Arab Names in Arabic
Over 220,000 vocalized variants
Every name is normalized and vocalized
Covers common spelling mistakes
Overview
The complexity of the Arabic script gives rise to a variety of Arabic spelling variants and spelling errors, which can lead to various problems in Arabic information processing. To this end, CJKI has developed the Database of Arab Names in Arabic (DANA), a one-of-a-kind resource that covers several hundred thousand Arabic script variants and common spelling mistakes.
A key feature of DANA is that every Arabic name is normalized and vocalized to produce a database of error-free, fully sanitized Arabic canonical forms. The vocalization was performed by a team of editors with the aid of tools and interfaces designed to achieve maximum efficiency.
The canonical forms are used both as a basis for creating accurate romanized variants for our Database of Arab Names (DAN), which contains over 6.5 million romanized variants, as well as Arabic orthographic variants for DANA.
Arab Names in Arabic
Practical Applications
DANA can be used for a variety of applications, including:
Machine translation
Compliance and risk management
Anti-money laundering and fraud detection
Database cleansing and normalization
Information retrieval and query processing
Entity recognition and extraction
Anti-terror and immigration control
Reference Documents
Arab Name Transcription Engine
Online demo for ANTE
Calculating Name Frequency in Arabic
White paper
Related Resources
DANA exists both as a standalone database, or it can be paired with our Database of Arab Names (DAN), and our other Arab proper noun databases.
Database of Arabic Names
Arabic personal names and their romanized variants
Expanded OFAC
Variants of Arab names in OFAC’s SDN list
Foreign Names in Arabic
Non-Arab names in Arabic and their variants