Improving Low-Resource Translation with Finite State Grammars

Author

Nicholas J. Uva, The Graduate Center, City University of New YorkFollow

Date of Degree

2-2025

Document Type

Thesis

Degree Name

M.A.

Program

Linguistics

Advisor

Kyle Gorman

Subject Categories

Computational Linguistics

Keywords

linguistics, natural language processing, translation, machine translation, low-resource, finite state, finite state grammar, morphology

Abstract

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.

Recommended Citation

Uva, Nicholas J., "Improving Low-Resource Translation with Finite State Grammars" (2025). CUNY Academic Works.
https://academicworks.cuny.edu/gc_etds/6124