# CVIT-MT Systems for WAT-2018

## TL;DR

This paper presents IIIT-Hyderabad's machine translation system for WAT-2018, utilizing convolutional sequence-to-sequence models and backtranslation to improve English-Hindi translation performance.

## Contribution

It introduces a convolutional sequence-to-sequence architecture combined with backtranslation for English-Hindi translation in WAT-2018.

## Key findings

- Improved translation quality with convolutional models
- Effective use of backtranslation data
- Competitive performance on WAT-2018 corpus

## Abstract

This document describes the machine translation system used in the submissions of IIIT-Hyderabad CVIT-MT for the WAT-2018 English-Hindi translation task. Performance is evaluated on the associated corpus provided by the organizers. We experimented with convolutional sequence to sequence architectures. We also train with additional data obtained through backtranslation.