Idiap NMT System for WAT 2019 Multi-Modal Translation Task

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10424426" target="_blank" >RIV/00216208:11320/19:10424426 - isvavai.cz</a>

Result on the web

<a href="https://www.aclweb.org/anthology/D19-5223.pdf" target="_blank" >https://www.aclweb.org/anthology/D19-5223.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Idiap NMT System for WAT 2019 Multi-Modal Translation Task

Original language description

This paper describes the Idiap submission to WAT 2019 for the English-Hindi MultiModal Translation Task. We have used the state-of-the-art Transformer model and utilized the IITB English-Hindi parallel corpus as an additional data source. Among the different tracks of the multimodal task, we have participated in the &quot;Text-Only&quot; track for the evaluation and challenge test sets. Our submission tops in its track among the competitors in terms of both automatic and manual evaluation. Based on automatic scores, our text-only submission also outperforms systems that consider visual information in the &quot;multimodal translation&quot; task.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2019

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

ISBN

978-1-950737-90-1

ISSN

—

e-ISSN

—

Number of pages

6

Pages from-to

175-180

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg, PA, USA

Event location

Hong Kong, China

Event date

Nov 3, 2019

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—