Skip to content

Latest commit

 

History

History
10 lines (7 loc) · 572 Bytes

README.md

File metadata and controls

10 lines (7 loc) · 572 Bytes

Part-of-Speech-Tagger

Definition

A POS (Part-of-speech) tagger to grammatically classify tokens (noun, verb, adjective...) in a sentence.

Model

I've used a pre-trained model name ParsBERT, a transformer-based Persian language understanding model, and a monolingual one based on Google's BERT architecture.

Data

I've used Bijankhan Corpus for this task. You can access it here.