Defining Boundaries: The Impact of Domain Specification on Cross-Language and Cross-Domain Transfer in Machine Translation
It addresses the challenge of limited parallel corpora for low-resource languages and domains in machine translation, but the approach appears incremental as it builds on existing cross-lingual transfer methods.
This paper tackles the problem of zero-shot cross-lingual domain adaptation in neural machine translation, showing that domain characteristics and language-specific factors significantly influence transfer effectiveness across languages like Portuguese, Italian, French, Czech, Polish, and Greek.
Recent advancements in neural machine translation (NMT) have revolutionized the field, yet the dependency on extensive parallel corpora limits progress for low-resource languages and domains. Cross-lingual transfer learning offers a promising solution by utilizing data from high-resource languages but often struggles with in-domain NMT. This paper investigates zero-shot cross-lingual domain adaptation for NMT, focusing on the impact of domain specification and linguistic factors on transfer effectiveness. Using English as the source language and Spanish for fine-tuning, we evaluate multiple target languages, including Portuguese, Italian, French, Czech, Polish, and Greek. We demonstrate that both language-specific and domain-specific factors influence transfer effectiveness, with domain characteristics playing a crucial role in determining cross-domain transfer potential. We also explore the feasibility of zero-shot cross-lingual cross-domain transfer, providing insights into which domains are more responsive to transfer and why. Our results show the importance of well-defined domain boundaries and transparency in experimental setups for in-domain transfer learning.