End-to-end convolutional neural networks for intent detection

Yolchuyeva, Sevinj and Németh, Géza and Gyires-Tóth, Bálint: End-to-end convolutional neural networks for intent detection. Magyar Számítógépes Nyelvészeti Konferencia, (13). pp. 123-134. (2019)

[img] Cikk, tanulmány, mű

Download (628kB)


Convolutional Neural Networks (CNNs) have been applied to various machine learning tasks, such as computer vision, speech technologies and machine translation. One of the main advantages of CNNs is the representation learning capability from highdimensional data. End-to-end CNN models have been massively explored in computer vision domain and this approach has also been attempted in other domains as well. In this paper, a novel end-to-end CNN architecture with residual connections is presented for intent detection, which is one of the main goals for building a spoken language understanding (SLU) system. Experiments on two datasets (ATIS and Snips) were carried out. The results demonstrate that the proposed model outperforms previous solutions.

Item Type: Article
Event Title: Magyar Számítógépes Nyelvészeti Konferencia (15.) (2019) (Szeged)
Journal or Publication Title: Magyar Számítógépes Nyelvészeti Konferencia
Date: 2019
Volume: 13
Page Range: pp. 123-134
ISBN: 978-963-315-393-2
Uncontrolled Keywords: Nyelvészet - számítógép alkalmazása
Additional Information: Bibliogr.: p. 132-134. ; összefoglalás angol nyelven
Date Deposited: 2019. Jul. 03. 12:21
Last Modified: 2019. Jul. 03. 12:21
URI: http://acta.bibl.u-szeged.hu/id/eprint/59079

Actions (login required)

View Item View Item