TY - CONF
T1 - Gap-filling LR Parsing for Noisy Spoken Input
T2 - 1st International Conference on Spoken Language Processing, ICSLP 1990
AU - Saito, Hiroaki
N1 - Funding Information:
The author is grateful to Dr. Masaru Tomita for valuable comments on this work. The author also wishes to thank the members of the Center for Machine Translation for useful discussions.
Publisher Copyright:
© 1990 1st International Conference on Spoken Language Processing, ICSLP 1990. All rights reserved.
PY - 1990
Y1 - 1990
N2 - This paper introduces the new parsing technique "gap-filling LR parsing." This technique enhances the robustness of the generalized LR parsing and is very useful in speech recognition in that the parser can skip the very noisy part of the input The unidentified portion is resolved by the re-utterance of that portion by the speaker, which is parsed very efficiently by using the parse record of the first utterance. Experiments in parsing Japanese spoken input show the significant effectiveness of this interactive approach.
AB - This paper introduces the new parsing technique "gap-filling LR parsing." This technique enhances the robustness of the generalized LR parsing and is very useful in speech recognition in that the parser can skip the very noisy part of the input The unidentified portion is resolved by the re-utterance of that portion by the speaker, which is parsed very efficiently by using the parse record of the first utterance. Experiments in parsing Japanese spoken input show the significant effectiveness of this interactive approach.
UR - http://www.scopus.com/inward/record.url?scp=85133545547&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85133545547&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:85133545547
SP - 909
EP - 912
Y2 - 18 November 1990 through 22 November 1990
ER -