Mitigating Stylistic Biases of Machine Translation Systems via Monolingual Corpora Only

2025-07-16

AI Summary

Existing neural machine translation (NMT) systems struggle to preserve source-text stylistic properties, and mainstream style-control approaches rely heavily on parallel corpora, limiting their generalizability. This paper proposes Babel—a novel post-hoc NMT framework that achieves cross-lingual style fidelity using monolingual data only. Babel detects stylistic divergence between source and translation via context-aware embeddings and rectifies style discrepancies through a diffusion model operating under strict semantic constraints—without modifying the original NMT architecture or requiring parallel training data. Evaluated across five domains, Babel achieves 88.21% accuracy in identifying style inconsistencies, improves style preservation by 150%, and maintains high semantic similarity (0.92). Human evaluation confirms significant gains over baselines in fluency, adequacy, and stylistic consistency.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Diffusion Models for Vision

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Large pretrained models with web data
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

The advent of neural machine translation (NMT) has revolutionized cross-lingual communication, yet preserving stylistic nuances remains a significant challenge. While existing approaches often require parallel corpora for style preservation, we introduce Babel, a novel framework that enhances stylistic fidelity in NMT using only monolingual corpora. Babel employs two key components: (1) a style detector based on contextual embeddings that identifies stylistic disparities between source and target texts, and (2) a diffusion-based style applicator that rectifies stylistic inconsistencies while maintaining semantic integrity. Our framework integrates with existing NMT systems as a post-processing module, enabling style-aware translation without requiring architectural modifications or parallel stylistic data. Extensive experiments on five diverse domains (law, literature, scientific writing, medicine, and educational content) demonstrate Babel's effectiveness: it identifies stylistic inconsistencies with 88.21% precision and improves stylistic preservation by 150% while maintaining a high semantic similarity score of 0.92. Human evaluation confirms that translations refined by Babel better preserve source text style while maintaining fluency and adequacy.

Problem

• Enhancing stylistic fidelity in NMT without parallel corpora
• Detecting and rectifying stylistic inconsistencies in translations
• Improving style preservation across diverse domains effectively

Innovation

• Uses monolingual corpora for style preservation
• Employs style detector and diffusion applicator
• Integrates as post-processing without NMT changes