18385358. Automatically Labeling Items using a Machine-Trained Language Model (Microsoft Technology Licensing, LLC)
Automatically Labeling Items using a Machine-Trained Language Model
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Daniel Arthur Sommerfield of Mercer Island WA US
Adarsh Ramanathan of Bellevue WA US
Automatically Labeling Items using a Machine-Trained Language Model
This abstract first appeared for US patent application 18385358 titled 'Automatically Labeling Items using a Machine-Trained Language Model
Original Abstract Submitted
A computer-implemented labeling technique generates a task description that describes a labeling task to be given to a language model. The technique then sends a prompt to the language model, which includes the task description and a particular item to be labeled. The technique receives a response provided by the language model in response to the prompt, which specifies a class assigned by the language model to the item. In some implementations, the task description specifies a group of suggested classes to be used in classifying the particular item. The task description also invites the language model to specify another class upon a finding that none of the group of suggested classes applies to the item. The technique also allows a user to stop and restart a labeling run at any point in the labeling run. Other aspects of the technique include consensus processing and weight updating.