US Patent Application 18303394. SYSTEM AND METHOD FOR DETECTING UNHANDLED APPLICATIONS IN CONTRASTIVE SIAMESE NETWORK TRAINING simplified abstract

From WikiPatents
Jump to navigation Jump to search

SYSTEM AND METHOD FOR DETECTING UNHANDLED APPLICATIONS IN CONTRASTIVE SIAMESE NETWORK TRAINING

Organization Name

SAMSUNG ELECTRONICS CO., LTD.==Inventor(s)==

[[Category:Brendon Christopher Beachy Eby of Chicago IL (US)]]

[[Category:Suhel Jaber of San Jose CA (US)]]

[[Category:Sai Ajay Modukuri of San Francisco CA (US)]]

[[Category:Omar Abdelwahab of Mountain View CA (US)]]

[[Category:Ankit Goyal of Belmont CA (US)]]

SYSTEM AND METHOD FOR DETECTING UNHANDLED APPLICATIONS IN CONTRASTIVE SIAMESE NETWORK TRAINING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18303394 titled 'SYSTEM AND METHOD FOR DETECTING UNHANDLED APPLICATIONS IN CONTRASTIVE SIAMESE NETWORK TRAINING

Simplified Explanation

The patent application describes a method for classifying input utterances using a language model and updating the model based on the classification results.

  • The method involves determining target embedding vectors for each class and generating an utterance embedding vector using a pre-trained language model.
  • The predicted class for an input utterance is obtained by comparing the distances of the utterance embedding vector to spatial parameters representing the classes.
  • The spatial parameters are based on the target embedding vectors associated with each class.
  • The parameters of the language model are updated based on the difference between the predicted class and the expected class.


Original Abstract Submitted

A method includes determining, using at least one processing device of an electronic device, a target embedding vector for each class of a plurality of classes. The method also includes generating, using the at least one processing device, an utterance embedding vector using a pre-trained language model, where the utterance embedding vector represents an input utterance associated with an expected class. The method further includes obtaining, using the at least one processing device, a predicted class associated with the input utterance based on distances of the utterance embedding vector to spatial parameters representing the plurality of classes, where the spatial parameter of each class is based on the target embedding vector associated with that class. In addition, the method includes updating, using the at least one processing device, parameters of the language model based on a difference between the predicted class and the expected class.

Retrieved from "http://wikipatents.org/index.php?title=US_Patent_Application_18303394._SYSTEM_AND_METHOD_FOR_DETECTING_UNHANDLED_APPLICATIONS_IN_CONTRASTIVE_SIAMESE_NETWORK_TRAINING_simplified_abstract&oldid=9129"