One of the biggest problems for automatic translation is dealing with words and inflections that are obligatory in the target language but not in the source. This work is the first to provide a fully implemented solution to the problem of generating determiners and determining number: using a semantic representation and a series of three heuristic algorithms, this solution provides the most probable context-sensitive translation. Along with an extensive evaluation of the algorithms, this book offers much insight into natural language processing, machine translation, semantic analysis, and generation from underspecified inputs.