Institutional Repository
Technical University of Crete
EN  |  EL

Search

Browse

My Space

ClockWork-RNN based architectures for slot filling

Georgiadou Despoina, Diakoloukas Vasilis, Tsiaras Vasileios, Digalakis Vasilis

Simple record


URIhttp://purl.tuc.gr/dl/dias/6AFB8526-0978-45A1-8539-8DBDB9C25C69-
Identifierhttps://doi.org/10.21437/Interspeech.2017-1075-
Languageen-
Extent5 pagesen
TitleClockWork-RNN based architectures for slot fillingen
CreatorGeorgiadou Despoinaen
CreatorΓεωργιαδου Δεσποιναel
CreatorDiakoloukas Vasilisen
CreatorΔιακολουκας Βασιλeioςel
CreatorTsiaras Vasileiosen
CreatorΤσιαρας Βασιλειοςel
CreatorDigalakis Vasilisen
CreatorΔιγαλακης Βασιληςel
Publisher International Speech Communication Associationen
Content SummaryA 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
Type of ItemΠλήρης Δημοσίευση σε Συνέδριοel
Type of ItemConference Full Paperen
Licensehttp://creativecommons.org/licenses/by/4.0/en
Date of Item2018-06-01-
Date of Publication2017-
SubjectClock-work recurrent neural network (CW-RNN)en
SubjectSlot filling (SF)en
SubjectSpoken language understanding (SLU)en
Bibliographic CitationD. 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

Services

Statistics