A general framework for building natural language understanding modules in voice search

Abstract

Mobile search is a fast-growing business. Mobile voice search provides an easier way to search for information from mobile devices using voice. Natural language understanding (NLU) is a key component technology in voice search to assure search effectiveness. This paper describes a general framework for building the NLU modules in voice search applications. The NLU task is defined as segmenting ASR output, including ASR 1-Best and ASR Word Confusion Networks, into several concepts that are necessary for high-precision search. Application data such as raw query logs, annotated queries and source database are used to train the NLU models. We instantiated this framework on a mobile business search application and demonstrated the flexibility of using this framework. We report the experimental results on this application.