Kalmasoft Names Advanced Processor
Synopsis
Kalmasoft Names Advanced Processor (KNAP) is a web based solution consists of Web API service and a web application that performs multiple online name processes ranging from transcription to other useful operations.
Information
Last updated: 20/1/2023
Modules
-
Names Classification
Name classification includes ethnicity and gender likelihood classification, Arabic names only in both Arabic or Latin script..
-
Names Non-standard Romanization
Supported languages for Romanization are English, German, Afrikaans, Swahili, French, Italian, Spanish, Portuguese, Swedish, Danish, Finnish, and Polish.
-
Names Standard Romanization
Supported standards include ADEGN (Arabic Division of Experts on Geographic Names), ALA_LC (American Library Association_Library of Congress), BGN (Board on Geographic Names ), Buckwalter, Hans Wehr transliteration, DIN (Deutsches Institut für Normung), IGN (Institut Géographique National), ISO (International Organization for Standardization), KATS (Kalmasoft Arabic Transliteration System), RJGC (Royal Jordanian Geographic Centre), SAS (Spanish Arabists School), SATTS (Standard Arabic Technical Transliteration System), UNGEGN (United Nations Group of Experts on Geographic Names), IPA (International Phonetic Alphabet), Wade-Giles, MPS II (Mandarin Phonetic Symbols II), Yale Chinese, Tong-yong, Gwoyeu Romatzyh, IAST (International Alphabet of Sanskrit Transliteration), Hunterian system, National Library at Kolkata romanization, Nihon-shiki, Kunrei-shiki, Hepburn, Revised Romanization of Korean, McCune–Reischauer, Yale Korean, ICAO WP/17, Somali Latin Alphabet.
-
Names Non-standard Arabicization
Supported languages (in theier native scripts) include Oromo, Afar, Afrikaans, Amharic, Armenian, Assamese, Bengali, Bulgarian, Burmese, Catalan, Chinese, Czech, Danish, Dutch, Esperanto, Finnish, French, Gaelic, German, Greek, Gujarati, Hebrew, Hindi, Indonesian, Interlingua, Irish, Italian, Japanese, Korean, Kurdish, Malayalam, Marathi, Pashto, Persian, Portuguese, Romanian, Russian, Spanish, Somali, Swahili, Swedish, Telugu, Thai, Tigrinya, Turkish, Ukrainian, Urdu, Yiddish, Yoruba, Tigre, Filipino, Tamazight, Syriac.
-
Names Standard Arabicization
Supported Arabic spellings Common spelling, Levantine spelling, Egyptian spelling, Moroccan spelling, Omani spelling, Hassaniya spelling, Iraqi spelling, Sudanese spelling, Hijazi spelling, and Yemeni spelling; implementing Kalmasoft KRATS.
-
Romanized Personal Names Arabicization
Arabicizing names written Latin and also retrieving names of Arabic origin that are romanized in many different and obsecure ways like (Halid, Ahmet, Houcene).
-
Names Transcription
Name multilingual cross transcription, supported languages include Russian, Japanese, Korean, Hebrew, Amharic, Tigrinya, Farsi, Hindi.
-
Arabic Names Vocalization
Adding diacritical marks to Arabic names including dialectal variations.
-
Names Non-Standard Retrieval
Retrieval of personal names written in non-native script.
-
Names Parsing
Parsing name parts to different components (first, last, patronymic etc.) for Arabic names this translates to given, surname, Nasab, Kuniya, or Nisba.
-
Names Generation
Arabic names only.
