Invention Grant
- Patent Title: Natural question generation from query data using natural language processing system
-
Application No.: US15480780Application Date: 2017-04-06
-
Publication No.: US10423649B2Publication Date: 2019-09-24
- Inventor: William S. Ko , Malous M. Kossarian , Douglas A. Smith , Huaiyu Zhu
- Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Applicant Address: US NY Armonk
- Assignee: International Business Machines Corporation
- Current Assignee: International Business Machines Corporation
- Current Assignee Address: US NY Armonk
- Agency: Conley Rose, P.C.
- Main IPC: G06F17/30
- IPC: G06F17/30 ; G06F16/33 ; G06F17/27 ; G06F16/35 ; G06F16/951 ; G06F16/332 ; G06F16/955

Abstract:
A training query generation system is usable to generate fully formed training questions from prior search queries, some of which may be fully formed search queries and some of which are not fully formed. The system may identify fully formed questions from a query database stored on a storage device. The query database includes a plurality of search query character string, The system further identifies partially formed questions from the query database, creates question templates from the identified fully formed questions, and stores the question templates in a template database. The system then identifies entities with the partially formed questions, classifies each entity, and stores the classified entities in an entity database. Fully formed questions can then be generated using the question templates from the template database and classified entities from the entity database.
Public/Granted literature
- US20180293302A1 NATURAL QUESTION GENERATION FROM QUERY DATA USING NATURAL LANGUAGE PROCESSING SYSTEM Public/Granted day:2018-10-11
Information query