תקציר
Style transfer is one of the most intriguing hallmarks of natural language processing. It involves the semantic preserving conversion of artistic 'style'. Style transfer of the Hebrew language is an exceptionally challenging task due to the language's intricate morphology, inflectional structure, and orthography, which have undergone significant transformations throughout its history. In this work, we present the first generative language model for unsupervised textual style transfer for modern Hebrew, which rewrites sentences in a target style in the absence of parallel style corpora. We create a pseudo-parallel corpus through back translation, fine-tunes a pre-trained Hebrew language model, and leverages zero-shot learning. Our results demonstrate the first significant results in Hebrew style transfer in terms of transfer accuracy, semantic similarity, and fluency.
שפה מקורית | אנגלית |
---|---|
כותר פרסום המארח | Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023 |
עורכים | Jingrui He, Themis Palpanas, Xiaohua Hu, Alfredo Cuzzocrea, Dejing Dou, Dominik Slezak, Wei Wang, Aleksandra Gruca, Jerry Chun-Wei Lin, Rakesh Agrawal |
מוציא לאור | Institute of Electrical and Electronics Engineers Inc. |
עמודים | 4646-4653 |
מספר עמודים | 8 |
מסת"ב (אלקטרוני) | 9798350324457 |
מזהי עצם דיגיטלי (DOIs) | |
סטטוס פרסום | פורסם - 2023 |
אירוע | 2023 IEEE International Conference on Big Data, BigData 2023 - Sorrento, איטליה משך הזמן: 15 דצמ׳ 2023 → 18 דצמ׳ 2023 |
סדרות פרסומים
שם | Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023 |
---|
כנס
כנס | 2023 IEEE International Conference on Big Data, BigData 2023 |
---|---|
מדינה/אזור | איטליה |
עיר | Sorrento |
תקופה | 15/12/23 → 18/12/23 |
הערה ביבליוגרפית
Publisher Copyright:© 2023 IEEE.