Abstract: A system can comprise a memory that stores computer executable components, and a processor, operably coupled to the memory, that executes the computer executable components comprising: a linking component that associates one or more unmasked elements of the logical form with one or more corresponding structured knowledge elements of a knowledge base and a prediction component that predicts the one or more masked elements based on extended context of the corresponding structured knowledge elements of the knowledge base to generate one or more predicted elements. In an embodiment, the prediction component predicts the one or more masked elements based on scores of one or more candidate elements. In an embodiment, the system can determine one or more rules that describe the natural language text segment in terms of the structured knowledge elements and associated weights of the knowledge base paths.

Abstract: A decoder of a neural semantic parser receives input data associated with a natural language expression. An action is selected from a queue of actions, the queue of actions storing at least one action, the action being associated with an element from vocabulary of the natural language expression. The selected action is processed to build a tree structure where the processing of the selected action expands the tree structure with a node representing the element, where the tree structure is expanded bottom-up. A set of new actions is generated based on the node associated with the selected action and the vocabulary. The set of new actions is added to the queue of actions. The decoder repeats selecting, processing, generating and adding until a criterion is met. A logical form of the natural language expression is output based on the tree structure.

Abstract: Examples described herein provide a method for explaining neuro-symbolic reinforcement learning reasoning in a neuro-symbolic neural network for neuro-symbolic artificial intelligence. The method includes selecting an action from among possible candidates taken in an environment, wherein the action comprises a pair of a verb and an entity and displaying one or more logical facts that are extracted from natural observation sentences of the environment. The method also includes visualizing contrastive information for a current state and a goal state which is from external knowledge and displaying trained rules in the neuro-symbolic neural network for neuro-symbolic artificial intelligence, wherein, in response to a first user selection of the action, highlighting each pair of the verb and the entity and a fired predicate corresponding to the first user selection.

Abstract: In an approach for propagating labels of objects in an image, a processor receives the image. A processor performs a normalization of the image. A processor runs the image through a pre-trained object detector. A processor receives a set of detected objects from the pre-trained object detector. A processor determines a width dimension and a height dimension of a bounding box for each detected object of the set of detected objects. A processor propagates a label for each instance of each detected object in the image with the respective bounding box using prior geometric knowledge of bounding box placement. A processor inverses the normalization of the labeled image. A processor outputs the labeled image.

Abstract: A state determination apparatus 100 determines the state of a structure 200. The state determination apparatus 100 includes a measurement unit 10 configured to measure a deflection amount and a surface displacement amount in each of a plurality of target regions that are preset on the structure 200, a feature value calculation unit 20 configured to calculate, for the respective target regions, feature values each indicating a relationship between the deflection amount and the surface displacement amount, using the measured deflection amount and surface displacement amount, a spatial distribution calculation unit 30 configured to calculate a spatial distribution of the feature values using the feature values calculated for each of the target regions, and a degradation state determination unit 40 configured to determine a degradation state of the structure 200 based on the spatial distribution of the feature value.

Abstract: A degradation detection device (10) includes: an image acquisition unit (11) that acquires an image sequence of a detection target; a matching point specification unit (12) that specifies matching points in the image sequence; a motion amount calculation unit (13) that, based on the specified matching points, for each frame that constitutes the image sequence, specifies motion occurring between the frame and a frame immediately previous thereto, and calculates a motion amount for each of the matching points along a time series; and a degraded region candidate specification unit (14) that specifies a region in which degradation has likely occurred in the image sequence, based on the motion amounts of the matching points that were calculated along the time series.

Abstract: A state assessing device 100 includes: a parameter estimation unit 110 that estimates, using time-series images obtained by an image taking device taking images of a structure and a measured value of a distance from the image taking device to the structure, a motion parameter representing a relative motion of a surface of the structure with respect to the image taking device; and an abnormality determination unit 120 that determines an abnormality in the structure by using an estimation result of the motion parameter.