US 12,340,792 B2
Systems and methods for few-shot intent classifier models
Jin Qu, San Mateo, CA (US); Wenhao Liu, Redwood City, CA (US); Kazuma Hashimoto, 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 Nov. 23, 2021, as Appl. No. 17/534,008.
Claims priority of provisional application 63/189,632, filed on May 17, 2021.
Prior Publication US 2022/0366893 A1, Nov. 17, 2022
Int. Cl. G10L 15/06 (2013.01); G10L 15/16 (2006.01)
CPC G10L 15/063 (2013.01) [G10L 15/16 (2013.01); G10L 2015/0636 (2013.01); G10L 2015/0638 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for few-shot intent classification of an input natural language utterance, the method comprising:
receiving, via a communication interface, a training dataset containing a plurality of utterances and a plurality of pre-defined intent labels;
transforming the training dataset into a plurality of utterance-label pairs by pairing an utterance of the plurality of utterances with each of the plurality pre-defined intent labels, wherein each of the plurality of utterance-label pairs includes the utterance and a pre-defined intent label of the plurality of pre-defined intent labels;
generating a transformed entailment label for each of the plurality of utterance-label pairs, wherein the transformed entailment label indicates an entailment relationship between the utterance and the pre-defined intent label in an utterance-label pair;
inputting the plurality of utterance-label pairs to a classifier;
generating, using the classifier, an entailment probability distribution for each of the plurality of utterance-label pairs;
comparing the entailment probability distribution with the corresponding transformed entailment label for each of the plurality utterance-label pair;
computing a training objective based on the comparison of the entailment probability distribution with the corresponding transformed entailment label for each of the plurality of utterance-label pair; and
updating the classifier based on the training objective via backpropagation.