-
Names Standard Romanization
Supported romanization standards ADEGN (Arabic Division of Experts on Geographic Names), ALA_LC (American Library Association_Library of Congress), BGN (Board on Geographic Names ), Buckwalter, Hans Wehr transliteration, DIN (Deutsches Institut für Normung), IGN (Institut Géographique National), ISO (International Organization for Standardization), KATS (Kalmasoft Arabic Transliteration System), RJGC (Royal Jordanian Geographic Centre), SAS (Spanish Arabists School), SATTS (Standard Arabic Technical Transliteration System), UNGEGN (United Nations Group of Experts on Geographic Names), IPA (International Phonetic Alphabet), Wade-Giles, MPS II (Mandarin Phonetic Symbols II), Yale Chinese, Tong-yong, Gwoyeu Romatzyh, IAST (International Alphabet of Sanskrit Transliteration), Hunterian system, National Library at Kolkata romanization, Nihon-shiki, Kunrei-shiki, Hepburn, Revised Romanization of Korean, McCune–Reischauer, Yale Korean, ICAO WP/17.
-
Names Arabicization
Arabic transcription of place names.
-
Names Standard Retrieval
Retrieving the original place names in their native script from the transcripted version. Supported standards include ADEGN (Arabic Division of Experts on Geographic Names), ALA_LC (American Library Association_Library of Congress), BGN (Board on Geographic Names ), Buckwalter, Hans Wehr transliteration, DIN (Deutsches Institut für Normung), IGN (Institut Géographique National), ISO (International Organization for Standardization), KATS (Kalmasoft Arabic Transliteration System), RJGC (Royal Jordanian Geographic Centre), SAS (Spanish Arabists School), SATTS (Standard Arabic Technical Transliteration System), UNGEGN (United Nations Group of Experts on Geographic Names), IPA (International Phonetic Alphabet), Wade-Giles, MPS II (Mandarin Phonetic Symbols II), Yale Chinese, Tong-yong, Gwoyeu Romatzyh, IAST (International Alphabet of Sanskrit Transliteration), Hunterian system, National Library at Kolkata romanization, Nihon-shiki, Kunrei-shiki, Hepburn, Revised Romanization of Korean, McCune–Reischauer, Yale Korean.
-
Language Recognition
A module for language recognition.
-
Arabic Entity Extraction
Arabic names entity recognition and extraction NERSys.
-
Arabic Entity Linking
Arabic Entity Linking
-
Arabic Topic Classification
Arabic Topic Classification
-
Arabic Dialect Recognition
Arabic Dialect Recognition
-
Arabic Sentiment Analysis
Arabic Sentiment Analysis
-
Arabic Emotion Analysis
Arabic Emotion Analysis
-
Arabic Profanity Analysis
Arabic Profanity Analysis
-
Arabic PoS Tagging
-
Arabic Text Diacritization
-
Amharic Verbs Conjugation
-
Amharic Nouns Declension
-
Arabic Verbs Conjugation
-
Arabic Nouns Declension
-
Arabic Root Extraction
Deployment
Kalmasoft offers Names Advanced Processor in three different ways, RESTful API, Java SDK, and Server Edition.
SaaS through RESTful API
The SaaS version of NAP is based on subscription, with less cost for hardware, and ideal for users who like to pay-as-you-go.
On-premise Java SDK
The on-premise version is implemeted for the high-speed needs, best for very high transaction environments like search engines, health agencies, financial and security institutions.
Server Edition
For extra control, a cloud deployment on-premise private cloud is the way to go, this enables user custom profile and other advanced features.
Specifications
Specification | Details |
---|---|
System technology | Web API |
Applications supported | Cloud based applications |
Frontend | HTML, CSS, Angular |
Backend | Microsoft .Net Core / Web API |
Database technology | Microsoft SQL Server |
Application domain | Onomastics and toponymy |
Application level | All types of institutions |
System design | Cloud based Web services (SOA) |
Data dependency
Careful organization of data dependencies.
Integrated processing
A thorough outline of procedures needed to process names.
Highlight
Interoperable framework for names processing systems implementing various technologies.
Designed on a SOA architecture and supports modern cloud technologies (SaaS, NaaS, SAN, HTML5, IP6) to host different applications.
Independent of geographic environment and includes all the necessary standards of name transcription in most world countries.
Designed to work in an integrated environment including systems similar to egovernment subsystems.
Modular design applicable to all levels of name processing and seamlessly integrates the whole name processing system with other governmental and civil circles in different and dependent layers.