arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1412.5477cs.CL
收藏

梵文电子文本中男性名词格形变化的计算模型

Computational Model to Generate Case-Inflected Forms of Masculine Nouns for Word Search in Sanskrit E-Text

SRM University(SRM大学);Meenakshi College for Women(米纳克希女子学院);Mother Teresa Women’s University(特蕾莎修女女子大学)

S V Kasmir Raja, V Rajitha, Lakshmanan Meenakshi

摘要:

梵语中的单词搜索问题与复杂性是不可分割的,包括那些由委婉连接词和大小写变化引起的复杂性。一个名词的格屈折形式通常有24种,因为在梵语中有8种格和3种数--单数、双数和复数。生成这些屈折形式的传统方法相当复杂,因为即使是非常相似的单词之间生成的形式也存在差异,并且涉及微妙的细微差别。此外,使用当前可用的大小写变化形式生成器,在大文本中的单词搜索期间生成和搜索单词的24种形式将是麻烦的练习。这项研究提出了一种新的方法来产生的情况下,曲折的形式,更简单的计算。此外,一个优化的模型,这是足够的只生成那些词的形式,需要在一个词的搜索,是超过80%的效率相比,完整的情况下,屈折形式发生器,在这项研究中首次提出。

英文摘要:

The problem of word search in Sanskrit is inseparable from complexities that include those caused by euphonic conjunctions and case-inflections. The case-inflectional forms of a noun normally number 24 owing to the fact that in Sanskrit there are eight cases and three numbers-singular, dual and plural. The traditional method of generating these inflectional forms is rather elaborate owing to the fact that there are differences in the forms generated between even very similar words and there are subtle nuances involved. Further, it would be a cumbersome exercise to generate and search for 24 forms of a word during a word search in a large text, using the currently available case-inflectional form generators. This study presents a new approach to generating case-inflectional forms that is simpler to compute. Further, an optimized model that is sufficient for generating only those word forms that are required in a word search and is more than 80% efficient compared to the complete case-inflectional forms generator, is presented in this study for the first time.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