A Smaller and Better Word Embedding for Neural Machine Translation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3ASGHGDUL7" target="_blank" >RIV/00216208:11320/23:SGHGDUL7 - isvavai.cz</a>

Result on the web

<a href="https://www.webofscience.com/wos/woscc/summary/e0b8ef34-8e6b-412a-9b8f-87607433ed44-bb92f483/relevance/1" target="_blank" >https://www.webofscience.com/wos/woscc/summary/e0b8ef34-8e6b-412a-9b8f-87607433ed44-bb92f483/relevance/1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/access.2023.3270171" target="_blank" >10.1109/access.2023.3270171</a>

Result language

angličtina

Original language name

A Smaller and Better Word Embedding for Neural Machine Translation

Original language description

"Word embeddings play an important role in Neural Machine Translation (NMT). However, it still has a series of problems such as ignoring the prior knowledge of the association between words, relying on specific task constraints passively in parameter training, and isolating individual embedding's learning process from one another. In this paper, we propose a new word embedding method to add the prior knowledge of the association between words to the training process, and at the same time to share the iterative training results among all word embeddings. This method is applicable to all mainstream NMT systems. In our experiments, it achieves an improvement of +0.9 BLEU points on the WMT'14 English?German task. On the Global Voices v2018q4 Spanish?Czech low-resource translation tasks, it leads to a more prominent performance improvement over the strong baselines (a +2.6 BLEU improvement on average). As another "bonus", the new word embedding has far fewer parameters than the traditional word embedding, even as low as 15% of the parameters of the baselines."

Czech name

—

Czech description

—

Type

J_ost - Miscellaneous article in a specialist periodical

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2023

Confidentiality

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

Name of the periodical

"IEEE ACCESS"

ISSN

2169-3536

e-ISSN

—

Volume of the periodical

11

Issue of the periodical within the volume

2023

Country of publishing house

US - UNITED STATES

Number of pages

9

Pages from-to

40770-40778

UT code for WoS article

001033140800001

EID of the result in the Scopus database

—