Armenian-Surname-Normalizer

VladTepes33/Armenian-Surname-Normalizer

Phonetic normalization of Armenian surnames (Latin script) in PHP — trigram indexing + proximity scoring for fuzzy search over diaspora archives.

PHP Stars: 0 Forks: 0 Language/NLP
armenian-languagephonetic-normalizationfuzzy-searchname-processinghistorical-data

Summary

A PHP library for phonetic normalization of Armenian surnames transcribed in Latin script, designed to handle inconsistent transliteration from diaspora archives. It applies a 10-step normalization process (lowercase, accent removal, nasal/phonetic digraph conversion, prefix/suffix stripping, etc.) to produce a canonical form, enabling fuzzy search across historical records.

View on GitHub
More in: Armenian Language NLP Toolkit →

Similar Projects

armenian-to-phonetic
Scipion/armenian-to-phonetic

A web-based tool that converts Armenian script into a Latin phonetic transcription. It consists of two HTML pages: a ...

HTML Stars: 0
liturgical-armenian-translit-js
mattash/liturgical-armenian-translit-js

A JavaScript library for transliterating Classical Armenian (Grabar) text into English using Western Armenian liturgi...

JavaScript Stars: 1
armenian-transliteration
lobotomoe/armenian-transliteration

A comprehensive TypeScript library for transliterating Armenian text between the Armenian script and multiple target ...

TypeScript Stars: 0
armenian-transcription
vahetildian/armenian-transcription

A small Python script for transcribing Eastern Armenian text into a custom French-inspired phonetic transcription sys...

Python Stars: 0
ArmenianLatinToArmenian
haykeminyan/ArmenianLatinToArmenian

A Python library for transliterating Armenian text written in Latin script (Romanized Armenian) back to the Armenian ...

Python Stars: 0
TfjsTransliteration
aeghian/TfjsTransliteration

A Firefox browser addon that uses TensorFlow.js to transliterate Armenian words written in English letters (phonetic ...

JavaScript Stars: 0