Semantics-Driven Statistical Machine Translation

Semantic parsing, the task of mapping natural language sentences to logical forms, has recently played an important role in building natural language interfaces and question answering systems. In this talk, I will present three ways in which semantic parsing relates to machine translation: First, semantic parsing can be viewed *as* a translation task with many of the familiar issues, e.g., divergent hierarchical structures. Second, I discuss recent work in which semantic parsing is tackled *via* translation (more accurately, paraphrasing) techniques, where original sentences are mapped into canonical sentences encoding the logical form. Finally, I will discuss ways in which semantic parsing could be useful *for* translation. Hopefully, this talk will open a deeper dialogue between the semantic parsing and machine translation communities and generate some fresh perspectives on semantics and translation.