Multi-Domain Adaptation in Neural Machine Translation Through Multidimensional Tagging
This addresses the need for efficient multi-domain adaptation in industrial NMT systems, such as for e-commerce or content platforms, though it is incremental in its approach.
The paper tackles the problem of neural machine translation across multiple closely related sub-domains, proposing MDT, a method that uses multidimensional tagging to simultaneously fine-tune on several sub-domains, achieving results competitive to specialist models while reducing development and maintenance costs.
While NMT has achieved remarkable results in the last 5 years, production systems come with strict quality requirements in arbitrarily niche domains that are not always adequately covered by readily available parallel corpora. This is typically addressed by training domain specific models, using fine-tuning methods and some variation of back-translation on top of in-domain monolingual corpora. However, industrial practitioners can rarely afford to focus on a single domain. A far more typical scenario includes a set of closely related, yet succinctly different sub-domains. At Booking.com, we need to translate property descriptions, user reviews, as well as messages, (for example those sent between a customer and an agent or property manager). An editor might need to translate articles across a set of different topics. An e-commerce platform would typically need to translate both the description of each item and the user generated content related to them. To this end, we propose MDT: a novel method to simultaneously fine-tune on several sub-domains by passing multidimensional sentence-level information to the model during training and inference. We show that MDT achieves results competitive to N specialist models each fine-tuned on a single constituent domain, while effectively serving all N sub-domains, therefore cutting development and maintenance costs by the same factor. Besides BLEU (industry standard automatic evaluation metric known to only weakly correlate with human judgement) we also report rigorous human evaluation results for all models and sub-domains as well as specific examples that better contextualise the performance of each model in terms of adequacy and fluency. To facilitate further research, we plan to make the code available upon acceptance.