Self-attention based end-to-end Hindi-English Neural Machine Translation

TL;DR

This paper proposes a self-attention based transformer model for Hindi-English neural machine translation, demonstrating its effectiveness over traditional models through BLEU score comparisons.

Contribution

Introduction of an end-to-end self-attention transformer model for Hindi-English NMT, with comparative analysis against existing encoder-decoder models.

Findings

Transformer model outperforms traditional encoder-decoder models

Self-attention improves translation quality for Hindi-English NMT

Model evaluation based on BLEU scores shows significant gains

Abstract

Machine Translation (MT) is a zone of concentrate in Natural Language processing which manages the programmed interpretation of human language, starting with one language then onto the next by the PC. Having a rich research history spreading over about three decades, Machine interpretation is a standout amongst the most looked for after region of research in the computational linguistics network. As a piece of this current ace's proposal, the fundamental center examines the Deep-learning based strategies that have gained critical ground as of late and turning into the de facto strategy in MT. We would like to point out the recent advances that have been put forward in the field of Neural Translation models, different domains under which NMT has replaced conventional SMT models and would also like to mention future avenues in the field. Consequently, we propose an end-to-end self-attention transformer network for Neural Machine Translation, trained on Hindi-English parallel corpus and compare the model's efficiency with other state of art models like encoder-decoder and attention-based encoder-decoder neural models on the basis of BLEU. We conclude this paper with a comparative analysis of the three proposed models.