Volume: 20, Issues: 2-3(2007)
pp. 151-163 DOI: 10.1142/S0219427907001640
|
|
Abstract |
Full Text (PDF, 421KB)
|
References
|
 |
| Title: |
Pattern Dictionary Development based on Non-Compositional Language Model for Japanese Compound and Complex Sentences |
| Author(s): |
SATORU IKEHARA
Tottori University, Tottori-city, 680-8552, JapanMASATO TOKUHISA
Tottori University, Tottori-city, 680-8552, JapanJIN'ICHI MURAKAMI
Tottori University, Tottori-city, 680-8552, JapanMASASHI SARAKI
Nihon University, Tokyo, 101-0061, JapanMASAHIRO MIYAZAKI
Niigata University, Niigata-city, 950-2102, JapanNAOSHI IKEDA
Gifu University, Gifu-city, 501-1112, Japan
|
| Abstract: |
A large-scale sentence pattern dictionary (SP-dictionary) for Japanese compound and complex sentences has been developed. The dictionary has been compiled based on the non-compositional language model. Sentences with 2 or 3 predicates are extracted from a Japanese-to-English parallel corpus of 1 million sentences, and the compositional constituents contained within them are generalized to produce a SP-dictionary containing a total of 215,000 pattern pairs. In evaluation tests, the SP-dictionary achieved a syntactic coverage of 92% and a semantic coverage of 70%. |
| Keywords: |
Pattern dictionary; Machine translation; Language model
|
|
|
