扩展词组数最小法的假名汉字转换

本文描述了改进后的“词组最小法”、并提出了新算法。它被名为“扩展词组最小法”。重新定义了句子中词组的计算方法。为了实现此目标，从始读到句子假名的全部读入，将词库查询及语法检查的结果以“树”型数据加以保留。采用上述算法后，以假名文字为单位的变换率可达９５．８％；以词组为单位的变换率可达８８．９％。

We tried to enhance a“minimumizing a sum of syllables in a sentence”and proposed a new algorithm,named“ninimumizing a sum of syllables in a broad sense”.We redefined a way of counting syllables in a sentence.Realizing this,we searched dictionary and checked grammatical rules and maintained into'tree'form till the analysis for all'Yomi'were finished.In evaluating the conversion-accuracy using said conversion algorithm,we got 95.8% achievement based on the count of Kana-character and got 88.9% achievement on the count of syllable.