Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
EN  |  EL

Αναζήτηση

Πλοήγηση

Ο Χώρος μου

ClockWork-RNN based architectures for slot filling

Georgiadou Despoina, Diakoloukas Vasilis, Tsiaras Vasileios, Digalakis Vasilis

Απλή Εγγραφή


URIhttp://purl.tuc.gr/dl/dias/6AFB8526-0978-45A1-8539-8DBDB9C25C69-
Αναγνωριστικόhttps://doi.org/10.21437/Interspeech.2017-1075-
Γλώσσαen-
Μέγεθος5 pagesen
ΤίτλοςClockWork-RNN based architectures for slot fillingen
ΔημιουργόςGeorgiadou Despoinaen
ΔημιουργόςΓεωργιαδου Δεσποιναel
ΔημιουργόςDiakoloukas Vasilisen
ΔημιουργόςΔιακολουκας Βασιλeioςel
ΔημιουργόςTsiaras Vasileiosen
ΔημιουργόςΤσιαρας Βασιλειοςel
ΔημιουργόςDigalakis Vasilisen
ΔημιουργόςΔιγαλακης Βασιληςel
Εκδότης International Speech Communication Associationen
ΠερίληψηA 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
ΤύποςΠλήρης Δημοσίευση σε Συνέδριοel
ΤύποςConference Full Paperen
Άδεια Χρήσηςhttp://creativecommons.org/licenses/by/4.0/en
Ημερομηνία2018-06-01-
Ημερομηνία Δημοσίευσης2017-
Θεματική ΚατηγορίαClock-work recurrent neural network (CW-RNN)en
Θεματική ΚατηγορίαSlot filling (SF)en
Θεματική ΚατηγορίαSpoken language understanding (SLU)en
Βιβλιογραφική ΑναφοράD. 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.2017-1075en

Υπηρεσίες

Στατιστικά