Computing N-dimensional sentiment using a large language model
AssigneeCompass Pathfinder Limited
InventorsPatrick Clarke, Robert F. Dougherty, Gregory A. Ryslik, Carly Leininger
Life of this patent
Estimating the term…
Abstract
Approaches for generating predictions related to a set of input text are provided. Text can be received. A machine learning model can be utilized to determine a set of classification probabilities of the text relative to a set of anchor points. A sentiment score indicative of an emotional content of the text can be determined based, at least in part, upon a convex combination of the set of probabilities for the text. One or more predictions related to the text can be generated.
Claims8
A computer-implemented method, comprising:
- receiving text;
- using a machine learning model to determine a set of classification probabilities for the text relative to a set of nine anchor points in a three-dimensional cube, wherein the set of classification probabilities for the text is computed using an output of a large language model fine-tuned on a multi-genre natural language inference (MNLI) dataset;
- determining a sentiment score indicative of an emotional content of the text based, at least in part, upon a convex combination of values from the nine anchor points, using the set of classification probabilities for the text;
- and
- generating one or more predictions based on the sentiment score, wherein the one or more predictions are associated with a response to an administered therapy for treatment-resistant depression.
A computing system, comprising:
- a computing device processor;
- and
- a memory device including instructions that, when executed by the computing device processor, enable the computing system to:
- receive text;
- use a machine learning model to determine a set of classification probabilities for the text relative to a set of nine anchor points in a three-dimensional cube, wherein the set of classification probabilities for the text is computed using an output of a large language model fine-tuned on a multi-genre natural language inference (MNLI) dataset;
- and
- determine a sentiment score indicative of an emotional content of the text based, at least in part, upon a convex combination of values from the nine anchor points, using the set of classification probabilities for the text;
- and
- generate one or more predictions based on the sentiment score, wherein the one or more predictions are associated with a response to an administered therapy for treatment-resistant depression.
A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to:
- receive text;
- use a machine learning model to determine a set of classification probabilities for the text relative to a set of nine anchor points in a three-dimensional cube, wherein the set of classification probabilities for the text is computed using an output of a large language model fine-tuned on a multi-genre natural language inference (MNLI) dataset;
- and
- determine a sentiment score indicative of an emotional content of the text based, at least in part, upon a convex combination of values from the nine anchor points, using the set of classification probabilities for the text;
- and
- generate one or more predictions based on the sentiment score, wherein the one or more predictions are associated with a response to an administered therapy for treatment-resistant depression.
Dependencies are inferred from the claim text.