# Romanian NLP

CPU-optimized Romanian natural language processing model, including tokenization, part-of-speech tagging, dependency parsing, named entity recognition, and other functions

Stanza is an efficient multilingual analysis toolkit that provides natural language processing models from raw text to syntactic parsing and entity recognition.

CPU-optimized Romanian language processing pipeline with complete NLP components including token classification, dependency parsing, and named entity recognition

This is a customized and compact version of distilbert-base-multilingual-cased for Romanian, fully replicating the original model's representational capabilities with maintained accuracy.