US 12,169,698 B2
Systems and methods for reading comprehension for a question answering task
Akari Asai, San Francisco, CA (US); Kazuma Hashimoto, Menlo Park, CA (US); Richard Socher, Menlo Park, CA (US); and Caiming Xiong, Menlo Park, CA (US)
Assigned to Salesforce, Inc., San Francisco, CA (US)
Filed by Salesforce, Inc., San Francisco, CA (US)
Filed on Sep. 7, 2023, as Appl. No. 18/463,019.
Application 18/463,019 is a continuation of application No. 16/695,494, filed on Nov. 26, 2019, granted, now 11,775,775.
Claims priority of provisional application 62/851,048, filed on May 21, 2019.
Prior Publication US 2023/0419050 A1, Dec. 28, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); G06F 40/40 (2020.01); G06F 40/30 (2020.01)
CPC G06F 40/40 (2020.01) [G06F 40/30 (2020.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, at a pipeline neural network, an input text of a natural language question and context that provides an answer to the natural language question;
selecting, using a context selection network in the pipeline neural network, a premium context from the context, wherein the premium context includes at least two paragraphs;
determining, using a question type network in the pipeline neural network, a type of the natural language question, wherein the question type network includes a Bidirectional Encoder Representations from Transformers (BERT) model and a classification layer and further comprising training the classification layer for determining the type of the natural language question; and
determining the answer to the natural language question as a yes or no answer when the type of the natural language question is a yes or a no question.