|
Natural Language Processing LabDepartment of Computer Science & EngineeringTezpur University, Napaam, India - 784028 |
|
Currently available resources: International Phonetics Alphabet Typing Tool - An offline Unicode International Phonetics Alphabet (IPA) typing tool useful for phonetic transcription Geetanjali (Ramdhenu) to Unicode Converter - Geetanjali font text to Unicode Assamese converter Most Frequent 2000 Assamese words [from EMILLE corpus] - List of most frequent 2000 words with frequency. Assamese stop word list - An incomplete list of Assamese stop words. Assamese to Roman script converter - A packaged written in C to convert Assamese Luit font to Roman Script. Roman To Unicode Assamese converter - A packaged written in Java to convert Roman script to Unicode Assamese. Morphological Analyzer Parts of speech tagset (Hierarchical) - A hierarchical tagset [3-level] designed specifically for Assamese language. Parts of speech tagset (Flat) - A tagset consisting of 172 tags for Assamese Language. Parts of speech tagger for Assamese - An Assamese POS tagger package written in C++ with accuracy 85.64% tezuBank : Collection of Assamese (200 sentences) parse tree for Assamese Named Entity
Recognition for Assamese: Dialectal
Speech Synthesis: NLP
Resources for Manipuri: |
||