Invention Grant
- Patent Title: Question answering from minimal context over documents
-
Application No.: US15980207Application Date: 2018-05-15
-
Publication No.: US11227218B2Publication Date: 2022-01-18
- Inventor: Sewon Min , Victor Zhong , Caiming Xiong , Richard Socher
- Applicant: salesforce.com, inc.
- Applicant Address: US CA San Francisco
- Assignee: salesforce.com, inc.
- Current Assignee: salesforce.com, inc.
- Current Assignee Address: US CA San Francisco
- Agency: Haynes and Boone, LLP
- Main IPC: G06F40/30
- IPC: G06F40/30 ; G06N20/00 ; G06N3/08 ; G06N5/04 ; G06N3/04 ; G06F40/20

Abstract:
A natural language processing system that includes a sentence selector and a question answering module. The sentence selector receives a question and sentences that are associated with a context. For a question and each sentence, the sentence selector determines a score. A score represents whether the question is answerable with the sentence. Sentence selector then generates a minimum set of sentences from the scores associated with the question and sentences. The question answering module generates an answer for the question from the minimum set of sentences.
Public/Granted literature
- US20190258939A1 Question Answering From Minimal Context Over Documents Public/Granted day:2019-08-22
Information query