mlsanityData to 14 Oct 2026

Multilingual Text Style Transfer: Datasets & Models for Indian Languages

arXiv 2405.20805 ↗First posted 31 May 2024cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

Text style transfer (TST) involves altering the linguistic style of a text while preserving its core 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 (Mukherjee et al., 2023). 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 (Mukherjee et al., 2023) 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.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 29 of its 53 references that are in the map. First posted on arXiv 31 May 2024.

Builds on

29 of 53 references.

References · 29

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  4. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  5. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  6. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  7. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  8. 2020Multilingual Translation with Extensible Multilingual Pretraining and Finetuningcited by 287
  9. 2017Toward Controlled Generation of Textcited by 272
  10. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 248
  11. 2017Why We Need New Evaluation Metrics for NLGcited by 233
  12. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
17 more
  1. 2020Deep Learning for Text Style Transfer: A Surveycited by 162
  2. 2017Style Transfer in Text: Exploration and Evaluationcited by 146
  3. 2022mGPT: Few-Shot Learners Go Multilingualcited by 142
  4. 2018Style Transfer Through Back-Translationcited by 124
  5. 2020Explaining Explanations: Axiomatic Feature Interactions for Deep Networkscited by 103
  6. 2019Evaluating Style Transfer for Textcited by 61
  7. 2017Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Modelscited by 57
  8. 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 52
  9. 2021Few-shot Controllable Style Transfer for Low-Resource Multilingual Settingscited by 21
  10. 2023TwistList: Resources and Baselines for Tongue Twister Generationcited by 16
  11. 2024Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokenscited by 11
  12. 2024Text Detoxification as Style Transfer in English and Hindicited by 11
  13. 2023Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoisingcited by 7
  14. 2018Automatic Identification of Closely-related Indian Languages: Resources and Experimentscited by 5
  15. 2022Low Resource Style Transfer via Domain Adaptive Meta Learningcited by 4
  16. 2023Weakly-supervised Deep Cognate Detection Framework for Low-Resourced Languages Using Morphological Knowledge of Closely-Related Languagescited by 2
  17. 2021SE-DAE: Style-Enhanced Denoising Auto-Encoder for Unsupervised Text Style Transfercited by 1

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 4.

9 papers.

  1. 2024Style-Specific Neurons for Steering LLMs in Text Style Transfercited by 24
  2. 2024Are Large Language Models Actually Good at Text Style Transfer?cited by 13
  3. 2024Multilingual and Explainable Text Detoxification with Parallel Corporacited by 12
  4. 2025Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics?cited by 7
  5. 2024Text Style Transfer: An Introductory Overviewcited by 5
  6. 2025Towards Style Alignment in Cross-Cultural Translationcited by 4
  7. 2025RusCode: Russian Cultural Code Benchmark for Text-to-Image Generationcited by 1
  8. 2025mStyleDistance: Multilingual Style Embeddings and their Evaluationcited by 1
  9. 2024A Survey of Text Style Transfer: Applications and Ethical Implicationscited by 0