logo

For the Inventor, By the Inventor

The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Patent No.:

US 11775839 B1

PDFFull Text
Date of Patent:
Oct. 03, 2023

Filed:

Jun. 10, 2020

Frequently asked questions and document retrieval using bidirectional encoder representations from transformers (bert) model trained on generated paraphrases

Applicant:

International Business Machines Corporation, Armonk, NY (US);

Inventors:

Yosi Mass, Ramat Gan, IL;

Boaz Carmeli, Koranit, IL;

Haggai Roitman, Yoknea'm Elit, IL;

David Konopnicki, Haifa, IL;

Assignee:

International Business Machines Corporation, Armonk, NY (US);

Attorney:

Barry D. Blount

Primary Examiner:

Hosain T Alam

Assistant Examiner:

Robert F May

Int. Cl.
CPC ...
G06F 16/245 (2019.01); G06N 3/088 (2023.01); G06F 16/2457 (2019.01); G06N 3/045 (2023.01);
U.S. Cl.
CPC ...
G06N 3/088 (2013.01); G06F 16/24578 (2019.01); G06N 3/045 (2023.01);
Abstract

An example system includes a processor to receive a query. The processor can retrieve ranked candidates from an index based on the query. The processor can re-rank the ranked candidates using a Bidirectional Encoder Representations from Transformers (BERT) query-question (Q-q) model trained to match queries to questions of a frequently asked question (FAQ) dataset, wherein the BERT Q-q model is fine-tuned using paraphrases generated for the questions in the FAQ dataset. The processor can return the re-ranked candidates in response to the query.

Find Patent Forward Citations

Quick Actions:

Mass, Yosi. (2023). Frequently asked questions and document retrieval using bidirectional encoder representations from transformers (bert) model trained on generated paraphrases (U.S. Patent No. 11775839). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/11775839

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…