Similarity measure in backward transliteration between different character sets and its application to clir [反向異文字音譯相似度評量方法與跨語言資訊檢索]
Journal
Proceedings of the 13th Conference on Computational Linguistics and Speech Processing, ROCLING 2000
Pages
97-113
Date Issued
2000
Author(s)
Lin W.-H
Abstract
This paper classifies the problem of machine transliteration into four types, i.e., forward/backward transliteration between same/different character sets, based on transliteration direction and character sets. A phoneme-based similarity measure is proposed to deal with backward transliteration between different character sets. Chinese-English information retrieval is taken as an example. The experiments show that phoneme-based approach is better than grapheme-based approach. In a mate matching of 1,261 candidates, the average rank is 7.80 and 57.65% of candidates are ranked as number one. © Proceedings of the 13th Conference on Computational Linguistics and Speech Processing, ROCLING 2000.
Other Subjects
Character sets; Computational linguistics; As numbers; ITS applications; Machine transliteration; Matchings; Similarity measure; Speech processing
Type
conference paper