An In-depth Walkthrough on Evolution of Neural Machine Translation
Computation and Language
2024-09-05 v1 Machine Learning
Neural and Evolutionary Computing
Abstract
Neural Machine Translation (NMT) methodologies have burgeoned from using simple feed-forward architectures to the state of the art; viz. BERT model. The use cases of NMT models have been broadened from just language translations to conversational agents (chatbots), abstractive text summarization, image captioning, etc. which have proved to be a gem in their respective applications. This paper aims to study the major trends in Neural Machine Translation, the state of the art models in the domain and a high level comparison between them.
Cite
@article{arxiv.2004.04902,
title = {An In-depth Walkthrough on Evolution of Neural Machine Translation},
author = {Rohan Jagtap and Sudhir N. Dhage},
journal= {arXiv preprint arXiv:2004.04902},
year = {2024}
}
Comments
10 pages, 10 figures