Rosette® Name Translator (RNT) accepts names in Chinese and produces accurate, standardized English translations for use by end users, databases, or further processing downstream.
Whether your application just needs a way to import data not written in Latin script, or your users need to get an idea of the names in a document in a foreign script, Rosette Name Translator easily integrates into applications for financial compliance, border control, law enforcement, litigation support, or intelligence via a Java API.
Rosette Name Translator allows the user to select the standard to which they would like to translate Chinese names, and then applies the standard systematically and consistently for fast and accurate searching of names in information retrieval systems. Both traditional Chinese and simplified Chinese are supported.
The translation of Chinese names to English is the rendering of a Chinese name in a transliteration or Romanization standard. The software supports various standards including the widely used pinyin standard favored by China, the hanyu pinyin standard and the older Wade-Giles standard.
The sounds of Chinese names are systematically translated according to these standards. Here is a sample of how a name might be translated in these three ways.
| Original Chinese | Pinyin | Hanyu Pinyin | Wade-Giles | |
|---|---|---|---|---|
| Simplified Chinese | 毛泽东 | Mao Zedong | Máo zé dōng | Mao Tse Tung |
| Traditional Chinese | 毛澤東 | Mao Zedong | Máo zé dōng | Mao Tse Tung |
Applying the transliteration standard correctly is not enough for a good translation, so Rosette Name Translator also handles Chinese name translation issues such as mis-segmentation of name components.
Chinese is a particularly tricky when it comes to segmentation of name components. Given names in Chinese are frequently written with two characters. Should the transliteration put those two characters together (Zhang Jingquan)? Hyphenate them (Zhang Jing-Quan)? Or write them as two words (Zhang Jing Quan)?
Family names and given names are written with anywhere from one to three characters each. Chinese names, just like Chinese text, is written without spaces between words, thus, it is very challenging to identify where one name begins and another ends
Rosette Name Translator leverages Basis Technology’s many years of experience tokenizing Chinese text to figure out where each name component begins and ends so that the translations can be formatted to look like Zhang Jingquan instead of Zhangjingquan.
Rosette Name Translator is used by agencies of the U.S. government as well as by banks and companies in the governance, risk and compliance domains. For over 20 years, Basis Technology has provided software tools for analyzing and extracting information from multilingual text.
For more information about Rosette Name Translator, download the product datasheet, request a product evaluation, or read a presentation about “Building Applications with Rosette Name Indexer and Rosette Name Translator” by Basis Technology CTO Benson Margulies.