Trivial Transfer Learning for Low-Resource Neural Machine Translation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F18%3A10390163" target="_blank" >RIV/00216208:11320/18:10390163 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Trivial Transfer Learning for Low-Resource Neural Machine Translation

Original language description

Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We present a simple transfer learning method, where we first train a &quot;parent&quot; model for a high-resource language pair and then continue the training on a lowresource pair only by replacing the training corpus. This &quot;child&quot; model performs significantly better than the baseline trained for lowresource pair only. We are the first to show this for targeting different languages, and we observe the improvements even for unrelated languages with different alphabets.

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

2018

Confidentiality

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

Article name in the collection

Proceedings of the Third Conference on Machine Translation, Volume 1: Research Papers

ISBN

978-1-948087-81-0

ISSN

—

e-ISSN

neuvedeno

Number of pages

9

Pages from-to

244-252

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg, PA, USA

Event location

Bruxelles, Belgium

Event date

Oct 31, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—