Satoru Ikehara

Zero Pronoun Resolution in a Machine Translation System by using Japanese to English Verbal Semantic Attributes.

A method of anaphoral resolution of zero pronouns in Japanese language texts using the verbal semantic attributes is suggested. This method focuses attention on the semantic attributes of verbs and examines the context from the relationship between the semantic attributes of verbs governing zero pronouns and the semantic attributes of verbs governing their referents. The semantic attributes of verbs are created using 2 different viewpoints: dynamic characteristics of verbs and the relationship of verbs to cases. By using this method, it is shown that, in the case of translating newspaper articles, the major portion (93%) of anaphoral resolution of zero pronouns necessary for machine translation can be achieved by using only linguistic knowledge.Factors to be given special attention when incorporating this method into a machine translation system are examined, together with suggested conditions for the detection of zero pronouns and methods for their conversion. This study considers four factors that are important when implementing this method in a Japanese to English machine translation system: the difference in conception between Japanese and English expressions, the difference in case frame patterns between Japanese and English, restrictions by voice and restriction by translation structure. Implementation of the proposed method with due consideration of these points leads to a viable method for anaphoral resolution of zero pronouns in a practical machine translation system.

Natural language processing in a Japanese text-to-speech system

A Japanese text-to-speech system is developed that provides continuous generation of natural speech from newspaper articles and other Japanese texts written in an unrestricted mixture of Kanji (ideograms. — 7000 Chinese characters), Kana (two types of phonograms, — 200 characters), alphanumerics and marks (including ¥, &,

Goi-Taikei | A Japanese Lexicon

, etc.).nIn the newly developed system, the Japanese texts are analyzed in terms of both grammar and meaning where texts have ambiguities, but in terms of grammar only where there is no ambiguity. The dictionary in this system contains ordinarily segmented words for various open texts and special compound words, most of which are proper nouns that have multiple readings when segmented. This reduces the percentage of erroneous readings from 2.2% for the conventional method to 0.2% and of erroneous accentuation from 20% to 5%.nThe dictionary containing approximately 430,000 words uses a resident index consists of the first two characters of the words. This approach for accessing is adopted because many Japanese words consists of two basic characters. This improved the systems efficiency in maintaining a higher level of accuracy.nThese improvements will provide advanced information exchanges to subscriber networks.