Preserving Ambiguities in Generation via Automata Intersection

We discuss the problem of generating text that preserves certain ambiguities, a capability that is useful in applications such as machine translation. We show that it is relatively simple to extend a hybrid symbolic/statistical generator to do ambiguity preservation. The paper gives algorithms and examples, and it discusses practical linguistic difficulties that arise in ambiguity preservation.

Authors

• Kevin Knight and Irene Langkilde University of Southern California

Keywords

No keywords are indexed for this paper.