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

Read full text Summarise with VIRAT
Authors: Soheila Ansari, Mounir Boukadoum, Fatiha Sadat
Cited by: 0
References: 15

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

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.

Fields of Study & Subjects

Natural Language Processing Techniques Translation Studies and Practices Topic Modeling

Publication details

Pages
131–139
Publication date
1 January 2026
Language
EN