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

Authors:
Open Access
Publisher website
Google Scholar
Abstract
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.
Funding Information
  • Ministry of Science and ICT (MSIT), South Korea, through the Information Technology Research Center (ITRC) support program supervised
  • Institute of Information & Communications Technology Planning & Evaluation (IITP-2018-0-01405)
  • IITP grant funded
  • Korea Government (MSIT) (2020-0-00368)
  • Basic Science Research Program through the National Research Foundation of Korea (NRF) Funded
  • Ministry of Education (NRF-2021R1A6A1A03045425)

This publication has 29 references indexed in Scilit: