Multi-modal Neural Machine Translation for Low-Resource Classical Persian Poetry: A Culture-Aware Evaluation

Soheila Ansari, Mounir Boukadoum, Fatiha Sadat


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.
Anthology ID:
2026.silkroadnlp-1.14
Volume:
The Proceedings of the First Workshop on NLP and LLMs for the Iranian Language Family
Month:
March
Year:
2026
Address:
Rabat, Morocco
Editors:
Rayyan Merchant, Karine Megerdoomian
Venues:
SilkRoadNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
131–139
Language:
URL:
https://aclanthology.org/2026.silkroadnlp-1.14/
DOI:
Bibkey:
Cite (ACL):
Soheila Ansari, Mounir Boukadoum, and Fatiha Sadat. 2026. Multi-modal Neural Machine Translation for Low-Resource Classical Persian Poetry: A Culture-Aware Evaluation. In The Proceedings of the First Workshop on NLP and LLMs for the Iranian Language Family, pages 131–139, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
Multi-modal Neural Machine Translation for Low-Resource Classical Persian Poetry: A Culture-Aware Evaluation (Ansari et al., SilkRoadNLP 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.silkroadnlp-1.14.pdf