Mimicking Infants' Bilingual Language Acquisition for Domain Specialized Neural Machine Translation

Park, C.; Go, W.; Eo, S.; Moon, H.; Lee, S.; Lim, H.

doi:10.1109/ACCESS.2022.3165572

상세 보기

Mimicking Infants' Bilingual Language Acquisition for Domain Specialized Neural Machine Translation

Park, C.;
Go, W.;
Eo, S.;
Moon, H.;
Lee, S.;
... Lim, H.

Citations

WEB OF SCIENCE

5

Citations

SCOPUS

4

초록

Existing methods of training domain-specialized neural machine translation (DS-NMT) models are based on the pretrain-finetuning approach (PFA). In this study, we reinterpret existing methods based on the perspective of cognitive science related to cross language speech perception. We propose the cross communication method (CCM), a new DS-NMT training approach. Inspired by the learning method of infants, we perform DS-NMT training by configuring and training DC and GC concurrently in batches. Quantitative and qualitative analysis of our experimental results show that CCM can achieve superior performance compared to the conventional methods. Additionally, we conducted an experiment considering the DS-NMT service to meet industrial demands. © 2013 IEEE.

키워드

cross communication method; deep learning; Domain-specialized neural machine translation; neural machine translation; SPLIT-ATTENTION; NETWORK MODEL; SPEECH; DISCRIMINATION; EXPERIENCE; PERCEPTION; JAPANESE; ADULTS

제목: Mimicking Infants' Bilingual Language Acquisition for Domain Specialized Neural Machine Translation

저자: Park, C.; Go, W.; Eo, S.; Moon, H.; Lee, S.; Lim, H.

DOI: 10.1109/ACCESS.2022.3165572

발행일: 2022

유형: Article

저널명: IEEE Access

권: 10

페이지: 38684 ~ 38693