Comparing Recurrent and Convolutional Architectures for English-Hindi Neural Machine Translation

2017-11-01WS 2017Unverified0· sign in to hype

S. Singh, hya, Ritesh Panjwani, Anoop Kunchukuttan, Pushpak Bhattacharyya

Unverified — Be the first to reproduce this paper.

Abstract

In this paper, we empirically compare the two encoder-decoder neural machine translation architectures: convolutional sequence to sequence model (ConvS2S) and recurrent sequence to sequence model (RNNS2S) for English-Hindi language pair as part of IIT Bombay's submission to WAT2017 shared task. We report the results for both English-Hindi and Hindi-English direction of language pair.

Tasks

Decoder Image Captioning Language Modeling Language Modelling Machine Translation Question Answering Translation Word Embeddings

Comparing Recurrent and Convolutional Architectures for English-Hindi Neural Machine Translation

Abstract

Tasks

Reproductions