2024-03-29T00:17:23Z
https://nagoya.repo.nii.ac.jp/oai
oai:nagoya.repo.nii.ac.jp:00006184
2023-01-16T05:02:44Z
312:313:314
Robust Dependency Parsing of Spontaneous Japanese Spoken Language
Ohno, Tomohiro
Matsubara, Shigeki
Kawaguchi, Nobuo
Inagaki, Yasuyoshi
open access
Copyright 2005 IEICE 許諾番号 07RB0094号
dependency parsing
stochastic parsing
Japanese speech
linguistic phenomena
syntactically annotated corpus
Spontaneously spoken Japanese includes a lot of grammatically ill-formed linguistic phenomena such as fillers, hesitations, inversions, and so on, which do not appear in written language. This paper proposes a novel method of robust dependency parsing using a large-scale spoken language corpus, and evaluates the availability and robustness of the method using spontaneously spoken dialogue sentences. By utilizing stochastic information about the appearance of ill-formed phenomena, the method can robustly parse spoken Japanese including fillers, inversions, or dependencies over utterance units. Experimental results reveal that the parsing accuracy reached 87.0 %, and we confirmed that it is effective to utilize the location information of a bunsetsu, and the distance information between bunsetsus as stochastic information.
IEICE
2005-03
eng
journal article
VoR
http://hdl.handle.net/2237/7824
https://nagoya.repo.nii.ac.jp/records/6184
http://search.ieice.org/bin/summary.php?id=e88-d_3_545&category=D&year=2005&lang=E&abst=
0916-8532
IEICE Transactions on Information and Systems
E88-D
3
545
552
https://nagoya.repo.nii.ac.jp/record/6184/files/E88-D-545.pdf
application/pdf
1.2 MB
2018-02-19