Abstract: Provided is a method, computer program product, and system for fusing knowledge graphs to generate a larger knowledgebase for responding to cross document questions. A processor may extract contextual information from a plurality of documents. The processor may generate, based on the extracted contextual information, a knowledge graph for each document of the plurality of documents. The processor may analyze each knowledge graph to determine if one or more entities of each knowledge graph are linked. The processor may fuse, in response to an entity in a first knowledge graph being linked to an entity in a second knowledge graph, the first knowledge graph with the second knowledge graph to create a fused knowledge graph.

Abstract: Disclosed are techniques for modifying deep learning models (such as neural networks) to run more efficiently in computing environments with limited floating point computation resources. A deep learning model is trained using a set of training data. Input and output values are then recorded from the layers of the trained model when supplied with the training data, which are then used to generate deep forest decision tree models corresponding to individual layers of the trained model. Experimental versions of the trained model are then generated with different layers of the trained model replaced with their corresponding deep forest decision tree models. These experimental versions are then ranked according to the accuracy of their results compared to the results of the trained model. An updated trained model is then generated with one or more layers replaced with their corresponding deep forest decision tree models.

Abstract: An example operation may include one or more of generating a three-dimensional (3D) model of an object via execution of a machine learning model on one or more images of the object, capturing a plurality of snapshots of the 3D model of the object at different angles to generate a plurality of snapshot images of the object, fusing a feature into each of the plurality of snapshots to generate a plurality of fused snapshots of the 3D model of the object, and storing the plurality of fused snapshots of the 3D model of the object in memory.

Abstract: Analysis of edge closures of metal surface particles based on a graph structure.

Abstract: An embodiment includes parsing geographical data into a path graph having a plurality of nodes and edges, and identifying first and second subsets of the nodes as source nodes and destination nodes, respectively. The embodiment generates path data for a candidate delivery route from a source node to a destination node and along an edge between the source and destination nodes. The embodiment processes the path data using first and second evaluation techniques based on respective metrics. The embodiment compares evaluation values from the evaluation techniques to evaluation values associated with another candidate delivery route, and selects the candidate delivery route as a finalized delivery route based on the comparison results. The embodiment then generates a route plan that includes the finalized delivery route.

Abstract: From a set of point data, a set of scattered rays is constructed. From the set of scattered rays, a set of ray slopes is computed. The set of ray slopes is mapped to a corresponding set of trigonometric functions. Using an optimization method, a parameter of the set of trigonometric functions is selected. Using an inverse of the set trigonometric functions, a vehicle mass corresponding to the set of point data is computed. Based on the vehicle mass, a threshold braking distance of a collision avoidance system of the vehicle is adjusted, the threshold braking distance comprising a distance from an object predicted to collide with the vehicle. By braking the vehicle at least the threshold braking distance from the object, a predicted collision between the vehicle and the object is avoided.

Abstract: An example operation may include one or more of executing a machine learning model on training data, where the training data comprises a plurality of word strings, identifying words within the training data that are extracted by the machine learning model during the executing, determining a color for the machine learning model based on the identified words and a predefined mapping of words to colors, and rendering, via a user interface, a label associated with the machine learning model in the determined color for the machine learning model.

Abstract: An example operation may include one or more of generating a plurality of bounding boxes at a plurality of content areas in an image corresponding to a plurality of pieces of text within the image, converting the plurality of bounding boxes into a plurality of bounding box vectors based on attributes of the plurality of bounding boxes, training a machine learning model to transform a bounding box into a location in vector space based on the plurality of bounding box vectors, and storing the trained machine learning model in memory.

Abstract: Embodiments of the present invention provide an approach for compressing data, and more particularly, to large-scale text data encoding and compression using absolute overfitting on pre-trained language models. Large-scale data is parsed into sentences. A unique token is generated for each sentence to form a token list. A generative (or compression) model is trained from the tokens in the token list to produce the corresponding sentence of each token through absolute overfitting of a pre-trained language model. The compressed text data is stored as the token list and generative model, resulting in a storage space savings.

Abstract: A method and related system detail a split of an architecture of a monolithic application into an architecture of a micro service application. The method receives source code for the monolithic application, and maps the source code into a directed graph. The graph is split into subgraphs and optimized. The method further provides the detailing of the micro service application split, based on the subgraphs.

Abstract: From a set of point data, a set of scattered rays is constructed. From the set of scattered rays, a set of ray slopes is computed. The set of ray slopes is mapped to a corresponding set of trigonometric functions. Using an optimization method, a parameter of the set of trigonometric functions is selected. Using an inverse of the set trigonometric functions, a vehicle mass corresponding to the set of point data is computed. Based on the vehicle mass, a threshold braking distance of a collision avoidance system of the vehicle is adjusted, the threshold braking distance comprising a distance from an object predicted to collide with the vehicle. By braking the vehicle at least the threshold braking distance from the object, a predicted collision between the vehicle and the object is avoided.

