---
language:
- zh
tags:
- Transformer
- korean
- romanization
- person name
- 한국어
license: cc-by-nc-sa-4.0
---

# <font color="IndianRed"> Kraft (Korean Romanization From Transformer) </font>
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1aIGvyvqRdHv7QTRahhD1sf8L6yV39kxc?usp=sharing/)

The Kraft (Korean Romanization From Transformer) model translates the characters (Hangul) of a Korean person name into the Roman alphabet ([McCune–Reischauer system](https://en.wikipedia.org/wiki/McCune%E2%80%93Reischauer)). Kraft uses the Transformer architecture, which is a type of neural network architecture that was introduced in the 2017 paper "Attention Is All You Need" by Google researchers. It is designed for sequence-to-sequence tasks, such as machine translation, language modeling, and summarization.

Translating a Korean name into an English romanization is a type of machine translation task, where the input is a sequence of characters representing a Korean name, and the output is a sequence of characters representing the English romanization of that name. The Transformer model, with its attention mechanism and ability to handle input sequences of varying lengths, is well-suited to this type of task, and is able to accurately translate Korean names to English romanization. 

## <font color="IndianRed"> Model description </font>

The transformer model has an encoder and a decoder, in which the encoder takes a sentence in the source language and the decoder outputs it into the target language. 

## <font color="IndianRed"> Intended uses & limitations </font>

Note that this model primarily aims at translating Korean names into English romanization.