Neural Machine Translation advised by Statistical Machine Translation: the case of Farsi-Spanish bilingually low-resource scenario

Benyamin Ahmadnia, Parisa Kordjamshidi, Gholamreza Haffari

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

6 Citations (Scopus)

Abstract

In this paper, we propose a sequence-to-sequence NMT model on Farsi-Spanish bilingually low-resource language pair. We apply effective preprocessing steps specific for Farsi language and optimize the model for both translation and transliteration. We also propose a loss function that enhances the word alignment and consequently improves translation quality.

Original languageEnglish
Title of host publicationProceedings - 17th IEEE International Conference on Machine Learning and Applications
EditorsM. Arif Wani, Mehmed Kantardzic, Moamar Sayed-Mouchaweh, Joao Gama, Edwin Lughofer
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1209-1213
Number of pages5
ISBN (Electronic)9781538668047
ISBN (Print)9781538668061
DOIs
Publication statusPublished - 2018
EventIEEE International Conference on Machine Learning and Applications 2018 - Orlando, United States of America
Duration: 17 Dec 201820 Dec 2018
Conference number: 17th
https://www.icmla-conference.org/icmla18/

Conference

ConferenceIEEE International Conference on Machine Learning and Applications 2018
Abbreviated titleICMLA 2018
CountryUnited States of America
CityOrlando
Period17/12/1820/12/18
Internet address

Keywords

  • Natural language processing
  • Neural machine translation
  • Statistical machine translation

Cite this