A word alignment study to improve the reliability of the statistical and neural translation system
Safae Berrichi and
Azzeddine Mazroui
International Journal of Networking and Virtual Organisations, 2022, vol. 26, issue 1/2, 104-124
Abstract:
Word alignment is an essential task for numerous natural language processing applications, including machine translation. The performance of the statistical machine translation systems is directly impacted by the performance of their alignment modules. However, such alignment models perform worse and induce low machine translation performance when translating morphological rich or low resource languages. The first objective of this paper is to examine the impact of incorporating some morphosyntactic features on the statistical alignment models and on the associated translation systems for the (Arabic, English) language pair, and to identify which of these features is most suitable. Although the neural machine translation system does not directly include a concept of word alignment, we propose, in the second part of this work, a method of adjusting the attention mechanism of these systems by the statistical alignments. Experimental results show that the proposed approaches significantly improve the alignment and the translation performances.
Keywords: morphosyntactic representation; statistical word alignment; attention mechanism; statistical translation; neural translation; Arabic language. (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:
Downloads: (external link)
http://www.inderscience.com/link.php?id=121915 (text/html)
Access to full text is restricted to subscribers.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:ids:ijnvor:v:26:y:2022:i:1/2:p:104-124
Access Statistics for this article
More articles in International Journal of Networking and Virtual Organisations from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().