Improving Low-Resource Translation with Finite State Grammars

<p>Scarcity of training data continues to pose a problem for the development of neural machine translation systems for low-resource languages. This study develops a method for the incorporation of linguistic information into the training of neural machine translation models for low-resource languages, using morphological grammars created using finite state transducers. This study explores the benefits, historical background, and effectiveness of this approach. This study incorporates morphological tags into a pre-trained multilingual neural machine translation model using a dual encoder structure. This study finds an improvement in performance in the Irish-English translation scenario. This method offers promising results with low computational requirements, and contributes to the understanding of techniques for low resource neural machine translation.</p>

Name thesis:degree_name

Master of Arts

Level thesis:degree_level

Master

Discipline thesis:degree_discipline

Linguistics

Grantor

The Graduate School and University Center of The City University of New York

Year dc:date.available

2025

Author dc:creator

• Uva, Nicholas J

Advisor dc:contributor.advisor

• Kyle Gorman

• Computational Linguistics
• linguistics
• natural language processing
• translation
• machine translation
• low-resource
• finite state
• finite state grammar
• morphology

Repository record dc:identifier

https://academicworks.cuny.edu/gc_etds/6124

OAI identifier oai:identifier

oai:academicworks.cuny.edu:gc_etds-7237