Decoding strategies for improving low-resource machine translation

Chanjun Park, Yeongwook Yang, Kinam Park, Heuiseok Lim

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

Pre-processing and post-processing are significant aspects of natural language processing (NLP) application software. Pre-processing in neural machine translation (NMT) includes subword tokenization to alleviate the problem of unknown words, parallel corpus filtering that only filters data suitable for training, and data augmentation to ensure that the corpus contains sufficient content. Post-processing includes automatic post editing and the application of various strategies during decoding in the translation process. Most recent NLP researches are based on the Pretrain-Finetuning Approach (PFA). However, when small and medium-sized organizations with insufficient hardware attempt to provide NLP services, throughput and memory problems often occur. These difficulties increase when utilizing PFA to process low-resource languages, as PFA requires large amounts of data, and the data for low-resource languages are often insufficient. Utilizing the current research premise that NMT model performance can be enhanced through various pre-processing and post-processing strategies without changing the model, we applied various decoding strategies to Korean–English NMT, which relies on a low-resource language pair. Through comparative experiments, we proved that translation performance could be enhanced without changes to the model. We experimentally examined how performance changed in response to beam size changes and n-gram blocking, and whether performance was enhanced when a length penalty was applied. The results showed that various decoding strategies enhance the performance and compare well with previous Korean–English NMT approaches. Therefore, the proposed methodology can improve the performance of NMT models, without the use of PFA; this presents a new perspective for improving machine translation performance.

Original languageEnglish
Article number1562
Pages (from-to)1-15
Number of pages15
JournalElectronics (Switzerland)
Volume9
Issue number10
DOIs
Publication statusPublished - 2020 Oct

Keywords

  • Decoding strategies
  • Efficiency processing
  • Korean–English neural machine translation
  • Neural machine translation
  • Post-processing
  • Transformer

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Hardware and Architecture
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Decoding strategies for improving low-resource machine translation'. Together they form a unique fingerprint.

Cite this