Name Matching and Translation for Identity Resolution, Watch Lists, and Name Searches

Software to standardize name spellings and find matching names

Technology to Power Watch Lists, Name Searches, and Identity Resolution

Our name matching and translation technology is integrated into government applications for matching names against watch lists; 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.

Governments Rely on Basis Technology

Governments around the world and agencies of the U.S. intelligence community, the Department of Defense, the FBI and others use our products for intelligence triage in critical languages—Arabic, Chinese, Dari, Farsi, Pashto, and Urdu. Our text analytics and name technologies serve vital functions in monitoring and sifting open source intelligence; correlating names against watch lists and between disparate reports; and boosting the productivity of scarce analysts and linguists.

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 watch list 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

For More Information

Learn More

For more information about the identity resolution solutions, download our whitepapers

관련 링크

지원 플랫폼

Windows, Linux, Solaris, AIX, HPUX, Mac OS 등