US 12,379,894 B1
Reference resolution during natural language processing
Antoine R. Raux, Los Gatos, CA (US); Yi Ma, Milpitas, CA (US); Kevin D. Pitolin, Cupertino, CA (US); Felicia Edwards, Belmont, CA (US); and Chengchao Yang, San Jose, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Feb. 22, 2022, as Appl. No. 17/677,936.
Claims priority of provisional application 63/227,120, filed on Jul. 29, 2021.
Claims priority of provisional application 63/154,942, filed on Mar. 1, 2021.
Int. Cl. G06F 3/16 (2006.01); G06F 3/01 (2006.01); G10L 15/22 (2006.01)
CPC G06F 3/167 (2013.01) [G06F 3/013 (2013.01); G06F 3/017 (2013.01); G10L 15/22 (2013.01); G10L 2015/223 (2013.01); G10L 2015/226 (2013.01)] 45 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable storage medium storing one or more programs configured to be executed by one or more processors of an electronic device, the one or more programs including instructions for:
detecting invocation of a digital assistant;
determining, using a reference resolution service, a set of possible entities prior to receiving a user utterance including an ambiguous reference;
receiving the user utterance including the ambiguous reference;
determining, based on the user utterance and the set of possible entities, a plurality of candidate interpretations including a preliminary set of entities corresponding to the ambiguous reference, wherein a first candidate interpretation of the plurality of candidate interpretations is determined by a first natural language model associated with a first application and a second candidate interpretation of the plurality of candidate interpretations is determined by a second natural language model different from the first natural language model and wherein the second natural language model is associated with a second application different from the first application;
determining, with the reference resolution service and based on the plurality of candidate interpretations including the preliminary set of entities corresponding to the ambiguous reference, an entity corresponding to the ambiguous reference; and
performing, based on the plurality of candidate interpretations and the entity corresponding to the ambiguous reference, a task associated with the user utterance.