Handling Translation Divergences: Combining Statistical and Symbolic Techniques in Generation-Heavy Machine Translation
Abstract
This paper describes a novel approach to handling translation divergences in a Generation-Heavy Hybrid Machine Translation (GHMT) system. The translation divergence problem is usually reserved for Transfer and Interlingual MT because it requires a large combination of complex lexical and structural mappings. A major requirement of these approaches is the accessibility of large amounts of explicit symmetrical knowledge for both source and target languages. This limitation renders Transfer and Interlingual approaches ineffective in the face of structurally-divergent language pairs with asymmetrical resources. GHMT addresses the more common form of this problem, source-poor/target-rich, by fully exploiting symbolic and statistical target-language resources. This is accomplished by using target-language lexical semantics, categorial variations and subcategorization frames to overgenerate multiple lexico-structural variations from a target-glossed syntactic dependency of the source-language sentence. The symbolic over-generation, which accounts for different possible translation divergences, is constrained by a statistical target-language model.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 2002
- Accession Number
- ADA458925
Entities
People
- Bonnie J. Dorr
- Nizar Habash
Organizations
- University of Maryland