Statistical Machine Translation for Bilingually Low-Resource Scenarios: A Round-Tripping Approach

Benyamin Ahmadnia, Gholamreza Haffari, Javier Serrano

Producció científica: Capítol de llibreCapítolRecercaAvaluat per experts

7 Cites (Scopus)

Resum

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.

Idioma originalAnglès nord-americà
Títol de la publicació5th International Congress on Information Science and Technology, CiSt 2018
EditorsMohammed Al Achhab, Mohammed El Mohajir, Ismail Jellouli, Badr Eddine El Mohajir
Pàgines261-265
Nombre de pàgines5
ISBN (electrònic)9781538643853
DOIs
Estat de la publicacióPublicada - 28 de des. 2018

Sèrie de publicacions

NomColloquium in Information Science and Technology, CIST
Volum2018-October
ISSN (imprès)2327-185X
ISSN (electrònic)2327-1884

Fingerprint

Navegar pels temes de recerca de 'Statistical Machine Translation for Bilingually Low-Resource Scenarios: A Round-Tripping Approach'. Junts formen un fingerprint únic.

Com citar-ho