Hybrid Similarity Measurement Algorithm based on Improved Phonetic Code
Lihua Liu, Ziiian Pei, Zhuopeng Meng, Mao Wang, Xuan Li, Jibing Wu · 2022
In English-Chinese translation, there have always been problems such as multiple information, confusing and inconsistent translation names, etc. Faced with these problems, the phonetic similarity between translated entities is taken as the research point in this paper, and a similarity measurement algorithm based on improved phonetic code is proposed, by which the matching accuracy between strings is improved effectively. It could be applied to the cross-language entity matching scene with high accuracy and usability.