Paper: Uses of Monolingual In-Domain Corpora for Cross-Domain Adaptation with Hybrid MT Approaches

ACL ID W13-2817
Title Uses of Monolingual In-Domain Corpora for Cross-Domain Adaptation with Hybrid MT Approaches
Venue Workshop on Hybrid Approaches to Translation
Session
Year 2013
Authors

Resource limitation is challenging for cross- domain adaption. This paper employs patterns identified from a monolingual in-domain cor- pus and patterns learned from the post-edited translation results, and translation model as well as language model learned from pseudo bilingual corpora produced by a baseline MT system. The adaptation from a government document domain to a medical record domain shows the rules mined from the monolingual in-domain corpus are useful, and the effect of using the selected pseudo bilingual corpus is significant.