Spoken language understanding (SLU) aims to map a user's speech into a semantic frame. Since most of the previous works use the semantic structures for SLU, we verify that the structure is useful even for noisy input. We apply a structured prediction method to SLU problem and compare it to an unstructured one. In addition, we present a combined method to embed long-distance dependency between entities in a cascaded manner. On air travel data, we show that our approach improves performance over baseline models.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Minwoo JEONG, Gary Geunbae LEE, "On the Use of Structures for Spoken Language Understanding: A Two-Step Approach" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 5, pp. 1552-1561, May 2008, doi: 10.1093/ietisy/e91-d.5.1552.
Abstract: Spoken language understanding (SLU) aims to map a user's speech into a semantic frame. Since most of the previous works use the semantic structures for SLU, we verify that the structure is useful even for noisy input. We apply a structured prediction method to SLU problem and compare it to an unstructured one. In addition, we present a combined method to embed long-distance dependency between entities in a cascaded manner. On air travel data, we show that our approach improves performance over baseline models.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.5.1552/_p
Copy
@ARTICLE{e91-d_5_1552,
author={Minwoo JEONG, Gary Geunbae LEE, },
journal={IEICE TRANSACTIONS on Information},
title={On the Use of Structures for Spoken Language Understanding: A Two-Step Approach},
year={2008},
volume={E91-D},
number={5},
pages={1552-1561},
abstract={Spoken language understanding (SLU) aims to map a user's speech into a semantic frame. Since most of the previous works use the semantic structures for SLU, we verify that the structure is useful even for noisy input. We apply a structured prediction method to SLU problem and compare it to an unstructured one. In addition, we present a combined method to embed long-distance dependency between entities in a cascaded manner. On air travel data, we show that our approach improves performance over baseline models.},
keywords={},
doi={10.1093/ietisy/e91-d.5.1552},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - On the Use of Structures for Spoken Language Understanding: A Two-Step Approach
T2 - IEICE TRANSACTIONS on Information
SP - 1552
EP - 1561
AU - Minwoo JEONG
AU - Gary Geunbae LEE
PY - 2008
DO - 10.1093/ietisy/e91-d.5.1552
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2008
AB - Spoken language understanding (SLU) aims to map a user's speech into a semantic frame. Since most of the previous works use the semantic structures for SLU, we verify that the structure is useful even for noisy input. We apply a structured prediction method to SLU problem and compare it to an unstructured one. In addition, we present a combined method to embed long-distance dependency between entities in a cascaded manner. On air travel data, we show that our approach improves performance over baseline models.
ER -