Statistical Machine Translation for bilingually low-resource scenarios

a round-tripping approach

Benyamin Ahmadnia, Gholamreza Haffari, Javier Serrano

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

2 Citations (Scopus)

Abstract

In this paper we apply the round-tripping algorithm to Statistical Machine Translation (SMT) for making effective use of monolingual data to tackle the training data scarcity. In this approach, the outbound-trip (forward) and inbound-trip (backward) translation tasks make a closed loop, and produce informative feedback to train the translation models. Based on this produced feedback we iteratively update the forward and backward translation models. The experimental results show that translation quality is improved for Persian\leftrightarrow Spanish translation task.

Original languageEnglish
Title of host publication5th International IEEE Congress on Information Science and Technology, IEEE CiSt'18
Subtitle of host publicationMarrakech, Morocco, October 21-27, 2018
EditorsIsmaii Jeiiouii
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages261-265
Number of pages5
ISBN (Electronic)9781538643853
ISBN (Print)9781538643860
DOIs
Publication statusPublished - 2018
EventInternational Congress on Information Science and Technology 2018 - Marrakech, Morocco
Duration: 21 Oct 201827 Oct 2018
Conference number: 5th
http://www.ieee.ma/cist18/

Publication series

NameColloquium in Information Science and Technology, CIST
Volume2018-October
ISSN (Print)2327-185X
ISSN (Electronic)2327-1884

Conference

ConferenceInternational Congress on Information Science and Technology 2018
Abbreviated titleCiSt 2018
CountryMorocco
CityMarrakech
Period21/10/1827/10/18
Internet address

Keywords

  • low-resource languages
  • natural language processing
  • round-tripping algorithm
  • statistical machine translation

Cite this

Ahmadnia, B., Haffari, G., & Serrano, J. (2018). Statistical Machine Translation for bilingually low-resource scenarios: a round-tripping approach. In I. Jeiiouii (Ed.), 5th International IEEE Congress on Information Science and Technology, IEEE CiSt'18: Marrakech, Morocco, October 21-27, 2018 (pp. 261-265). [8596614] (Colloquium in Information Science and Technology, CIST; Vol. 2018-October). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CIST.2018.8596614
Ahmadnia, Benyamin ; Haffari, Gholamreza ; Serrano, Javier. / Statistical Machine Translation for bilingually low-resource scenarios : a round-tripping approach. 5th International IEEE Congress on Information Science and Technology, IEEE CiSt'18: Marrakech, Morocco, October 21-27, 2018. editor / Ismaii Jeiiouii. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 261-265 (Colloquium in Information Science and Technology, CIST).
@inproceedings{916a2b38da40497f94808f74cf2db6d1,
title = "Statistical Machine Translation for bilingually low-resource scenarios: a round-tripping approach",
abstract = "In this paper we apply the round-tripping algorithm to Statistical Machine Translation (SMT) for making effective use of monolingual data to tackle the training data scarcity. In this approach, the outbound-trip (forward) and inbound-trip (backward) translation tasks make a closed loop, and produce informative feedback to train the translation models. Based on this produced feedback we iteratively update the forward and backward translation models. The experimental results show that translation quality is improved for Persian\leftrightarrow Spanish translation task.",
keywords = "low-resource languages, natural language processing, round-tripping algorithm, statistical machine translation",
author = "Benyamin Ahmadnia and Gholamreza Haffari and Javier Serrano",
year = "2018",
doi = "10.1109/CIST.2018.8596614",
language = "English",
isbn = "9781538643860",
series = "Colloquium in Information Science and Technology, CIST",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
pages = "261--265",
editor = "Ismaii Jeiiouii",
booktitle = "5th International IEEE Congress on Information Science and Technology, IEEE CiSt'18",
address = "United States of America",

}

Ahmadnia, B, Haffari, G & Serrano, J 2018, Statistical Machine Translation for bilingually low-resource scenarios: a round-tripping approach. in I Jeiiouii (ed.), 5th International IEEE Congress on Information Science and Technology, IEEE CiSt'18: Marrakech, Morocco, October 21-27, 2018., 8596614, Colloquium in Information Science and Technology, CIST, vol. 2018-October, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 261-265, International Congress on Information Science and Technology 2018, Marrakech, Morocco, 21/10/18. https://doi.org/10.1109/CIST.2018.8596614

Statistical Machine Translation for bilingually low-resource scenarios : a round-tripping approach. / Ahmadnia, Benyamin; Haffari, Gholamreza; Serrano, Javier.

5th International IEEE Congress on Information Science and Technology, IEEE CiSt'18: Marrakech, Morocco, October 21-27, 2018. ed. / Ismaii Jeiiouii. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 261-265 8596614 (Colloquium in Information Science and Technology, CIST; Vol. 2018-October).

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

TY - GEN

T1 - Statistical Machine Translation for bilingually low-resource scenarios

T2 - a round-tripping approach

AU - Ahmadnia, Benyamin

AU - Haffari, Gholamreza

AU - Serrano, Javier

PY - 2018

Y1 - 2018

N2 - In this paper we apply the round-tripping algorithm to Statistical Machine Translation (SMT) for making effective use of monolingual data to tackle the training data scarcity. In this approach, the outbound-trip (forward) and inbound-trip (backward) translation tasks make a closed loop, and produce informative feedback to train the translation models. Based on this produced feedback we iteratively update the forward and backward translation models. The experimental results show that translation quality is improved for Persian\leftrightarrow Spanish translation task.

AB - In this paper we apply the round-tripping algorithm to Statistical Machine Translation (SMT) for making effective use of monolingual data to tackle the training data scarcity. In this approach, the outbound-trip (forward) and inbound-trip (backward) translation tasks make a closed loop, and produce informative feedback to train the translation models. Based on this produced feedback we iteratively update the forward and backward translation models. The experimental results show that translation quality is improved for Persian\leftrightarrow Spanish translation task.

KW - low-resource languages

KW - natural language processing

KW - round-tripping algorithm

KW - statistical machine translation

UR - http://www.scopus.com/inward/record.url?scp=85061430540&partnerID=8YFLogxK

U2 - 10.1109/CIST.2018.8596614

DO - 10.1109/CIST.2018.8596614

M3 - Conference Paper

SN - 9781538643860

T3 - Colloquium in Information Science and Technology, CIST

SP - 261

EP - 265

BT - 5th International IEEE Congress on Information Science and Technology, IEEE CiSt'18

A2 - Jeiiouii, Ismaii

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Ahmadnia B, Haffari G, Serrano J. Statistical Machine Translation for bilingually low-resource scenarios: a round-tripping approach. In Jeiiouii I, editor, 5th International IEEE Congress on Information Science and Technology, IEEE CiSt'18: Marrakech, Morocco, October 21-27, 2018. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 261-265. 8596614. (Colloquium in Information Science and Technology, CIST). https://doi.org/10.1109/CIST.2018.8596614