Multilingual Text Style Transfer: Datasets & Models for Indian Languages

Sourabrata Mukherjee, Atul Kr. Ojha, Akanksha Bansal, Deepak Alok, John P. McCrae, Ondrej Dusek


Abstract
Text style transfer (TST) involves altering the linguistic style of a text while preserving its style-independent content. This paper focuses on sentiment transfer, a popular TST subtask, across a spectrum of Indian languages: Hindi, Magahi, Malayalam, Marathi, Punjabi, Odia, Telugu, and Urdu, expanding upon previous work on English-Bangla sentiment transfer. We introduce dedicated datasets of 1,000 positive and 1,000 negative style-parallel sentences for each of these eight languages. We then evaluate the performance of various benchmark models categorized into parallel, non-parallel, cross-lingual, and shared learning approaches, including the Llama2 and GPT-3.5 large language models (LLMs). Our experiments highlight the significance of parallel data in TST and demonstrate the effectiveness of the Masked Style Filling (MSF) approach in non-parallel techniques. Moreover, cross-lingual and joint multilingual learning methods show promise, offering insights into selecting optimal models tailored to the specific language and task requirements. To the best of our knowledge, this work represents the first comprehensive exploration of the TST task as sentiment transfer across a diverse set of languages.
Anthology ID:
2024.inlg-main.41
Volume:
Proceedings of the 17th International Natural Language Generation Conference
Month:
September
Year:
2024
Address:
Tokyo, Japan
Editors:
Saad Mahamood, Nguyen Le Minh, Daphne Ippolito
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
494–522
Language:
URL:
https://aclanthology.org/2024.inlg-main.41
DOI:
Bibkey:
Cite (ACL):
Sourabrata Mukherjee, Atul Kr. Ojha, Akanksha Bansal, Deepak Alok, John P. McCrae, and Ondrej Dusek. 2024. Multilingual Text Style Transfer: Datasets & Models for Indian Languages. In Proceedings of the 17th International Natural Language Generation Conference, pages 494–522, Tokyo, Japan. Association for Computational Linguistics.
Cite (Informal):
Multilingual Text Style Transfer: Datasets & Models for Indian Languages (Mukherjee et al., INLG 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.inlg-main.41.pdf