Abstract: In one embodiment, a method includes receiving a user query from a client system associated with a first user, executing tasks via agents which return responses, each response comprising information items, analyzing the responses to determine slots, each slot corresponding to one of the information items, determining compositional sub-goals for each response, wherein each compositional sub-goal indicates a semantic-intent of the respective response, generating compositional fragments by a compositional natural-language generation (NLG) model, each compositional fragment comprising a partial natural-language response, determining a top-level compositional goal, generating a communication content by the compositional NLG model, wherein the communication content comprises a complete natural-language response to the user query, and wherein the complete natural-language response is based on the partial natural-language responses of the compositional fragments, and sending instructions for presenting the communicat

Abstract: In one embodiment, a method includes receiving a user input from a client system associated with a user, generating a plurality of candidate responses by a natural-language generation module in response to the user input, determining a quality-indication by a filtering module for each candidate response of the plurality of candidate responses based on one or more classification models and one or more classification rules, wherein the classification models and classification rules are based on one or more acceptance-criteria, selecting one or more candidate responses from the plurality of candidate responses based on their respective quality-indications, ranking the selected candidate responses based on one or more ranking-criteria, and sending instructions for presenting a top-ranked candidate response to the user to the client system associated with the user responsive to receiving the user input.