![Ιδρυματικό Αποθετήριο [SANDBOX]](images/dias.logo.png "Ιδρυματικό Αποθετήριο [SANDBOX]"){kind=logo}
Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
Πολυτεχνείο Κρήτης
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/6AFB8526-0978-45A1-8539-8DBDB9C25C69 | - |
| Αναγνωριστικό | https://doi.org/10.21437/Interspeech.2017-1075 | - |
| Γλώσσα | en | - |
| Μέγεθος | 5 pages | en |
| Τίτλος | ClockWork-RNN based architectures for slot filling | en |
| Δημιουργός | Georgiadou Despoina | en |
| Δημιουργός | Γεωργιαδου Δεσποινα | el |
| Δημιουργός | Diakoloukas Vasilis | en |
| Δημιουργός | Διακολουκας Βασιλeioς | el |
| Δημιουργός | Tsiaras Vasileios | en |
| Δημιουργός | Τσιαρας Βασιλειος | el |
| Δημιουργός | Digalakis Vasilis | en |
| Δημιουργός | Διγαλακης Βασιλης | el |
| Εκδότης | International Speech Communication Association | en |
| Περίληψη | A prevalent and challenging task in spoken language understanding is slot filling. Currently, the best approaches in this domain are based on recurrent neural networks (RNNs). However, in their simplest form, RNNs cannot learn long-term dependencies in the data. In this paper, we propose the use of ClockWork recurrent neural network (CW-RNN) architectures in the slot-filling domain. CW-RNN is a multi-timescale implementation of the simple RNN architecture, which has proven to be powerful since it maintains relatively small model complexity. In addition, CW-RNN exhibits a great ability to model long-term memory inherently. In our experiments on the ATIS benchmark data set, we also evaluate several novel variants of CW-RNN and we find that they significantly outperform simple RNNs and they achieve results among the state-of-the-art, while retaining smaller complexity. | en |
| Τύπος | Πλήρης Δημοσίευση σε Συνέδριο | el |
| Τύπος | Conference Full Paper | en |
| Άδεια Χρήσης | http://creativecommons.org/licenses/by/4.0/ | en |
| Ημερομηνία | 2018-06-01 | - |
| Ημερομηνία Δημοσίευσης | 2017 | - |
| Θεματική Κατηγορία | Clock-work recurrent neural network (CW-RNN) | en |
| Θεματική Κατηγορία | Slot filling (SF) | en |
| Θεματική Κατηγορία | Spoken language understanding (SLU) | en |
| Βιβλιογραφική Αναφορά | D. Georgiadou, V. Diakoloukas, V. Tsiaras and V. Digalakis, "ClockWork-RNN based architectures for slot filling," in 18th Annual Conference of the International Speech Communication Association, 2017, pp. 2481-2485. doi: 10.21437/Interspeech.2017-1075 | en |
Copyright © DIAS 2013
