In this paper we present results on developing robust natural language interfaces by combining shallowand partialinterpretationwith dialoguemanagement. The key issue is to reduce ...
Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...
The Person Cross Document Coreference systems depend on the context for making decisions on the possible coreferences between person name mentions. The amount of context required ...
Background: The behaviors of cells in metazoans are context dependent, thus large-scale multicellular modeling is often necessary, for which cellular automata are natural candidat...
We empirically show that there are significant differences between the discourse structure of Japanese texts and the discourse structure of their corresponding English translation...