Neural Machine Translation for English to Hindi Using GRU

EasyChair Preprint 5698

Abstract

Language translation helps people to communicate, share information and establish a worldwide relationship. Neural Machine Translation helps to build the performances since it translates text from one language into another. This paper gen- erates a summary with a headline and also compares three Neural Machine Translation models based on different Techniques for English-Hindi language pairwise: Sequence Architecture with both encoder and decoder (1) Long Short Term Memory (2) Bidirectional Long Short Term Memory (Bi-LSTM) Conditional Random Field (CRF) and (3) Gated recurrent units (GRUs) with attention mechanism applied in three models. The comparison showed that GRU is better in performances than LSTM and Bi-LSTM CRF.

Keyphrases: Natural language Processing: GRU, Neural Machine Translation, Text Summarization

@booklet{EasyChair:5698,
  author    = {P Shalu and M Meera},
  title     = {Neural Machine Translation for English to Hindi Using GRU},
  howpublished = {EasyChair Preprint 5698},
  year      = {EasyChair, 2021}}