Mitigating Stylistic Biases of Machine Translation Systems via Monolingual Corpora Only
This addresses the challenge of stylistic biases in machine translation for users needing accurate cross-lingual communication, offering a novel solution without requiring parallel data.
The paper tackled the problem of preserving stylistic nuances in neural machine translation by introducing Babel, a framework that uses only monolingual corpora to enhance stylistic fidelity, achieving 88.21% precision in detecting inconsistencies and improving stylistic preservation by 150% while maintaining high semantic similarity.
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.