US 11,657,215 B2
Robust expandable dialogue system
Percy Shuo Liang, Palo Alto, CA (US); David Leo Wright Hall, Berkeley, CA (US); Jesse Daniel Eskes Rusak, Somerville, MA (US); and Daniel Klein, Orinda, CA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Sep. 21, 2021, as Appl. No. 17/448,289.
Application 17/448,289 is a continuation of application No. 16/115,491, filed on Aug. 28, 2018, granted, now 11,132,499.
Claims priority of provisional application 62/613,995, filed on Jan. 5, 2018.
Claims priority of provisional application 62/554,456, filed on Sep. 5, 2017.
Claims priority of provisional application 62/551,200, filed on Aug. 28, 2017.
Prior Publication US 2022/0004702 A1, Jan. 6, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/06 (2013.01); G06F 40/169 (2020.01); G10L 15/16 (2006.01); G10L 15/02 (2006.01); G10L 15/183 (2013.01); G10L 15/07 (2013.01)
CPC G06F 40/169 (2020.01) [G10L 15/02 (2013.01); G10L 15/063 (2013.01); G10L 15/16 (2013.01); G10L 15/183 (2013.01); G10L 15/06 (2013.01); G10L 15/075 (2013.01); G10L 2015/0631 (2013.01); G10L 2015/0638 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method performed by a computing system for training a machine learning model for natural language interaction, the method comprising:
establishing a plurality of instances of a natural language dialogue for a domain, each instance of the natural language dialogue including a subset of utterances for the domain selected by the machine learning model;
for each instance of the natural language dialogue for the domain, receiving one or more input responses;
for each instance of the natural language dialogue for the domain, selecting a pre-defined template from a library of pre-defined templates based on the one or more input responses, the selected pre-defined template including an assistive action and one or more generalized paths;
receiving for each selected pre-defined template, one or more sanitizing constraints that refine the one or more generalized paths, the one or more sanitizing constraints used in execution of the assistive action by a computing device to return one or more values that advance the natural language dialogue based on the one or more input responses;
receiving one or more selected candidate dialogues selected from a plurality of candidate dialogues for the domain, each candidate dialogue including utterances, responses, a selected pre-defined template, and one or more sanitizing constraints corresponding to the selected pre-defined template; and
retraining the machine learning model based on the one or more selected candidate dialogues to obtain a retrained machine learning model that is trained to recognize that a future natural language dialogue corresponds to one of the one or more selected candidate dialogues and select assistive actions described by annotations for that selected candidate dialogue.