The Formality Style Transformation (FST) task aims to convert informal text into formal while preserving the original meaning. It is essential to improve the performance of a variety of NLP tasks that rely on formal language input. Nevertheless, it remains challenging for low-resource languages due to the need for high-quality parallel corpora. On the other hand, languages that use non-Latin scripts, such as Persian (Farsi), are morphologically complex and underrepresented, which limits the performance of pretrained models. More specifically, informal Persian text often contains colloquial expressions, dialectal variations, non-standard spellings, and code-switching with English or Arabic words, which makes it difficult for models to generate accurate formal equivalents. In this survey, we provide a systematic overview of existing methods, datasets, and evaluation metrics for Persian formality style transformation. Finally, we discuss open challenges and identify future research directions in this domain.
Naebzadeh et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: