Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Kazunori Muraki"'
Autor:
Akitoshi Okumura, Kazunori Muraki
Publikováno v:
ANLP
The authors propose a model for analyzing English sentences including coordinate conjunctions such as "and","or","but" and the equivalent words. Syntactic analysis of the English coordinate sentences is one of the most difficult problems for machine
Publikováno v:
COLING-ACL
This paper proposes a method by which 5W1H (who, when, where, what, why, how, and predicate) information is used to classify and navigate Japanese-language texts. 5W1H information, extracted from text data, has an access platform with three functions
Autor:
Shinko Tamura, Shinichiro Kamei, Shinichi Doi, Kenji Satoh, Kiyoshi Yamabana, Kazunori Muraki
Publikováno v:
ANLP
We present an interactive translation method to support non-professional users to write an original document. The method, combining dictionary lookup function and user-guided stepwise interactive machine translation, allows the user to obtain clear r
Autor:
Kazunori Muraki, Naoyuki Nomura
Publikováno v:
COLING
The verb subcategorization frame information plays a major role of disambiguations in many NLP applications. Japanese, however, imposes difficulties of subcategorizing in part because it allows arbitrary ellipses of case elements. We propose a new ty
Publikováno v:
COLING
This paper presents a practical method for a global structure analyzing algorithm of Japanese long sentences with lexical information, a method which we call Lexical Discourse Grammar (LDG). This method assumes that Japanese function words, such as c
Autor:
Shin-ichiro Kamei, Shin-ichi Doi, Takako Komatsu, Susumu Akamine, Hitoshi Iida, Kazunori Muraki
Publikováno v:
3rd International Conference on Spoken Language Processing (ICSLP 1994).
Publikováno v:
3rd International Conference on Spoken Language Processing (ICSLP 1994).
Autor:
Shinichiro Kamei, Kazunori Muraki
Publikováno v:
COLING
Degree words in natural language, such as 'often' and 'sometimes,' do not have denotations in the real world. This causes some interesting characteristics for degree words. For example, the correspondence between the English word 'often' and the intn
Publikováno v:
MUC
NEC Corporation has had years of experience in natural language processing and machine translation[1, 2, 3, 4, 5], and currently markets commercial natural language processing systems. Utilizing dictionaries and parsing engines we have already had, w
Publikováno v:
EACL