Abstract: An approach is provided for improving a named entity recognition. Using a multi-label classification in a neural network, a sub-entity is identified in an original sentence. First and second labels are determined indicating first and second candidate types of the sub-entity. First and second replacement sentences are generated. The first replacement sentence replaces the sub-entity in the original sentence with a first sub-entity of the first candidate type. The second replacement sentence replaces the sub-entity in the original sentence with a second sub-entity of the second candidate type. First and second confidence scores for the first and second replacement sentences are determined. Based on the first confidence score exceeding the second confidence score by more than a threshold amount, the neural network is retrained by selecting the first instead of the second candidate type as the sub-entity type.

Abstract: Mechanisms are provided for generating an augmented reality representation of a real-world environment. An augmented reality (AR) system receives a captured digital image of the real-world environment and generates an initial estimate of a candidate point specifying an estimated location of an annotation point of a virtual object model within the captured digital image of the real-world environment. An accuracy of the initial estimate is calculated based on a function of characteristics of the annotation point and a function of characteristics of the candidate point and, in response to the evaluation of accuracy indicating that the initial estimate is not accurate, an annotation point location refinement operation is performed to generate a refined candidate point for aligning the annotation point with the captured digital image of the real-world environment. An AR representation of the real-world environment is generated based on the refined candidate point.

Abstract: A method, computer system, and a computer program product for data protection is provided. The present invention may include, generating an encoder network. The present invention may also include, encoding a training data using the generated encoder network, wherein the training data includes natural language data. The present invention may further include, training a deep learning model using the encoded training data.

Abstract: A method, computer program product, and computer system for finding outliers in multidimensional time series samples. Each time series sample is divided into at least 2 sub samples having equal time duration. At least one prediction model is pre-trained using the sub samples and a prediction result for each sub sample for each prediction model is obtained by executing the pre-trained prediction models with the time series samples as input. A Shapely value corresponding to each prediction result is sub samples for each prediction model to generate multiple clusters of Shapely values for each prediction model. Highest ranking Shapely value outliers are determined from analysis of the multiple clusters. Highest ranking outlier sub samples corresponding to the highest ranking Shapely value outliers are identified.

Abstract: A system and method for table conversion including converting a table containing text in tabular form to an image, labeling each text area of the image with a bounding box, determining for each bounding box, a position information, a semantic information, and an image information, reconstructing the image into a graph form having a plurality of nodes, wherein each node represents the bounding box of the text areas of the image, inputting at least two nodes into a trained neural network to determine a relative relationship between the at least two nodes, building a knowledge graph using the relative relationship of the at least two nodes, and translating the knowledge graph into machine readable natural language.

Abstract: In an approach for road section recognition using multi-modal cognitive mechanism, a processor receives an audio signal from a road test. A processor processes the audio signal to generate an acoustic spectrum density distribution map to identify a respective at least one road section switching point in a first mode. A processor processes a spectrogram of the audio signal to identify the respective at least one road section switching point in a second mode. A processor uses a machine learning model to predict an expected sound at each frame of the audio signal, to calculate a similarity between the expected sound and an actual sound, and to identify the respective at least one road switching point when the similarity is lower than a pre-set similarity threshold in a third mode. A processor combines results of the three modes to obtain a final set of road section switching points.

Abstract: A system and method for field extraction including determining a key position of a key in an electronic file, isolating candidate key values based on a distance from the key position, selecting a key value from the candidate key values based on an output of a trained neural network, and extracting the key and the key value from the electronic file, regardless of a key-value structure.

Abstract: From a set of point data, a set of scattered rays is constructed. From the set of scattered rays, a set of ray slopes is computed. The set of ray slopes is mapped to a corresponding set of trigonometric functions. Using an optimization method, a parameter of the set of trigonometric functions is selected. Using an inverse of the set trigonometric functions, a vehicle mass corresponding to the set of point data is computed. Based on the vehicle mass, a threshold braking distance of a collision avoidance system of the vehicle is adjusted, the threshold braking distance comprising a distance from an object predicted to collide with the vehicle. By braking the vehicle at least the threshold braking distance from the object, a predicted collision between the vehicle and the object is avoided.

Abstract: A method, computer program product, and computer system for generating and using a basic state layer. N task models are provided (N ? 2). Each task model was trained on a same pre-trained backbone model. Each task model includes M feature layers and a task layer (M ? 1). Each feature layer of each task model includes a parameter matrix that is different for the different models. An encoder-decoder model is trained. The encoder-decoder model includes sequentially: an input layer, an encoder, M hidden layers, a decoder, and an output layer. The encoder is a neural network that maps and compresses the parameter matrices in the input layer into the M hidden layers, which generates a basic state model. The decoder is a neural network that receives the basic state model as input and generates the output layer to be identical to the input layer.