A novel hybrid approach to improve neural machine translation decoding using phrase-based statistical machine translation

Simple item page
dc.contributor.authorSatir E.
dc.contributor.authorBulut H.
dc.date.accessioned2024-07-22T08:05:38Z
dc.date.available2024-07-22T08:05:38Z
dc.date.issued2021
dc.description.abstractPhrase-based models are among the best performing statistical machine translation (SMT) systems. These systems make translations phrase-by-phrase at a time. The decoding process is done locally in these systems. In addition, neural machine translation (NMT) systems have become very popular for the past four or five years with essential features such as more fluent translations. However, sometimes NMT systems give up accuracy for fluent translations due to the nature of the decoding technique they use. In this study, we aim to develop a hybrid system by guiding NMT decoding using the output sentences of the phrase-based SMT systems. According to the two-way translation experiments, German-to-English and English-to-German, and the results obtained in terms of two popular machine translation evaluation metrics: BLEU and METEOR, our method improves the quality of NMT system translations. © 2021 IEEE.
dc.identifier.DOI-ID10.1109/INISTA52262.2021.9548401
dc.identifier.urihttp://akademikarsiv.cbu.edu.tr:4000/handle/123456789/13211
dc.language.isoEnglish
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.subjectComputational linguistics
dc.subjectComputer aided language translation
dc.subjectDecoding
dc.subjectHybrid systems
dc.subjectSpeech transmission
dc.subjectDecoding process
dc.subjectEssential features
dc.subjectFluents
dc.subjectHybrid approach
dc.subjectHybrid MT
dc.subjectMachine translation systems
dc.subjectNeural MT
dc.subjectPhrase-based models
dc.subjectPhrase-based statistical machine translation
dc.subjectStatistical machine translation system
dc.subjectNeural machine translation
dc.titleA novel hybrid approach to improve neural machine translation decoding using phrase-based statistical machine translation
dc.typeConference paper

Files

Collections

Scopus Koleksiyonu