Invention Grant
- Patent Title: Question and answer pair generation using machine learning
-
Application No.: US16101520Application Date: 2018-08-13
-
Publication No.: US11250038B2Publication Date: 2022-02-15
- Inventor: Payal Bajaj , Gearard Boland , Anshul Gupta , Matthew Glenn Jin , Eduardo Enrique Noriega De Armas , Jason Shaver , Neelakantan Sundaresan , Roshanak Zilouchian Moghaddam
- Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.
- Applicant Address: US WA Redmond
- Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.
- Current Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.
- Current Assignee Address: US WA Redmond
- Main IPC: G06F16/33
- IPC: G06F16/33 ; G06F16/332 ; G06N3/04 ; G06N5/04 ; G06F16/38 ; G06F16/951 ; G06N3/08

Abstract:
An interactive question and answer (Q&A) service provides pairs of questions and corresponding answers related to the content of a web page. The service includes pre-configured Q&A pairs derived from a deep learning framework that includes a series of neural networks trained through joint and transfer learning to generate questions for a given text passage. In addition, pre-configured Q&A pairs are generated from historical web access patterns and sources related to the content of the web page.
Public/Granted literature
- US20190228099A1 QUESTION AND ANSWER PAIR GENERATION USING MACHINE LEARNING Public/Granted day:2019-07-25
Information query