US 2023/0419164 A1 · Multitask Machine-Learning Model Training and Training Data Augmentation

Abstract

Multitask machine-learning model training and training data augmentation techniques are described. In one example, training is performed for multiple tasks simultaneously as part of training a multitask machine-learning model using question pairs. Examples of the multiple tasks include question summarization and recognizing question entailment. Further, a loss function is described that incorporates a parameter sharing loss that is configured to adjust an amount that parameters are shared between corresponding layers trained for the first and second tasks, respectively. In an implementation, training data augmentation techniques are also employed by synthesizing question pairs, automatically and without user intervention, to improve accuracy in model training.

Claims20

Dependent claims

A method comprising:

receiving, by a processing device, training data including a first set of training data associated with a first task and a second set of training data associated with a second task;
training, by the processing device, a multitask machine-learning model having a first set of layers using the first set of training data associated with the first task and a second set of layers using the second set of training data associated with the second task, the training using a multitask learning loss function defining differing amounts of parameter sharing between corresponding said layers associated with the first and second tasks, respectively;
and
outputting, by the processing device, a result of processing a subsequent input by the trained multitask machine-learning model.

1 more element

Dependencies are inferred from the claim text.

Multitask Machine-Learning Model Training and Training Data Augmentation

Life of this patent

Multitask Machine-Learning Model Training and Training Data Augmentation

Life of this patent

Abstract

Claims20