DocumentCode
2700895
Title
Structures for Spoken Language Understanding: A Two-Step Approach
Author
Minwoo Jeong ; Lee, Gwo Giun
Author_Institution
Dept. of Comput. Sci. & Eng., Pohang Univ. of Sci. & Technol., South Korea
Volume
4
fYear
2007
fDate
15-20 April 2007
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 valuable even for noisy input. We apply a structured prediction method to SLU problem with comparison to 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
natural language processing; speech processing; semantic frame; spoken language understanding; structured prediction method; Cities and towns; Computer science; Context modeling; Data mining; Hidden Markov models; Natural languages; Prediction methods; Speech; Working environment noise; Spoken language understanding; long-distance dependency; named entity recognition from speech; structured prediction; two-step cascaded approach;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on
Conference_Location
Honolulu, HI
ISSN
1520-6149
Print_ISBN
1-4244-0727-3
Type
conf
DOI
10.1109/ICASSP.2007.367183
Filename
4218057
Link To Document