US 11,941,348 B2
Language model for abstractive summarization
Luke Percival de Oliveira, San Francisco, CA (US); and Alfredo Láinez Rodrigo, Madrid (ES)
Assigned to Twilio Inc., San Francisco, CA (US)
Filed by Twilio Inc., San Francisco, CA (US)
Filed on Sep. 7, 2022, as Appl. No. 17/939,176.
Application 17/939,176 is a continuation of application No. 17/304,081, filed on Jun. 14, 2021, granted, now 11,475,210.
Claims priority of provisional application 63/072,538, filed on Aug. 31, 2020.
Prior Publication US 2022/0414319 A1, Dec. 29, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/04 (2023.01); G06F 40/166 (2020.01); G06F 40/284 (2020.01); G06N 3/08 (2023.01); H04M 3/51 (2006.01)
CPC G06F 40/166 (2020.01) [G06F 40/284 (2020.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); H04M 3/5183 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
accessing, by one or more processors, text to be summarized;
providing, by the one or more processors and to a trained machine-learning model, the text to be summarized and a running summary thereof, the trained machine-learning model outputting a word to be included in the running summary of the text; and
storing, by the one or more processors, the running summary including the word outputted by the trained machine-learning model.