Fast Domain Adaptation of SMT models without in-Domain Parallel Data
Prashant Mathur, Sriram Venkatapathy, Nicola Cancedda · 2014
We address a challenging problem frequently faced by MT service providers: creating a domainspecific system based on a purely source-monolingual sample of text from the domain. We solve this problem by introducing methods for domain adaptation requiring no in-domain parallel data. Our approach yields results comparable to state-of-the-art systems optimized on an in-domain parallel set with a drop of as little as 0.5 BLEU points across 4 domains.