@inproceedings{hatch-richardson-2025-semitic,
    title = "{S}emitic Root Encoding: Tokenization Based on the Templatic Morphology of {S}emitic Languages in {NMT}",
    author = "Hatch, Brendan T.  and
      Richardson, Stephen D.",
    editor = "Darwish, Kareem  and
      Ali, Ahmed  and
      Abu Farha, Ibrahim  and
      Touileb, Samia  and
      Zitouni, Imed  and
      Abdelali, Ahmed  and
      Al-Ghamdi, Sharefah  and
      Alkhereyf, Sakhar  and
      Zaghouani, Wajdi  and
      Khalifa, Salam  and
      AlKhamissi, Badr  and
      Almatham, Rawan  and
      Hamed, Injy  and
      Alyafeai, Zaid  and
      Alowisheq, Areeb  and
      Inoue, Go  and
      Mrini, Khalil  and
      Alshammari, Waad",
    booktitle = "Proceedings of The Third Arabic Natural Language Processing Conference",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.arabicnlp-main.3/",
    pages = "26--41",
    ISBN = "979-8-89176-352-4",
    abstract = "The morphological structure of Semitic languages, such as Arabic, is based on non-concatenative 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."
}