For building question answering systems and natural language interfaces,semantic parsing has emerged as an important and powerful paradigm. Semanticparsers map natural language into logical forms, the classic representation formany important linguistic phenomena. The modern twist is that we are interestedin learning semantic parsers from data, which introduces a new layer ofstatistical and computational issues. This article lays out the components of astatistical semantic parser, highlighting the key challenges. We will see thatsemantic parsing is a rich fusion of the logical and the statistical world, andthat this fusion will play an integral role in the future of natural languageunderstanding systems.
展开▼