Semitic Root Encoding: Tokenization Based on the Templatic Morphology of Semitic Languages in NMT
Year: 2025
Type: conference-paper
Abstract: The morphological structure of Semitic languages, such as Arabic, is based on nonconcatenative roots and templates.This complex word structure used by humans is obscured to neural models that employ traditional tokenization algorithms, such as byte-pair encoding (BPE) (Sennrich et al., 2016;Gage, 1994).In this work, we present and evaluate Semitic Root Encoding (SRE), a tokenization method that represents both concatenative and non-concatenative structures in Semitic words with sequences of root, template stem, and BPE tokens.We apply the method to neural machine translation (NMT) and find that SRE tokenization yields an average increase of 1.15 BLEU over the baseline.SRE tokenization is also robust against generating combinations of roots with template stems that do not occur in nature.Finally, we compare the performance of SRE to tokenization based on non-linguistic root and template structures and tokenization based on stems, providing evidence that NMT models are capable of leveraging tokens based on non-concatenative Semitic morphology.
Authors: Brendan T. Hatch, Stephen D. Richardson
Institution: Brigham Young University
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4416037689
FWCI:
Cites:
Cited by:
Related to: