Το έργο με τίτλο ClockWork-RNN based architectures for slot filling από τον/τους δημιουργό/ούς Georgiadou Despoina, Diakoloukas Vasilis, Tsiaras Vasileios, Digalakis Vasilis διατίθεται με την άδεια Creative Commons Αναφορά Δημιουργού 4.0 Διεθνές
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
https://doi.org/10.21437/Interspeech.2017-1075
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.