An inference apparatus 10 includes: a hypothesis candidate generation unit 11 configured to perform inference by applying inference knowledge that includes information indicating a temporal sequence to observation in which facts that have been observed are expressed using logical expressions, and thereby generate a hypothesis candidate from which the observation can be derived; and a contradiction examination unit 12 configured to determine, on the basis of the information indicating a temporal sequence, whether or not the generated hypothesis candidate includes a temporal contradiction.

Systems and methods for natural language processing are described. One or more embodiments of the present disclosure receive a query related to information in a table, compute an operation selector by combining the query with an operation embedding representing a plurality of table operations, compute a column selector by combining the query with a weighted operation embedding, compute a row selector based on the operation selector and the column selector, compute a probability value for a cell in the table based on the row selector and the column selector, where the probability value represents a probability that the cell provides an answer to the query, and transmit contents of the cell based on the probability value.

A method, apparatus and computer program for detecting natural language (NL) bias by a conversational system is described. Embodiments of the invention determine an NL bias in a set of training questions used to train a machine learning model used by the conversational system to select a user intent. Other embodiments of the invention determine an NL bias in a user question received by the conversation system as compared to the set of training questions. The NL bias causes the machine learning to preferentially associate user queries to a user intent. In respective embodiments, the system takes a corrective action to adjust the NL bias of the training questions or the user question.

A method and system of audibly broadcasting responses to a user based on user queries about a specific patient molecular report, the method comprising receiving an audible query from the user to a microphone coupled to a collaboration device, identifying at least one intent associated with the audible query, identifying at least one data operation associated with the at least one intent, associating each of the at least one data operations with a first set of data presented on the molecular report, executing each of the at least one data operations on a second set of data to generate response data, generating an audible response file associated with the response data and providing the audible response file for broadcasting via a speaker coupled to the collaboration device.

Gene expression programming-based behavior monitoring is disclosed. A machine receives, as input, a plurality of data examples. A method can include receiving data indicating behaviors of the device, determining, using a gene expression programming (GEP) method, a data model that explains the data, and comparing further data indicating further behavior of the device to the data model to determine whether the further behavior is explained by the data model.

A system and a method of displaying a predictive answer in a conversation window, are described. The method includes transmitting, to a device executing an application, a first message to cause the device to display a conversation window within the application, wherein the conversation window has a character entry field. The method includes generating, by one or more processors, a predictive answer based on a Uniform Resource Locator (URL) associated with the conversation window or a URL shape of the URL, wherein the predictive answer includes a predicted inquiry of a user. The method includes transmitting, to the device, a second message to cause the device to display the predictive answer in the conversation window.

Provided are a device and method for assessing a user's learning ability. The method includes acquiring target assessment data of a target user and a reference user related to a target domain, wherein the target assessment data includes question data related to the target domain and answer data of each of the target user and the reference user for the question data, acquiring a target neural network model of which training has been completed, acquiring comparison information representing the target user's ability in relation to the reference user's ability in the target domain through the target neural network model, and calculating the target user's virtual score in the target domain on the basis of the comparison information.

The present disclosure provides method and apparatus for generating responses in automated chatting. A message may be received in a session. An intention vector may be determined based at least on the message and the session through dynamic memory network (DMN), the intention vector indicating an attention point and an intention. A response may be generated based at least on the intention vector.

The method and system of the present disclosure facilitate automatic, and in an objective manner, selection of an optimal set of technical questions, from a question bank, personalized for a candidate. This ensures consistent, standardized, efficient and objective interviews that result in high quality recruitment, given the diversity of candidates, complexity of job requirements and interviews are inherently subjective. The state-of-the-art depends on responses so far, to generate on-the-fly questions causing a cognitive load on the interviewer. Also, there is no guarantee on the breadth and depth of concepts assessed in each interview. In the present disclosure, skill graphs are employed to create a semantically rich and detailed characterization of questions in terms of concepts. Optimization formulation uses the skill graph to generate constraints, content balancing and objective functions for selection of questions.

Embodiments of the present systems and methods may provide an intelligent systems framework for analysis of user-generated content from various capture points to determine user intent. For example, a method may be implemented in a computer system comprising a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor, the method may comprise receiving, at the computer system, data relating to a plurality of aspects of at least one person, including data from at least one of physical or physiological sensors and communicatively connected devices, extracting, at the computer system, from the received data, features relevant to events relating to at least one person, extracting, at the computer system, at least one intent of at least one event relating to at least one person, and performing, at the computer system, an action based on the extracted at least one intent.