| Naslov: | Reduction of Neural Machine Translation Failures by Incorporating Statistical Machine Translation |
|---|
| Avtorji: | ID Dugonik, Jani (Avtor)
ID Sepesy Maučec, Mirjam (Avtor)
ID Verber, Domen (Avtor)
ID Brest, Janez (Avtor) |
|---|
| Datoteke: |  Dugonik-2023-Reduction_of_Neural_Machine_Trans.pdf (400,40 KB)
MD5: 78CC15F779EB59334CBE411B83149E2D
 https://www.mdpi.com/2227-7390/11/11/2484
|
|---|
| Jezik: | Angleški jezik |
|---|
| Vrsta gradiva: | Članek v reviji |
|---|
| Tipologija: | 1.01 - Izvirni znanstveni članek |
|---|
| Organizacija: | FERI - Fakulteta za elektrotehniko, računalništvo in informatiko
|
|---|
| Opis: | 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. |
|---|
| Ključne besede: | neural machine translation, statistical machine translation, sentence embedding, similarity, classification, hybrid machine translation |
|---|
| Status publikacije: | Objavljeno |
|---|
| Verzija publikacije: | Objavljena publikacija |
|---|
| Poslano v recenzijo: | 21.04.2023 |
|---|
| Datum sprejetja članka: | 25.05.2023 |
|---|
| Datum objave: | 28.05.2023 |
|---|
| Založnik: | MDPI |
|---|
| Leto izida: | 2023 |
|---|
| Št. strani: | Str. 1-22 |
|---|
| Številčenje: | Letn. 11, Št. 11, št. članka 2484 |
|---|
| PID: | 20.500.12556/DKUM-87120  |
|---|
| UDK: | 004.5 |
|---|
| COBISS.SI-ID: | 154543107 |
|---|
| DOI: | 10.3390/math11112484 |
|---|
| ISSN pri članku: | 2227-7390 |
|---|
| Datum objave v DKUM: | 20.02.2024 |
|---|
| Število ogledov: | 545 |
|---|
| Število prenosov: | 61 |
|---|
| Metapodatki: |    |
|---|
| Področja: | Ostalo
|
|---|
|
:
|
Kopiraj citat |
|---|
| | | | Skupna ocena: | (0 glasov) |
|---|
| Vaša ocena: | Ocenjevanje je dovoljeno samo prijavljenim uporabnikom. |
|---|
| Objavi na: |  |
|---|
Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše
podrobnosti ali sproži prenos. |
