Abstract: An approach is provided in which an information handling system detects a multi-entity co-occurrence anomaly within a set of documents that corresponds to an amount of times that a first entity and a second entity co-occur in the set of documents. The information handling system then determines that at least one of the documents includes a title having a verb that grammatically connects the first entity to the second entity. As such, the information handling system collects document segments from the set of documents that have the first entity, the second entity, and the connecting verb. In turn, the information handling system uses the collected document segments to train a relation-based classifier.

Abstract: An approach is provided in which a knowledge manager selects an extraction layer from a convolutional neural network that was trained on an initial set of images. The knowledge manager processes subsequent images obtained from crawling a computer network that includes extracting image feature sets of the subsequent images from the selected extraction layer and generating tags from metadata associated with the subsequent images. In turn, the knowledge manager receives a new image, extracts a new image feature set from the selected extraction layer, and assigns one or more of the tags to the new image based upon evaluating the new image feature set to the image features sets of the subsequent images.

Abstract: An approach is provided in which a knowledge manager locates centroids in a high-dimensional vector space that are closest to a new image feature set and performs nearest neighbor searches on feature sets included in clusters corresponding to the located centroids. The knowledge manager then selects feature sets closest to the new image feature set based on the nearest neighbor searches and in turn, marks images corresponding to the selected closest features sets as similar images to a new image corresponding to the new image feature set.

Abstract: An approach is provided in which an information handling system detects a multi-entity co-occurrence anomaly within a set of documents that corresponds to an amount of times that a first entity and a second entity co-occur in the set of documents. The information handling system then determines that at least one of the documents includes a title having a verb that grammatically connects the first entity to the second entity. As such, the information handling system collects document segments from the set of documents that have the first entity, the second entity, and the connecting verb. In turn, the information handling system uses the collected document segments to train a relation-based classifier.

Abstract: An approach is provided in which a knowledge manager selects an extraction layer from a convolutional neural network that was trained on an initial set of images. The knowledge manager processes subsequent images obtained from crawling a computer network that includes extracting image feature sets of the subsequent images from the selected extraction layer and generating tags from metadata associated with the subsequent images. In turn, the knowledge manager receives a new image, extracts a new image feature set from the selected extraction layer, and assigns one or more of the tags to the new image based upon evaluating the new image feature set to the image features sets of the subsequent images.

Abstract: An approach is provided in which a knowledge manager selects an extraction layer from a convolutional neural network that was trained on an initial set of images. The knowledge manager processes subsequent images obtained from crawling a computer network that includes extracting image feature sets of the subsequent images from the selected extraction layer and generating tags from metadata associated with the subsequent images. In turn, the knowledge manager receives a new image, extracts a new image feature set from the selected extraction layer, and assigns one or more of the tags to the new image based upon evaluating the new image feature set to the image features sets of the subsequent images.

Abstract: An approach is provided in which a knowledge manager locates centroids in a high-dimensional vector space that are closest to a new image feature set and performs nearest neighbor searches on feature sets included in clusters corresponding to the located centroids. The knowledge manager then selects feature sets closest to the new image feature set based on the nearest neighbor searches and in turn, marks images corresponding to the selected closest features sets as similar images to a new image corresponding to the new image feature set. identifies a set of closest centroids to a new image in a high-dimensional vector space and performs a nearest neighbors search between the new image and each of the images included in a set of clusters that correspond to the set of closest centroids. In turn, the knowledge manager selects similar images based upon the nearest neighbors search and provides the similar images to a user interface.

Abstract: An approach is provided in which a knowledge manager selects an extraction layer from a convolutional neural network that was trained on an initial set of images. The knowledge manager processes subsequent images obtained from crawling a computer network that includes extracting image feature sets of the subsequent images from the selected extraction layer and generating tags from metadata associated with the subsequent images. In turn, the knowledge manager receives a new image, extracts a new image feature set from the selected extraction layer, and assigns one or more of the tags to the new image based upon evaluating the new image feature set to the image features sets of the subsequent images.