@inproceedings{ansari-etal-2026-multi,
    title = "Multi-modal Neural Machine Translation for Low-Resource Classical {P}ersian Poetry: A Culture-Aware Evaluation",
    author = "Ansari, Soheila  and
      Boukadoum, Mounir  and
      Sadat, Fatiha",
    editor = "Merchant, Rayyan  and
      Megerdoomian, Karine",
    booktitle = "The Proceedings of the First Workshop on {NLP} and {LLM}s for the {I}ranian Language Family",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.silkroadnlp-1.14/",
    pages = "131--139",
    ISBN = "979-8-89176-371-5",
    abstract = "Persian poetry, particularly Rumi{'}s Masnaviye-Ma{'}navi, is known for its complex form, mystical narrative style, rich cultural information, and linguistic nuances, and is considered a low-resource domain. Translating Persian poetry is a challenging task for neural machine translation (NMT) systems. To address this challenge, we present a novel multimodal NMT system for Rumi{'}s Masnavi in four stages. First, we built a new multi-modal parallel Persian-English corpus of 26,571 aligned verses from all six books of Masnavi, and all paired with aligned audio recitations. Second, a strong text-only baseline is developed by applying domain-adaptive fine-tuning to mBART- 50, pre-trained on a large monolingual Persian poetry corpus, followed by training on the parallel Masnavi corpus (train set). Third, we extend this model to a multi-modal scenario by adding aligned audio representations using a cross-attention fusion mechanism. Fourth, we conduct a culture-aware evaluation. We propose a culture-specific item (CSI) evaluation approach by developing a CSI classification system and a Persian-English CSI dictionary alongside the standard MT metrics. Our findings demonstrate that integrating audio recitations increased the BLEU score from 9.85 to 17.95, and raised CSI-recall from 61.60{\%} to 82.04{\%}, suggesting greater consistency in producing culturally meaningful terms."
}