Improving Domain-specific Machine Translation by Constraining the Language Model
Abstract
A domain-specific statistical machine translation engine is shown to be more accurate when only domain-specific language data are used to build the target-language language model. This has been found to be true when compared to using a much larger, out-of-domain corpus for building the language model, either alone or in combination with the domain-specific data.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 01, 2012
- Accession Number
- ADA568649
Entities
People
- Jeffrey C. Micher
Organizations
- United States Army Research Laboratory