arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1911.00152cs.CL
收藏

基于语音算法隐喻的专业术语索引优化技术的实现

Implementation of an Index Optimize Technology for Highly Specialized Terms based on the Phonetic Algorithm Metaphone

Borys Grinchenko Kyiv University(鲍里斯·格林琴科基辅大学)

V. Buriachok, M. Hadzhyiev, V. Sokolov, P. Skladannyi, L. Kuzmenko

摘要:

在汇编数据库时,例如为了满足保健机构的需要,在介绍和进一步处理医生和病人的姓名和姓氏方面存在相当普遍的问题,因为这些姓名和姓氏在发音和书写方面都是高度专业化的。这是因为人们的名字和姓氏不可能是唯一的,他们的符号不受任何语音规则的约束,而他们在不同语言中的长度可能不匹配。随着互联网的出现,这种情况变得普遍严重,并可能导致多份电子邮件被发送到一个地址。通过使用语音算法来比较单词Daitch-Mokotoff、Soundex、NYSIIS、Polyphone和Metaphone,以及Levenshtein和Jaro算法,基于Q-gram的算法,可以解决指定的问题,这些算法可以找到单词之间的距离。其中最广泛的是Soundex和Metaphone算法,它们旨在根据单词的声音对其进行索引,同时考虑到发音规则。通过应用Metaphone算法,已经尝试优化语音搜索过程以用于模糊重合的任务,例如,在各种数据库和登记处中的数据去重,以减少姓氏的不正确输入的错误数量。对最常见姓氏的分析显示,其中一些姓氏起源于乌克兰或俄罗斯。与此同时,名字的发音和书写所遵循的规则,例如在乌克兰语中,与英语的基本算法有很大不同,与俄语也有很大不同。这就是为什么语音算法应该首先考虑乌克兰姓氏形成的特殊性,这在现在特别重要。

英文摘要:

When compiling databases, for example to meet the needs of healthcare establishments, there is quite a common problem with the introduction and further processing of names and last names of doctors and patients that are highly specialized both in terms of pronunciation and writing. This is because names and last names of people cannot be unique, their notation is not subject to any rules of phonetics, while their length in different languages may not match. With the advent of the Internet, this situation has become generally critical and can lead to that multiple copies of e-mails are sent to one address. It is possible to solve the specified problem by using phonetic algorithms for comparing words Daitch-Mokotoff, Soundex, NYSIIS, Polyphone, and Metaphone, as well as the Levenshtein and Jaro algorithms, Q-gram-based algorithms, which make it possible to find distances between words. The most widespread among them are the Soundex and Metaphone algorithms, which are designed to index the words based on their sound, taking into consideration the rules of pronunciation. By applying the Metaphone algorithm, an attempt has been made to optimize the phonetic search processes for tasks of fuzzy coincidence, for example, at data deduplication in various databases and registries, in order to reduce the number of errors of incorrect input of last names. An analysis of the most common last names reveals that some of them are of the Ukrainian or Russian origin. At the same time, the rules following which the names are pronounced and written, for example in Ukrainian, differ radically from basic algorithms for English and differ quite significantly for the Russian language. That is why a phonetic algorithm should take into consideration first of all the peculiarities in the formation of Ukrainian last names, which is of special relevance now.

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。

↑