Preventing translation quality deterioration caused by beam search decoding in neural machine translation using statistical machine translation

Simple item page
dc.contributor.authorSatir E.
dc.contributor.authorBulut H.
dc.date.accessioned2024-07-22T08:05:23Z
dc.date.available2024-07-22T08:05:23Z
dc.date.issued2021
dc.description.abstractDecoding is an important part of machine translation systems, and the most popular inference algorithm used here is beam search. Beam search algorithm improves translation by allowing a larger search space to be traversed than greedy search. However, as the beam width increases, the translation performance declines after a certain point in neural machine translation (NMT). This problem is usually not observed in statistical machine translation (SMT) due to the decoding method. This paper proposes a hybrid system-based method that uses SMT predictions to prevent quality deterioration in the beam search algorithm used in NMT decoding. Our approach is based on the reranking n-best list of NMT according to the SMT system translation sentence. We propose two different algorithms for reranking NMT n-best lists. The first algorithm uses the length information of the SMT outputs. In contrast, the second uses a word-based similarity approach with the Jaccard Index, the Dice's Coefficient, and the Overlap Coefficient. Experiments on three different language pairs show that the method we propose prevents the decrease in translation quality and produces a gain of 1.3 BLEU and 1.6 METEOR for different beam sizes and 1.8 BLEU and 2.1 METEOR average scores compared to the baseline results. © 2021
dc.identifier.DOI-ID10.1016/j.ins.2021.10.006
dc.identifier.issn00200255
dc.identifier.urihttp://akademikarsiv.cbu.edu.tr:4000/handle/123456789/13115
dc.language.isoEnglish
dc.publisherElsevier Inc.
dc.subjectComputational linguistics
dc.subjectComputer aided language translation
dc.subjectDecoding
dc.subjectDeterioration
dc.subjectHybrid systems
dc.subjectInference engines
dc.subjectLearning algorithms
dc.subjectSignal encoding
dc.subjectBeam search
dc.subjectBeam search algorithms
dc.subjectInference algorithm
dc.subjectMachine translation systems
dc.subjectN-best list
dc.subjectQuality deteriorations
dc.subjectRe-ranking
dc.subjectSearch spaces
dc.subjectStatistical machine translation
dc.subjectTranslation quality
dc.subjectNeural machine translation
dc.titlePreventing translation quality deterioration caused by beam search decoding in neural machine translation using statistical machine translation
dc.typeArticle

Files

Collections

Scopus Koleksiyonu