Invention Grant
- Patent Title: Natural language system question classifier, semantic representations, and logical form templates
-
Application No.: US14977334Application Date: 2015-12-21
-
Publication No.: US10262062B2Publication Date: 2019-04-16
- Inventor: Walter Wei-Tuh Chang , Codruta L. Girlea
- Applicant: Adobe Inc.
- Applicant Address: US CA San Jose
- Assignee: Adobe Inc.
- Current Assignee: Adobe Inc.
- Current Assignee Address: US CA San Jose
- Agency: Wolfe-SBMC
- Main IPC: G06F17/27
- IPC: G06F17/27 ; G06F17/28 ; G06F17/30 ; G06F17/24 ; G06N99/00 ; G10L15/18 ; G10L15/06

Abstract:
Natural language system question classifier, semantic representations, and logical form template techniques and systems are described. In one or more implementations, a natural language input is classified as corresponding to respective ones of a plurality of classes of questions. A semantic intent of the natural language input is extracted as a semantic entity and a semantic representation. Question classification labels that classify the question included in the natural language input is then used to select at least one of a plurality of logical form templates. The semantic intent that is extracted from the natural language input is then used to fill in the selected logical form templates, such as to fill in entity, subject, predicate, and object slots using the semantic entity and semantic representation. The filled-in logical form template is then mapped to form a database query that is then executed to query a database to answer the question.
Public/Granted literature
- US20170177715A1 Natural Language System Question Classifier, Semantic Representations, and Logical Form Templates Public/Granted day:2017-06-22
Information query