Abstract: Embodiments of the disclosed technologies are capable of generating diverse suggested message content. The embodiments describe generating a message plan comprising attribute data and section data. The embodiments further describe inputting the message plan as a prompt to a first generative model. The first generative model is fine-tuned using a training message plan. The training message plan comprises an ordered sequence of training attribute data and training section data. The training attribute data and training section data are extracted from historic messages or generated messages. The embodiments further describe generating, by the first generative model, message content suggestions based on the attribute data and section data.

Abstract: Embodiments of the disclosed technologies include configuring a first machine learning model to generate and output suggested message content based on first correlations between message content and message acceptance data, where the first machine learning model includes a first encoder-decoder model architecture, configuring a second machine learning model to generate and output message evaluation data based on second correlations between the message content and the message acceptance data, where the second machine learning model includes a second encoder-decoder model architecture, coupling an output of the first machine learning model to an input of the second machine learning model, and coupling an output of the second machine learning model to an input of the first machine learning model.

Abstract: Embodiments of the disclosed technologies include receiving first message attribute data and inputting the first message attribute data to a first machine learning model. The first machine learning model is configured to generate and output suggested message content based on first correlations between message content and message acceptance data. The first machine learning model generates a first set of message content suggestions based on the first message attribute data, and selects at least one message content suggestion from the first set of message content suggestions based on message evaluation data. Feedback data related to the selected at least one message content suggestion is received. The first machine learning model is tuned based on the feedback data. The tuned first machine learning model generates a second set of message content suggestions based on the first message attribute data.

Abstract: Methods, systems, and apparatuses include receiving input from a client device to facilitate electronic messaging between a first user associated with first attribute data and a second user, where the client device provides a messaging interface that facilitates the electronic messaging. A messaging intent is determined based on the first attribute data of the first user, where the messaging intent corresponds to a purpose of the electronic messaging. A set of attributes of the first attribute data is mapped to prompt inputs based on the messaging intent. A generative language model is applied to the prompt inputs. Suggestions for adding messaging content in the messaging interface are output by the generative language model based on the prompt inputs. The suggestions are presented on the messaging interface.

Abstract: Methods, systems, and apparatuses include receiving input from a client device providing a graphical user interface (GUI) associated with a profile and a profile interface. Attribute data is extracted from the profile in response to receiving the input. An identifier is determined for the profile based on the attribute data. A set of attributes of the attribute data is mapped to a set of prompt inputs based on the identifier. A prompt is created using the set of prompt inputs. A generative language model is applied to the prompt. A suggestion for adding content to the profile is output by the generative language model based on the prompt. The suggestion is sent to the client device for presentation via the profile interface.

Abstract: Techniques for decreasing (or eliminating) the possibility of a skill performing an action that is not responsive to a corresponding user input are described. A system may train one or more machine learning models with respect to user inputs, which resulted in incorrect actions being performed by skills, and corresponding user inputs, which resulted in the correct action being performed. The system may use the trained machine learning model(s) to rewrite user inputs that, if not rewritten, may result in incorrect actions being performed. The system may implement the trained machine learning model(s) with respect to ASR output text data to determine if the ASR output text data corresponds (or substantially corresponds) to previous ASR output text data that resulted in an incorrect action being performed.

Abstract: Methods, systems, and computer programs are presented for suggesting related search queries. One method includes an operation for obtaining a supervised model by training a machine-learning (ML) program with training data that includes search queries entered by users of an online service. Further, the method includes operations for initializing a generator model with the supervised model, and for improving the generator model using reinforcement learning. The reinforcement learning is being based on a reward based on naturalness, relatedness, and a user having a positive session on the online service. Further, the result of the improvement of the generator model is a roll-out model, which is utilized to generate query suggestions for a user of the online service based on a search query provided by the user.

Abstract: Computer-implemented machine learning-based techniques for assisted electronic message composition in a vertical messaging context. The vertical messaging context may be any electronic messaging context in which senders repetitively compose electronic messages to send to recipients where the messages are not identical but nonetheless have common tone, sentiment, content, and structure. The techniques assist users that compose electronic messages in a particular vertical messaging context in composing those messages quickly, with few or no grammatical errors, and with a likelihood of being positively received by the recipients of the messages.

Abstract: The disclosed technologies include a navigation agent for a search interface. In an embodiment, the navigation agent uses reinforcement learning to dynamically generate and select navigation options for presentation to a user during a search session. The navigation agent selects navigation options based on reward scores, which are computed using implicit and/or explicit user feedback received in response to presentations of navigation options.

Abstract: Techniques for decreasing (or eliminating) the possibility of a skill performing an action that is not responsive to a corresponding user input are described. A system may train one or more machine learning models with respect to user inputs, which resulted in incorrect actions being performed by skills, and corresponding user inputs, which resulted in the correct action being performed. The system may use the trained machine learning model(s) to rewrite user inputs that, if not rewritten, may result in incorrect actions being performed. The system may implement the trained machine learning model(s) with respect to ASR output text data to determine if the ASR output text data corresponds (or substantially corresponds) to previous ASR output text data that resulted in an incorrect action being performed.

Abstract: Techniques for decreasing (or eliminating) the possibility of a skill performing an action that is not responsive to a corresponding user input are described. A system may train one or more machine learning models with respect to user inputs, which resulted in incorrect actions being performed by skills, and corresponding user inputs, which resulted in the correct action being performed. The system may use the trained machine learning model(s) to rewrite user inputs that, if not rewritten, may result in incorrect actions being performed. The system may implement the trained machine learning model(s) with respect to ASR output text data to determine if the ASR output text data corresponds (or substantially corresponds) to previous ASR output text data that resulted in an incorrect action being performed.