
relatore Dott. Bacciu, Davide
Keywords
- deep learning
- lstm
- neural network
- transduction
- tree
- treelstm
Graduation session start date
02/03/2018
Availability
Full
Abstract (Inglese)
Abstract (Italiano)
The thesis describes a deep neural network for learning tree-to-tree transductions. The proposed approach uses TreeLSTM models to encode the input as a fixed size vector, followed by a decoding phase that generates the output. Experiments are provided to show how the model can learn structure-to-structure and structure-to-element transductions.
File
| Nome file | Dimensione |
|---|---|
| Tesi_Final.pdf | 1.71 Mb |
Contatta l’autore |
|