Abstract: An automated conversation intermediary performs several operations during a conversation between end users and chatbots. Prior to adding natural language input from an end user to a chatbot prompt, the intermediary annotates the input to indicate a role of the end user, using hidden markers for the annotation that are not presented to the end user during the conversation. The intermediary receives output generated by the chatbot, which also includes hidden markers in addition to natural language to be presented to the end user, and removes the hidden markers before providing the natural language portion of the output to the end user.

Abstract: A plurality of concepts is identified from utterances of a user of a service using a set of machine learning models. The plurality of concepts includes a primary concept representing an offering included in a catalog of the service, and a non-primary concept which provides additional information about the offering. A logical relationship is inferred among a pair of concepts using the set of machine learning models. A service order for the service is populated based at least in part on the relationship.

Abstract: A plurality of concepts is identified from utterances of a user of a service using a set of machine learning models. The plurality of concepts includes a primary concept representing an offering included in a catalog of the service, and a non-primary concept which provides additional information about the offering. A logical relationship is inferred among a pair of concepts using the set of machine learning models. A service order for the service is populated based at least in part on the relationship.

Abstract: Documents may be evaluated to determine inclusion of one or more types of information, such as personal information. Within the documents containing the one or more types of information, individual spans of information may be replaced with alternative data, which may maintain a type of content associated with the spans. Datasets of documents may be created where one or more types of information have been removed. These datasets may also be evaluated to determine whether one or more elements are over or under represented and then the datasets may be modified, such as by adding or removing documents, to provide an improved balance or distribution of the one or more elements.

Abstract: Various embodiments of a hierarchical system or method of identifying sensitive content in data is described. In some embodiments, sensitive data classifiers local to a data storage system can analyze a plurality of data items and classify at least some data items as potentially containing sensitive data. The sensitive data classifiers can provide the classified data items to a separate sensitive data discovery component. The sensitive data discovery component can, in some embodiments, obtain the classified data items, perform a sensitive data location analysis on the classified data items to identify a location of sensitive data within some of the classified data items, and generate location information for the sensitive data within the data items containing sensitive data. The sensitive data discovery component can provide to a destination this information, in some embodiments, where the destination might redact, tokenize, highlight, or perform other actions on the located sensitive data.

Abstract: Techniques for interpreting a text classifier model are described. An exemplary method includes receiving a request to interpret the text classifier; receiving input text to be used to interpret the text classifier; interpreting the text classifier using the input text and masked input text to determine two or more of a counterfactual score for the received input text or an aspect thereof, an importance score for the received input text or an aspect thereof, and a bias score for the received input text or an aspect thereof as requested by the request, and providing the determined one or more scores is provided to a requester.