How to Understand Incomplete Natural Language Queries

摘要

One or more domains can be predicted by analyzing incomplete natural language expressions using the analysis of the symbols and contextual information. For each domain, the user''s likely intent is determined using the analysis of the elements and contextual information. The intent may correspond to the function of the domain application. In this case, the information necessary for the function of executing the application may be filled using the analysis of the elements and / or the context information. Thereafter, the application may be provided to the user for intent confirmation. Intentional identification with incomplete natural language representation and contextual information can be used to train one or more models used to predict user intentions based on incomplete natural language representations.