Method, apparatus and computer program product for a hybrid question-answering (QA) system with a question classification model
AssigneeOptum, Inc.
InventorsRavi Kondadadi, Stephen G. Graham, Rick A. Hamilton, Dmitry Rekesh
Life of this patent
Estimating the term…
Abstract
Methods, apparatus, systems, computing devices, computing entities, and/or the like for a hybrid question-answering (QA) application are provided. The hybrid QA application includes both a retrieval QA application and a deep QA application, as well as a question classification model that determines whether the retrieval QA application or the deep QA application can generate a better answer to an input question.
Claims14
A computer-implemented method for implementing a question classification model for a hybrid question answering (QA) application, the hybrid QA application comprising a deep QA application and a retrieval QA application, the computer-implemented method comprises:
- receiving, by one or more processors, an input question originating from a user computing entity;
- determining, by the one or more processors, a first confidence score associated with the retrieval QA application using the question classification model, the first confidence score indicating a success likelihood of the retrieval QA application answering the input question and the question classification model comprising one or more machine learning models;
- determining, by the one or more processors, whether to use the retrieval QA application or the deep QA application to generate an answer to the input question by determining whether the first confidence score satisfies a first configurable threshold;
- responsive to determining that the first confidence score satisfies the first configurable threshold, generating, by the one or more processors, the answer to the input question using the retrieval QA application;
- and
- responsive to determining that the first confidence score does not satisfy the first configurable threshold, generating, by the one or more processors, the answer to the input question using the deep QA application.
A computer program product for implementing a question classification model for a hybrid question answering (QA) application, the hybrid QA application comprising a deep QA application and a retrieval QA application, the computer program product comprising a non-transitory computer readable medium having computer program instructions stored therein, the computer program instructions when executed by a processor, cause the processor to:
- receive an input question originating from a user computing entity;
- determine a first confidence score associated with the retrieval QA application using the question classification model, the first confidence score indicating a success likelihood of the retrieval QA application answering the input question and the question classification model comprising one or more machine learning models;
- determine whether to use the retrieval QA application or the deep QA application to generate an answer to the input question by determining whether the first confidence score satisfies a first configurable threshold;
- responsive to determining that the first confidence score satisfies the first configurable threshold, generate the answer to the input question using the retrieval QA application;
- and
- responsive to determining that the first confidence score does not satisfy the first configurable threshold, generate the answer to the input question using the deep QA application.
A computing system for implementing a question classification model for a hybrid question answering (QA) application, the hybrid QA application comprising a deep QA application and a retrieval QA application, the computing system comprising a non-transitory computer readable storage medium and one or more processors, the computing system configured to:
- receive an input question originating from a user computing entity;
- determine a first confidence score associated with the retrieval QA application using the question classification model, the first confidence score indicating a success likelihood of the retrieval QA application answering the input question and the question classification model comprising one or more machine learning models;
- determine whether to use the retrieval QA application or the deep QA application to generate an answer to the input question by determining whether the first confidence score satisfies a first configurable threshold;
- responsive to determining that the first confidence score satisfies the first configurable threshold, generate the answer to the input question using the retrieval QA application;
- and
- responsive to determining that the first confidence score does not satisfy the first configurable threshold, generate the answer to the input question using the deep QA application.
Dependencies are inferred from the claim text.