ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

Spoken language parsing based on incremental disambiguation

Yoshihide Kato, Shigeki Matsubara, Katsuhiko Toyama, Yasuyoshi Inagaki

Towards a real-time spoken dialogue system, several incremental parsing methods have been proposed so far. They construct syntactic structures for an initial fragment of an input sentence. However, they have a problem that the structures do not necessarily represent the syntactic relation correctly. The problem is caused by the ambiguity of initial fragments. This paper proposes an incremental disambiguation method, which decides correct structures at an stage where the entire input is not completed. The method finds the structures which are correct independently of the remaining input. When correct structures cannot be decided, the method delays the decision. Since the disambiguation is executed for every word input, the method can find correct structures at an early stage.


Cite as: Kato, Y., Matsubara, S., Toyama, K., Inagaki, Y. (2000) Spoken language parsing based on incremental disambiguation. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 2, 999-1002

@inproceedings{kato00b_icslp,
  author={Yoshihide Kato and Shigeki Matsubara and Katsuhiko Toyama and Yasuyoshi Inagaki},
  title={{Spoken language parsing based on incremental disambiguation}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 2, 999-1002}
}