Abstract | ||
---|---|---|
This paper presents an Information Extraction (IE) ap- proach for spoken language understanding. The goal in IE is to find proper values for pre-defined slots of given templates. IE for spoken language understanding pro- poses a concept spotting approach for spoken language because IE approach is interested in only pre-defined con- cept slots. In spite of this partial understanding, we can acquire necessary information for an application from the values of pre-defined slots because the slots are properly designed for speech understanding in a specific domain. Spoken language has so many recognition errors espe- cially in a poor environment so it is more difficult to un- derstand than textual language. Considering this fact, we attempt to understand the languages by concentrating on the specified information. In experiments on the car nav- igation domain, F-measure for concept spotting for tex- tual input (WER 0%) and spoken input (WER 39%) are 96.33% and 78.30% respectively. |
Year | Venue | Keywords |
---|---|---|
2004 | INTERSPEECH | information extraction |
Field | DocType | Citations |
Computer science,Speech recognition,Information extraction,Natural language processing,Artificial intelligence,Spotting,Spoken language | Conference | 2 |
PageRank | References | Authors |
0.45 | 4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jihyun Eun | 1 | 17 | 2.32 |
Changki Lee | 2 | 279 | 26.18 |
Gary Geunbae Lee | 3 | 932 | 93.23 |