A method to restrict the blow-up of hypotheses of a non-disambiguated shallow machine translation system
2009
Abstract
The article presents two automatic methods that reduce the complexity of the ambiguous space introduced by the omission of the part of speech tagger from the architecture of a shallow machine translation system. The methods were implemented in a fully functional translation system for related languages.
The language pair chosen for the experiments was Slovenian-Serbian as these languages are highly inflectional with morphologically ambiguous forms. The empirical evaluations show an improvement over the original system.