International Business Machines Corporation

Cesar Berrospi Ramis

Peter Willem Jan Staar

Kubilay Atasu

Abderrahim Labbi

Nikolaos Livathinos

Maksym Lysak

Viktor Kuropiatnyk

Charalampos Pozidis

Nikolas Ioannou

Thomas P Parnell

Vasileios Vasileiadis

Francesco Fusco

Ranking a plurality of text elements, each comprising at least one word, by specificity. For each text element to be ranked, such a method includes computing an embedding vector that locates a text element in an embedding space, and selecting a set of text fragments from reference text. Each of these text fragments contains the text element to be ranked and further text elements. For each text fragment, the method calculates respective distances in the embedding space between the further text elements. The method further includes calculating a specificity score for the text element to be ranked and storing the specificity score. After ranking the plurality of text elements, a text data structure using the specificity scores for text elements to extract data having a desired specificity from the data structure may be processed.

Specificity ranking of text elements and applications thereof

A computing system, program products and computer-implemented method of exploring data comprises accessing data structures and executing an interaction loop. Data structure captures connected graph nodes associated with attributes containing human-readable data. Interaction loop receives user-selected attributes associated with focal nodes and executes subroutines to determine layouts of an arborescence extending from focal nodes. The subroutines use starting nodes and pivot attributes as arguments. Identifying nodes of subroutines are connected to starting nodes by walking the graph and comparing pivot attributes with attributes associated with connected nodes, obtaining distance-dependent quantities. Subroutines compute layout data, including coordinates of the connected nodes. Coordinates are determined in accordance with the distance-dependent quantities. Interaction loop displays arborescence according to the layout data. Subroutines can be recursively executed, whereby, at each recursion level of execution, it is called with the selected attribute and each node of a selection of nodes, as a starting node.

Visually exploring implicit features of hierarchical graphs based on attributes of nodes of the graphs

A method for creating a database for a domain specific application includes providing a centralized data repository comprising data from different sources, identifying a set of data units of the repository that represent a specific domain, determining a pivotal entity type for an application, determining a mapping between different identifiers of the pivotal entity type, creating a reference set by selecting a first subset of the set of data units using the mapping, wherein the first subset represents the pivotal entity type, selecting, based at least in part on the mapping, a second subset of the set of data units, wherein the second subset represents non-pivotal entity types which are related to instances of the pivotal entity type in the reference set; and creating a database from data units and associated attributes selected from the reference set of data units and the second subset of data units.

Preparing a database for a domain specific application using a centralized data repository

Two sets Xand Xof histograms of words, and a vocabulary V are accessed. Each of the two sets is representable as a sparse matrix, each row of which corresponds to a histogram. Each histogram is representable as a sparse vector, whose dimension is determined by a dimension of the vocabulary. Two phases compute distances between pairs of histograms. The first phase includes computations performed for each histogram and for each word in the vocabulary to obtain a dense, floating-point vector y. The second phase includes computing, for each histogram, a sparse-matrix, dense-vector multiplication between a matrix-representation of the set Xof histograms and the vector y. The multiplication is performed to obtain distances between all histograms of the set Xand each histogram X[j]. Distances between all pairs of histograms are obtained, based on which distances between documents can subsequently be assessed.

Low-complexity methods for assessing distances between pairs of documents

In an approach for construing similarities between datasets, a processor accesses a pair of sets of feature weights, wherein the sets of feature weights include a query dataset and comprises first weights associated to first features and a reference dataset and comprises second weights associated to second features. Based on similarities between the first features and the second features, a processor discovers flows from the first features to the second features, wherein the flows maximize an overall similarity between the pair of sets of feature weights. Based on the similarities and the flows, a processor computes pair contributions to the overall similarity in order to obtain contributive elements, wherein the pair contributions are contributions of pairs joining the first features to the second features. A processor ranks the contributive elements to obtain respective ranks. A processor returns a result comprising the contributive elements and indications to the respective ranks.

Growing community of inventors

Zurich, Switzerland

Cesar Berrospi Ramis