Name Matching and Translation for Identity Resolution, Watchlists, and Name Searches

Name Matching and Translation

for Identity Resolution, Watchlists, and Name Searches

Software to Standardize Name Spellings and Find Matching Names

Our name matching and translation technology is integrated into government applications for matching names against watchlists; boosting the accuracy of identity resolution systems; and performing sophisticated name searches. Our advanced name extraction, normalizing, and matching software can be integrated into existing systems or be used as the basis for new systems seeking precision name matching in high-transaction environments.

Handles Common and Unusual Types of Name Variations

Rosette removes the obstacles to performing record linkage and data alignment, including name variations due to nicknames, initials, missing name components, missing spaces between names, out-of-order name components, the same name represented in different languages, and more.

Statistical Algorithms Recognize Countless Name Spelling Permutations and Names in Different Languages

The name matcher uses statistical algorithms to match names rather than relying on a long search through millions of name variations which can never cover every possible spelling permutation. Besides handling “Robert” vs. “Bob,” our software also accurately matches “Mao Tse-Tung”, “Mao Zedong”, and “毛泽东” (simplified Chinese).

Components Have Small Footprint and Are Fast for Flexible Integration

Because of their small footprint, the Rosette name components add only a very small incremental load to the hardware already running the main application whether for watchlist compliance or name resolution. Rosette is tuned for speed and easy integration into any application. Its SDK is available for Windows or Unix and comes with APIs for C++ and Java.

An Example of Name Matching Software Components in an Identity Resolution System 


1. Name Discovery – Rosette Entity Extractor automatically finds names of people in documents for 18 languages, using statistical models.


2. Name Normalization – Rosette Name Translator normalizes name spellings to any of several transliteration standards or translates names into English. Translation happens on three levels:

  • Standardization of English spelling – Assorted spellings of names can be normalized to a transliteration standard
  • Transliteration of names – Names from one script rewritten to another script—such as あづさ to Azusa
  • True translation of names – Backed by databases, we translate well-known names, turning جورج بوش into “George Bush” instead of “Jwrj Bwsh.”


3. Name Matching – Rosette Name Indexer resolves the quirks of spelling variations to find matching names despite:

  • The same name written in different languages (“Mao Tse Tung”, “毛泽东”, “毛澤東”)
  • Phonetic spelling differences
  • Orthographic spelling differences
  • Nicknames
  • Initials
  • Missing name components
  • Out-of-order name components
  • More name matching examples



The Name Matching You Need: A Comparison of Name Matching Technologies

Entity Search White Paper

Learn how entity search is revolutionizing the decision-making and problem solving process

Supported Platforms

Windows, Linux, Solaris, and MacOS

Contact us for more information:

This is a unique website which will require a more modern browser to work! Please upgrade today!