# Named Entity Recognition for Nepali Language

## TL;DR

This paper introduces a neural network model for Nepali Named Entity Recognition that outperforms previous models significantly, requiring no manual feature engineering or extensive data preprocessing.

## Contribution

It presents the first neural-based Nepali NER model using a grapheme-level architecture that surpasses existing feature-based and neural models in accuracy.

## Key findings

- 33% to 50% improvement over feature-based SVM
- up to 10% improvement over existing neural models
- no hand-crafted features or data pre-processing needed

## Abstract

Named Entity Recognition have been studied for different languages like English, German, Spanish and many others but no study have focused on Nepali language. In this paper we propose a neural based Nepali NER using latest state-of-the-art architecture based on grapheme-level which doesn't require any hand-crafted features and no data pre-processing. Our novel neural based model gained relative improvement of 33% to 50% compared to feature based SVM model and up to 10% improvement over state-of-the-art neural based model developed for languages beside Nepali.