An In-depth Walkthrough on Evolution of Neural Machine Translation
It provides a survey for researchers and practitioners interested in NMT advancements, but it is incremental as it summarizes existing work without new results.
This paper reviews the evolution of Neural Machine Translation (NMT), covering trends from early feed-forward architectures to modern models like BERT, and compares state-of-the-art approaches in the domain.
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.