Comparison of Syntax-0riented Spoken Japanese Understanding System with Semantic-Oriented System

Seiichi NAKAGAWA; Yoshimitsu HIRATA; Isao MURASE; Tomohiro TANOUE

Comparison of Syntax-0riented Spoken Japanese Understanding System with Semantic-Oriented System

Seiichi NAKAGAWA, Yoshimitsu HIRATA, Isao MURASE, Tomohiro TANOUE

Full Text Views

0

Cite this

Summary :

This paper describes syntax/semantics oriented spoken Japanese understanding systems named "SPOJUSSYNO/SEMO" and compares them. At first these systems make Hidden-Markov-Models (HMM) based on word units automatically by concatenating syllables. Then a word lattice is hypothsized by using a word spotting algorithm and word-based HMMs for an input utterance. In SPOJUS-SYNO, the time-synchronous left-to-right parsing algorithm is executed to find the best word sequence from the word lattice according to syntactic & semantic knowledge represented by a context free semantic grammar. In SPOJUS-SEMO, the knowledges of syntax and semantics are represented by a dependency and case grammar. These systems were implemented in the "UNIX-QA" task with the vocabulary size of 521 words. Experimental result shows that the sentence recognition/understanding rate was about 80/87% for six male speakers for the SPOJUS-SYNO, but was very low performance for the SPOJUS-SEMO.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E74-A No.7 pp.1854-1862

Publication Date: 1991/07/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Issue on Continuous Speech Recognition and Understanding)

Category: Speech Understanding

Authors

Seiichi NAKAGAWA
Yoshimitsu HIRATA
Isao MURASE
Tomohiro TANOUE

Keyword

Cite this

Copy

Seiichi NAKAGAWA, Yoshimitsu HIRATA, Isao MURASE, Tomohiro TANOUE, "Comparison of Syntax-0riented Spoken Japanese Understanding System with Semantic-Oriented System" in IEICE TRANSACTIONS on Fundamentals, vol. E74-A, no. 7, pp. 1854-1862, July 1991, doi: .
Abstract: This paper describes syntax/semantics oriented spoken Japanese understanding systems named "SPOJUSSYNO/SEMO" and compares them. At first these systems make Hidden-Markov-Models (HMM) based on word units automatically by concatenating syllables. Then a word lattice is hypothsized by using a word spotting algorithm and word-based HMMs for an input utterance. In SPOJUS-SYNO, the time-synchronous left-to-right parsing algorithm is executed to find the best word sequence from the word lattice according to syntactic & semantic knowledge represented by a context free semantic grammar. In SPOJUS-SEMO, the knowledges of syntax and semantics are represented by a dependency and case grammar. These systems were implemented in the "UNIX-QA" task with the vocabulary size of 521 words. Experimental result shows that the sentence recognition/understanding rate was about 80/87% for six male speakers for the SPOJUS-SYNO, but was very low performance for the SPOJUS-SEMO.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e74-a_7_1854/_p

Copy

@ARTICLE{e74-a_7_1854,
author={Seiichi NAKAGAWA, Yoshimitsu HIRATA, Isao MURASE, Tomohiro TANOUE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Comparison of Syntax-0riented Spoken Japanese Understanding System with Semantic-Oriented System},
year={1991},
volume={E74-A},
number={7},
pages={1854-1862},
abstract={ This paper describes syntax/semantics oriented spoken Japanese understanding systems named "SPOJUSSYNO/SEMO" and compares them. At first these systems make Hidden-Markov-Models (HMM) based on word units automatically by concatenating syllables. Then a word lattice is hypothsized by using a word spotting algorithm and word-based HMMs for an input utterance. In SPOJUS-SYNO, the time-synchronous left-to-right parsing algorithm is executed to find the best word sequence from the word lattice according to syntactic & semantic knowledge represented by a context free semantic grammar. In SPOJUS-SEMO, the knowledges of syntax and semantics are represented by a dependency and case grammar. These systems were implemented in the "UNIX-QA" task with the vocabulary size of 521 words. Experimental result shows that the sentence recognition/understanding rate was about 80/87% for six male speakers for the SPOJUS-SYNO, but was very low performance for the SPOJUS-SEMO.},
keywords={},
doi={},
ISSN={},
month={July},}

Copy

TY - JOUR
TI - Comparison of Syntax-0riented Spoken Japanese Understanding System with Semantic-Oriented System
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1854
EP - 1862
AU - Seiichi NAKAGAWA
AU - Yoshimitsu HIRATA
AU - Isao MURASE
AU - Tomohiro TANOUE
PY - 1991
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E74-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 1991
AB - This paper describes syntax/semantics oriented spoken Japanese understanding systems named "SPOJUSSYNO/SEMO" and compares them. At first these systems make Hidden-Markov-Models (HMM) based on word units automatically by concatenating syllables. Then a word lattice is hypothsized by using a word spotting algorithm and word-based HMMs for an input utterance. In SPOJUS-SYNO, the time-synchronous left-to-right parsing algorithm is executed to find the best word sequence from the word lattice according to syntactic & semantic knowledge represented by a context free semantic grammar. In SPOJUS-SEMO, the knowledges of syntax and semantics are represented by a dependency and case grammar. These systems were implemented in the "UNIX-QA" task with the vocabulary size of 521 words. Experimental result shows that the sentence recognition/understanding rate was about 80/87% for six male speakers for the SPOJUS-SYNO, but was very low performance for the SPOJUS-SEMO.
ER -