Abstract: The disclosure herein describes determining topics of communication transcripts using trained summarization models. A first communication transcript associated with a first communication is obtained and divided into a first set of communication segments. A first set of topic descriptions is generated based on the first set of communication segments by analyzing each communication segment of the first set of communication segments with a generative language model. A summarization model is trained using the first set of communication segments and associated first set of topic descriptions as training data. The trained summarization model is then applied to a second communication transcript and, based on applying the trained summarization model to the second communication transcript, a second set of topic descriptions of the second communication transcript is generated.

Abstract: The disclosure herein describes determining topics of communication transcripts using trained summarization models. A first communication transcript associated with a first communication is obtained and divided into a first set of communication segments. A first set of topic descriptions is generated based on the first set of communication segments by analyzing each communication segment of the first set of communication segments with a generative language model. A summarization model is trained using the first set of communication segments and associated first set of topic descriptions as training data. The trained summarization model is then applied to a second communication transcript and, based on applying the trained summarization model to the second communication transcript, a second set of topic descriptions of the second communication transcript is generated.

Abstract: The disclosure herein describes reducing training bias in outputs generated by a generative language model. A communication segment associated with a communication is obtained by at least one processor of a generative language model. An output value associated with the communication segment is generated by the generative language model. The output value is mapped to a set of training bias values associated with the generative language model and based on the mapping of the output value to a training bias value of the set of training bias values, an alternative output value is generated. The alternative output value is used in a generated segment output for the communication segment. The accuracy of segment outputs generated by the generative language model is improved through reducing or eliminating its training biases.

Abstract: Aspects of the technology described herein can provide assisted-communication with an intelligent personal assistant. An exemplary computing device may use a profile handler to receive a user profile of a user and a system profile of an interactive communications system. Moreover, a context handler in the exemplary computing device may receive an indication of a communication event related to the user, such as a call or message, and context information associated with the event. Further, a communication handler in the exemplary computing device may use the context information, the user profile, and/or the system profile to navigate the interactive system for the user. In some instances, where a user is unavailable to address a communication event, the intelligent personal assistant may utilize the communication handler to intercept the communication and negotiate the session on behalf of the user.

Abstract: Techniques are described herein that are capable of providing extensibility with regard to a context-aware digital personal assistant. For instance, a description of a capability of a target (e.g., a software target) may be received. Examples of a target include but are not limited to an application (e.g., a software application), a service, a bot, and a website. In a first example, a digital personal assistant may be caused to perform operation(s) based at least in part on a context of a user. In a second example, whether the digital personal assistant performs operation(s) that are configured to be triggered by first aspect(s) of the context of the user is controlled based at least in part on second aspect(s) of the context of the user. The operation(s) include notifying the user of the capability and/or implementing the capability on behalf of the user.

Abstract: Aspects of the technology described herein can provide assisted-communication with an intelligent personal assistant. An exemplary computing device may use a profile handler to receive a user profile of a user and a system profile of an interactive communications system. Moreover, a context handler in the exemplary computing device may receive an indication of a communication event related to the user, such as a call or message, and context information associated with the event. Further, a communication handler in the exemplary computing device may use the context information, the user profile, and/or the system profile to navigate the interactive system for the user. In some instances, where a user is unavailable to address a communication event, the intelligent personal assistant may utilize the communication handler to intercept the communication and negotiate the session on behalf of the user.

Abstract: Aspects of the technology described herein can provide assisted-communication with an intelligent personal assistant. An exemplary computing device may use a profile handler to receive a user profile of a user and a system profile of an interactive communications system. Moreover, a context handler in the exemplary computing device may receive an indication of a communication event related to the user, such as a call or message, and context information associated with the event. Further, a communication handler in the exemplary computing device may use the context information, the user profile, and/or the system profile to navigate the interactive system for the user. In some instances, where a user is unavailable to address a communication event, the intelligent personal assistant may utilize the communication handler to intercept the communication and negotiate the session on behalf of the user.

Abstract: A conversation assistance resource system is provided to connected a user to a resource based on a predicted user need. The conversation assistance resource system monitors user signals relative to a user profile associated with the user. The user profile is based on previously received user signals and includes user preferences, interests, etc. A user need is predicted based on a received user signal. A resource is identified based on the predicted user need and the user profile relative to the resource profile. A communication channel is established between the user and the resource responsive to confirmation by the parties such that the user may query the resource to resolve the predicted user need.

Abstract: A conversation assistance resource system is provided to connected a user to a resource based on a predicted user need. The conversation assistance resource system monitors user signals relative to a user profile associated with the user. The user profile is based on previously received user signals and includes user preferences, interests, etc. A user need is predicted based on a received user signal. A resource is identified based on the predicted user need and the user profile relative to the resource profile. A communication channel is established between the user and the resource responsive to confirmation by the parties such that the user may query the resource to resolve the predicted user need.

Abstract: Aspects of the technology described herein can provide assisted-communication with an intelligent personal assistant. An exemplary computing device may use a profile handler to receive a user profile of a user and a system profile of an interactive communications system. Moreover, a context handler in the exemplary computing device may receive an indication of a communication event related to the user, such as a call or message, and context information associated with the event. Further, a communication handler in the exemplary computing device may use the context information, the user profile, and/or the system profile to navigate the interactive system for the user. In some instances, where a user is unavailable to address a communication event, the intelligent personal assistant may utilize the communication handler to intercept the communication and negotiate the session on behalf of the user.

Abstract: Techniques are described herein that are capable of providing extensibility with regard to a context-aware digital personal assistant. For instance, a description of a capability of a target (e.g., a software target) may be received. Examples of a target include but are not limited to an application (e.g., a software application), a service, a bot, and a website. In a first example, a digital personal assistant may be caused to perform operation(s) based at least in part on a context of a user. In a second example, whether the digital personal assistant performs operation(s) that are configured to be triggered by first aspect(s) of the context of the user is controlled based at least in part on second aspect(s) of the context of the user. The operation(s) include notifying the user of the capability and/or implementing the capability on behalf of the user.