A machine reading comprehension (MRC) question and answer providing method includes receiving a user question; analyzing the user question; selecting at least one document from at least one domain corresponding to an analyzed user question and searching for a passage, which is a candidate answer determined as being suitable for the user question, in the selected at least one document; obtaining at least one correct answer candidate value by inputting the user question and a corresponding passage into each of at least one MRC question and answer unit; and determining whether the at least one correct answer candidate value is a best answer.

The explanation engine has a set of modules cooperating with each other configured to evaluate layers in a hierarchical architecture of a machine-based reasoning process that uses machine learning. The set of modules cooperate to support an explanation of how the machine-based reasoning process arrived at its reported results of both a final/top level result as well as corresponding intermediate output results. A messaging module of the explanation engine can collect the top-level result as well as one or more intermediate output results from intermediate layers of the machine-based reasoning process. Multiple layers of reasoning are associated with terminology used in at least one of i) a problem to be solved and ii) a domain pertinent to the problem in order to communicate how the machine-based reasoning process came to its reported results in a communication.

Methods and systems are described herein for merging datasets from multiple content domains for training a prediction model to predict a solution for a request related to a specific content domain. A dataset for a content domain may include requests and solutions organized as groups. For example, a dataset for a first content domain may include a first group having (a) a first set of requests (e.g., questions or queries) related to a first topic, and (h) a solution (e.g., an answer) associated with the first set of requests. The datasets of different content domains are analyzed based on context-based vector representations of the requests or solutions to determine the groups that are similar and merge those similar groups into a single merged group. A prediction model is trained with the merged groups for obtaining a prediction of a solution to any given request.

A social agent system includes a computing platform having processing hardware and a system memory storing a social agent software code. The processing hardware is configured to execute the social agent software code to receive, from a client system, input data provided by a user of the client system when the user is interacting with the social agent system using the client system, and to select, using the input data, a dialogue template for responding to the user. The dialogue template includes one or more placeholder fields to be filled by the client system to create a personalized dialogue for responding to the user. The processing hardware is further configured to execute the social agent software code to deliver, to the client system, the dialogue template including the one or more placeholder fields to be filled by the client system to create the personalized dialogue for responding to the user.

An approach for determining a veracity of a reported event is provided. In an embodiment, a set of predictor variables is retrieved from a selected use case. Each of these predictor values is a condition that indicates the veracity of the reported event. In addition, a set of hidden predictor variables is generated from a set of unstructured documents related to the reported event using a hidden Markov model that is based on the predictor variables using a cognitive system. These hidden predictor variables are combined with the set of predictor variables to generate a set of updated predictor variables. These updated predictor variables are used by the cognitive system to return a determination of the veracity of the reported event.

An AI-based process monitoring system access a plurality of data sources having different data formats to collect and analyze KPI data and shortlist KPIs that are to be used for determining the impact of automation of an automated process or sub-process. Information regarding an automated process is received and KPIs associated with the process and sub-processes of the process are identified. The identified KPIs are put through an approval process and the approved KPIs are presented to a user for selection. The user-selected KPIs are evaluated based on classification, ranking and sentiments associated therewith. The evaluations are again presented to the user along with a set of questionnaires wherein each of the questions has a dynamically controlled weight associated therewith. Based at least on the weights and user responses, a subset of the evaluated KPIs are shortlisted for use in evaluating the impact of process automation.

A method of extending a conversational computing interface. The method comprises executing a nonnative skill implemented in a nonnative programming language of the conversational computing interface. The method further comprises automatically computer-tracing computer operations performed by the nonnative skill during such execution. The method further comprises automatically computer-generating a native computer-executable plan representing the traced computer operations in a native programming language of the conversational computing interface.

A system for performing document extraction is configured to: (a) receive a first document; (b) extract the first document into document elements, the document elements including pages, lines, paragraphs, or any combination thereof; (c) determine a first set of fields of interest for the first document, wherein the first set of fields of interest are determined via a type of the first document or via a first set of queries for probing the first document; (d) determine, from a plurality of closed domain question answering (CDQA) models, a first set of CDQA models that provides answers to each field of interest included in the first set of fields of interest; and (e) provide answers to the first set of fields of interest to the client device.

An analysis apparatus (2000) acquires relationship information (50) indicating a degree of influence of each of a plurality of explanatory variables on an objective variable. The analysis apparatus (2000) generates, by using the relationship information (50), a cause-and-effect diagram (10) representing a relationship between the objective variable and the explanatory variables. The analysis apparatus (2000) determines a display aspect for a factor display (16) or presence or absence of the display in the cause-and-effect diagram (10), based on the degree of influence of the explanatory variable.

The information processing apparatus 1 includes the input unit 101 that receives observation represented by a conjunction of atomic formulas, background knowledge represented by a set of logic formulas, and condition to be satisfied by a new rule represented by a logic formula; the rule candidate generation unit 102 that generates the new rule represented by a logic formula having a predicate, which is contained in the observation or the background knowledge, as an element; the abduction system unit 103 that executes abduction to derive best hypothesis by using the background knowledge, to which the new rule generated is added, and the observation as inputs; and the rule evaluation unit 104 that evaluates whether the new rule satisfies the condition to be satisfied by using the best hypothesis.