 |
Conference papers
Exploring the use of Attention-Based Recurrent Neural Networks For Spoken Language Understanding
Abstract : This study explores the use of a bidirectional recurrent neural network (RNN) encoder/decoder based on a mechanism of attention for a Spoken Language Understanding (SLU) task. First experiments carried on the ATIS corpus confirm the quality of the RNN baseline system used in this paper, by comparing its results on the ATIS corpus to the results recently published in the literature. Additional experiments show that RNN based on a mechanism of attention performs better than RNN architectures recently proposed for a slot filling task. On the French MEDIA corpus, a French state-of-the-art corpus for SLU dedicated to hotel reservation and tourist information, experiments show that a bidirectionnal RNN reaches a f-measure value of 79.51 while the use of a mechanism of attention allows us to reach a f-measure value of 80.27.
Cited literature [13 references]
https://hal.archives-ouvertes.fr/hal-01433202
Contributor : Sylvain Meignier <>
Submitted on : Monday, November 9, 2020 - 8:14:56 PM
Last modification on : Wednesday, November 25, 2020 - 5:50:05 PM
Long-term archiving on: : Wednesday, February 10, 2021 - 7:59:26 PM
Contributor : Sylvain Meignier <>
Submitted on : Monday, November 9, 2020 - 8:14:56 PM
Last modification on : Wednesday, November 25, 2020 - 5:50:05 PM
Long-term archiving on: : Wednesday, February 10, 2021 - 7:59:26 PM
File
nips15.pdf
Files produced by the author(s)