Journal of Natural Language Processing
Online ISSN : 2185-8314
Print ISSN : 1340-7619
ISSN-L : 1340-7619
Search
Advanced search
OR
Browse
Search
Volume 2, Issue 1
Displaying 1-5 of 5 articles from this issue
Show all abstracts
    • |<
    • <
    • 1
    • >
    • >|
  • [title in Japanese]
    [in Japanese]
    1995 Volume 2 Issue 1 Pages 1-2
    Published: January 10, 1995
    Released on J-STAGE: March 01, 2011
    DOIhttps://doi.org/10.5715/jnlp.2.1
    JOURNAL FREE ACCESS
    Download PDF (209K)
  • Automatic Determination of Semantic Attributes for User Defined Words in Japanese to English Machine Translation
    SATORU IKEHARA, SATOSHI SHIRAI, AKIO YOKOO, FRANCIS BOND, YOSHIE OMI
    1995 Volume 2 Issue 1 Pages 3-17
    Published: January 10, 1995
    Released on J-STAGE: March 01, 2011
    DOIhttps://doi.org/10.5715/jnlp.2.3
    JOURNAL FREE ACCESS
    Show abstractHide abstract
    User dictionaries are important for practical machine translation. However it is difficult for users to enter the detailed semantic attributes that a system may require. This paper proposes a method of automatically determining semantic attributes for noun pairs entered by users. The method compares the Japanese and English words with words already in the system dictionary. When this method was applied to words in two user dictionaries (for newspaper articles and software manuals) it generated more attributes than trained humans did, with a recall rate of 40-80%. Evaluation showed that translations using the machine-made dictionary were similar in quality to translations using the human-made dictionary. Thus automatic determination of semantic attributes removes the need for highly trained lexographers to make user dictionaries.
    View full abstract
    Download PDF (1560K)
  • A zero anaphora resolution system for Japanese complex sentences based on semantic and pragmatic constraints
    SHIN'ICHIRO NISHIZAWA, HIROSHI NAKAGAWA
    1995 Volume 2 Issue 1 Pages 19-38
    Published: January 10, 1995
    Released on J-STAGE: March 01, 2011
    DOIhttps://doi.org/10.5715/jnlp.2.19
    JOURNAL FREE ACCESS
    Show abstractHide abstract
    Our aim is to construct a system which is able to deal with semantics of Japanese complex sentences. One of the most important problem to be solved is the zero anaphora resolution. According to (Nakagawa, 1994; Nakagawa & Nishizawa, 1994), we can use a new pragmatic role called motivated to bridge semantic roles of subordinate and those of main clauses. The new role constrains the relation among semantic and pragmatic roles within subordinate or main clause for Japanese complex sentences. So, we construct the system that treats this type of relation by constraint logic programming, and we use feature structures to formalize these constraints in unification grammar formalism. We also describe how this system works.
    View full abstract
    Download PDF (1621K)
  • GREEN: An Experimental System Generating Summary of Japanese Editorials by Combining Multiple Discourse Characteristics
    KAZUHIDE YAMAMOTO, SHIGERU MASUYAMA, SHOZO NAITO
    1995 Volume 2 Issue 1 Pages 39-55
    Published: January 10, 1995
    Released on J-STAGE: March 01, 2011
    DOIhttps://doi.org/10.5715/jnlp.2.39
    JOURNAL FREE ACCESS
    Show abstractHide abstract
    This paper describes an experimental system GREEN for summarizing Japanese texts. Analyzing several aspects of discourse phenomena is in general indispensable to make a summary of good quality because each linguistic phenomenon mutually affects in a complex manner. From this point of view, we have developed a system GREEN, which is capable of summarizing Japanese editorial newspaper articles. This system uses several surface linguistic characteristics appeared in Japanese texts. We evaluate the performance of the system using a method of questionnaire where human subjects evaluate the quality of the summaries generated by the system.
    View full abstract
    Download PDF (1635K)
  • Classification of Sentences by Word-length Distribution of Verbs with Proportions of Japanese Words and those of Compound Words
    MING-ZHE JIN
    1995 Volume 2 Issue 1 Pages 57-75
    Published: January 10, 1995
    Released on J-STAGE: March 01, 2011
    DOIhttps://doi.org/10.5715/jnlp.2.57
    JOURNAL FREE ACCESS
    Show abstractHide abstract
    For the identification of a unknown author of a certain literature, it is significant to find the main elements of writing styles which characterize authors or distinguish them. It was previously known that the authors' writing styles are characterized in distributions fo lengths of words are categorized by parts of speech. This paper presents a quantitative analysis of the classification of sentences by word-length distribution of verbs, and the relationships between writing styles in word-length distribution of verbs and the proportions of Japanese words and Chinese words or those of compound words and non-compound words in verbs. This analysis shows that word-length distribution of verbs characterizes writing styles even where there are no differences in the proportions of Japanese words and Chinese words or those of compound words and non-compound words.
    View full abstract
    Download PDF (1533K)
    • |<
    • <
    • 1
    • >
    • >|
feedback
 Top