20.500.12556/DKUM-87120 Reduction of Neural Machine Translation Failures by Incorporating Statistical Machine Translation This paper proposes a hybrid machine translation (HMT) system that improves the quality of neural machine translation (NMT) by incorporating statistical machine translation (SMT). Therefore, two NMT systems and two SMT systems were built for the Slovenian-English language pair, each for translation in one direction. We used a multilingual language model to embed the source sentence and translations into the same vector space. From each vector, we extracted features based on the distances and similarities calculated between the source sentence and the NMT translation, and between the source sentence and the SMT translation. To select the best possible translation, we used several well-known classifiers to predict which translation system generated a better translation of the source sentence. The proposed method of combining SMT and NMT in the hybrid system is novel. Our framework is language-independent and can be applied to other languages supported by the multilingual language model. Our experiment involved empirical applications. We compared the performance of the classifiers, and the results demonstrate that our proposed HMT system achieved notable improvements in the BLEU score, with an increase of 1.5 points and 10.9 points for both translation directions, respectively. neural machine translation statistical machine translation sentence embedding similarity classification hybrid machine translation nevronsko strojno prevajanje statistično strojno prevajanje podobnost klasifikacija hibridno strojno prevajanje true false true MDPI Angleški jezik Slovenski jezik https://www.mdpi.com/journal/mathematics Članek v reviji 2024-02-20 15:18:36 2024-02-20 15:27:32 2024-05-22 13:55:50 0000-00-00 00:00:00 2023 0 0 Str. 1-22 Št. 11, št. članka 2484 Letn. 11 2023 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2023-04-21 2023-05-25 2023-05-28 004.5 154543107 10.3390/math11112484 2227-7390 Dugonik-2023-Reduction_of_Neural_Machine_Trans.pdf Dugonik-2023-Reduction_of_Neural_Machine_Trans.pdf 1 78CC15F779EB59334CBE411B83149E2D a68f51766bedffb794e1ad1e13aea0f502f02942f3dacf06c94e62ad72b12fbd 073c3343-cffc-11ee-b227-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=176320 https://www.mdpi.com/2227-7390/11/11/2484 0 127f4638-cffc-11ee-b227-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=176321 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0