20.500.12556/DKUM-92312 On the use of morpho-syntactic description tags in neural machine translation with small and large training corpora With the transition to neural architectures, machine translation achieves very good quality for several resource-rich languages. However, the results are still much worse for languages with complex morphology, especially if they are low-resource languages. This paper reports the results of a systematic analysis of adding morphological information into neural machine translation system training. Translation systems presented and compared in this research exploit morphological information from corpora in different formats. Some formats join semantic and grammatical information and others separate these two types of information. Semantic information is modeled using lemmas and grammatical information using Morpho-Syntactic Description (MSD) tags. Experiments were performed on corpora of different sizes for the English–Slovene language pair. The conclusions were drawn for a domain-specific translation system and for a translation system for the general domain. With MSD tags, we improved the performance by up to 1.40 and 1.68 BLEU points in the two translation directions. We found that systems with training corpora in different formats improve the performance differently depending on the translation direction and corpora size. neural machine translation POS tags MSD tags inflected language data sparsity corpora size strojno prevajanje jezik redkost podatkov velikost telesa true false true MDPI AG Angleški jezik Slovenski jezik https://www.mdpi.com/journal/mathematics © 2022 by the authors Članek v reviji 2025-03-28 12:21:41 2025-03-28 12:21:41 2025-03-29 03:12:48 0000-00-00 00:00:00 2022 0 0 21 str. no. 9 Vol. 10 2022 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2022-01-31 2022-05-06 2022-05-09 004.5 107195395 10.3390/math10091608 2227-7390 mathematics-10-01608-v2.pdf mathematics-10-01608-v2.pdf 1 72D7F80C90A379F904D01A7DC8D27267 ef55e0bac045c8dcf06b72a6a101df506147cf909c61d8fad177549a76fdbb7d ff8d9174-0bc6-11f0-af5a-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=189783 https://www.mdpi.com/2227-7390/10/9/1608 0 040d0ba3-0bc7-11f0-af5a-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=189784 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0