An information processing device according to the present invention includes: a memory; and a processor coupled to the memory. The processor performs operations. The operations includes: generating, based on language data, a predicate argument structure including a predicate and an argument being an object of the predicate; generating first data indicating co-occurrence of the predicate and the argument in the predicate argument structure; decomposing the first data into a plurality of pieces of second data including fewer elements than elements included in the first data, and generating, based on the second data, third data including potential co-occurrence of the predicate and the argument; selecting the predicate argument structure by using the first data and the third data, and calculating, by using the third data, a score for a pair of the predicate argument structures including the selected predicate argument structure; and selecting the pair, based on the score.

A computing method receives a labeled sample from an annotator. The method may determine a plurality of reference model risk scores for the first labeled sample, where each reference model risk score corresponds to an amount of risk associated with adding the first labeled sample to a respective reference model of a plurality of reference models. The method may determine an overall risk score for the first labeled sample based on the plurality of reference model risk scores. The method may further determine a probe for confirmation of the first labeled sample and a trust score for the annotator by sending the probe to one or more annotators. In response to determining a trust score for the annotator the method may add the labeled sample to a ground truth or reject the labeled sample.

In some examples, machine learning based semantic structural hole identification may include mapping each text element of a plurality of text elements of a corpus into an embedding space that includes embeddings that are represented as vectors. A semantic network may be generated based on semantic relatedness between each pair of vectors. A boundary enclosure of the embedding space may be determined, and points to fill the boundary enclosure may be generated. Based on an analysis of voidness for each point within the boundary enclosure, a set of void points and void regions may be identified. Semantic holes may be identified for each void region, and utilized to determine semantic porosity of the corpus. A performance impact may be determined between utilization of the corpus to generate an application by using the text elements without filling the semantic holes and the text elements with the semantic holes filled.

This disclosure relates to improved techniques for performing human parsing functions using neural network architectures. The neural network architecture can model human objects in images using a hierarchal graph of interconnected nodes that correspond to anatomical features at various levels. Multi-level inference information can be generated for each of the nodes using separate inference processes. The multi-level inference information for each node can be combined or fused to generate final predictions for each of the nodes. Parsing results may be generated based on the final predictions.

An abnormality determination device includes one or more processors. The processors input first input data to a first model to obtain first output data. The first output data is formed by restoring data with the reduced dimension to data with the same dimension as that of the first input data. The processors input second input data, which is a difference between the first input data and the first output data, to a second model, and obtain second output data. The second output data is formed by restoring data with the reduced dimension to data with the same dimension as that of the second input data. The processors obtain restored data that is a sum of the first output data and the second output data. The processors compare the first input data with the restored data and determine an abnormality in the first input data based on the comparison result.

Systems and methods for operating a communication device. The methods comprise: receiving a signal at the communication device; performing, by the communication device, one or more machine learning algorithms using at least one feature of the signal as an input to generate a plurality of scores (each score representing a likelihood that the signal was modulated using a given modulation type of a plurality of different modulation types); assigning a modulation class to the signal based on the plurality of scores; determining whether a given wireless channel is available based at least on the modulation class assigned to the signal; and selectively using the given wireless channel for communicating signals based on results of the determining.

An anthropomorphic, artificial intelligence-based system and method to quote, compare, and purchase personal lines and commercial lines property and casualty insurance or benefits products and services and quoting, comparing, purchasing, or transferring residential services using a cognitive virtual assistant. The system and method collects information from an online advertising platform during the process and returns the collected information to the online advertising platform for optimization of the online advertising platform.

Disclosed herein is a system for facilitating accomplishing tasks based on a natural language conversation. Accordingly, the system may include a direct graph unit. Further, the direct graph unit may include a directed graph. Further, the directed graph models a non-linearity of the natural language conversation. Further, the directed graph may include a set of nodes connected by at least one edge. Further, the system may include a context-encoded language understanding unit may include a learning unit and an inferring unit. Further, the learning unit may be configured for receiving a plurality of inputs. Further, the learning unit may be configured for generating a model based on the plurality of inputs. Further, the inferring unit may be configured for receiving a plurality of inputs. Further, the inferring unit may be configured for generating an output based on the plurality of inputs and the model.

A method may include applying, to a corpus of data, a first machine learning technique to identify candidate domains of an ontology mapping brain structure to mental function. The corpus of data may include textual data describing a plurality of mental functions and spatial data corresponding to a plurality of brain structures. A second machine technique may be applied to optimize a quantity of domains included in the ontology and/or a quantity of mental function terms included in each domain. The ontology may be applied to phenotype an electronic medical record and predict a clinical outcome for a patient associated with the electronic medical record. Related systems and articles of manufacture, including computer program products, are also provided.

Disclosed is a multi-device based inference method and apparatus, where the multi-device based inference method includes receiving information related to operation devices performing an operation included in a neural network and a graph corresponding to the neural network, obtaining a size of an output of the operation in a forward direction of the graph based on the information and the graph, dividing an input of the operation in a backward direction of the graph based on the information, the graph, and the size of the output, and performing an inference based on the divided input.