Translating Short Segments with NMT: A Case Study in English-to-Hindi

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F18%3A10390198" target="_blank" >RIV/00216208:11320/18:10390198 - isvavai.cz</a>

Result on the web

<a href="http://rua.ua.es/dspace/handle/10045/76083" target="_blank" >http://rua.ua.es/dspace/handle/10045/76083</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Translating Short Segments with NMT: A Case Study in English-to-Hindi

Original language description

This paper presents a case study in translating short image captions of the Visual Genome dataset from English into Hindi using out-of-domain data sets of varying size. We experiment with three NMT models: the shallow and deep sequence-to-sequence and the Transformer model as implemented in Marian toolkit. Phrase-based Moses serves as the baseline. The results indicate that the Transformer model outperforms others in the large data setting in a number of automatic metrics and manual evaluation, and it also produces the fewest truncated sentences. Transformer training is however very sensitive to the hyperparameters, so it requires more experimenting. The deep sequence-to-sequence model produced more flawless outputs in the small data setting and it was generally more stable, at the cost of more training iterations.

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

<a href="/en/project/LM2015071" target="_blank" >LM2015071: Language Research Infrastructure in the Czech Republic</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2018

Confidentiality

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

Article name in the collection

Proceedings of the 21st Annual Conference of the European Association for Machine Translation (2018)

ISBN

978-84-09-01901-4

ISSN

—

e-ISSN

neuvedeno

Number of pages

392

Pages from-to

1-392

Publisher name

European Association for Machine Translation

Place of publication

Allschwil, Switzerland

Event location

Alicante, Spain

Event date

May 28, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—