International Business Machines Corporation

Jennifer Ann English

Malous Melissa Kossarian

Douglas A Smith

Charles E McManis, Jr

Bryn Robert Dole

Dmitriy Kernasovskiy

Harmony Y Shyr

A technique for answering questions includes receiving a question directed to a first subject. A mathematical operation is performed between each of one or more first topic vectors (associated with the first subject) and each of one or more second topic vectors (associated with a second subject) to generate respective strength values. Relevant ones of the respective strength values are summed to provide an overall strength value, which is utilized to determine a semantic distance (SD) between the first subject and the second subject. In response to the SD being within a threshold distance value (TDV), information associated with the first subject and the second subject is utilized to answer the question. In response to the SD not being within the TDV, information associated with the first subject is utilized to answer the question.

Answering questions based on semantic distances between subjects

A computer-implemented method according to one embodiment includes receiving a search query; determining a first set of categories associated with the search query, including performing a reverse lookup for the search query using a dynamic inference map in order to determine the first set of categories, where each category of the first set of categories includes one or more words that describe one or more aspects of the search query; determining a second set of categories associated with preliminary results of the search query; and filtering the preliminary results of the search query, including removing a subset of the preliminary results of the search query based on a comparison of the first set of categories to the second set of categories.

Categorically filtering search results

A technique for calculating a semantic distance between subjects includes performing a mathematical operation between each of one or more first topic vectors and each of one or more second topic vectors to generate respective strength values. The first topic vectors are associated with respective first topics of a first subject, the second topic vectors are associated with respective second topics of a second subject, and the respective strength values are indicative of a relative closeness between associated ones of the first and second topics. Relevant ones of the respective strength values are summed to provide an overall strength value between the first subject and the second subject. A semantic distance between the first subject and the second subject is determined based on the overall strength value.

Techniques for determining a semantic distance between subjects

A computer-implemented method according to one embodiment includes identifying a search query, determining a first set of categories associated with the search query, determining a second set of categories associated with preliminary results of the search query, and filtering the preliminary results of the search query based on an analysis utilizing the first set of categories and the second set of categories.

Determining a semantic distance between subjects

Embodiments provide a system and method for semantic distance calculation. The method can involve receiving a plurality of documents having a set of subjects extracted through the use of latent dirichlet allocation; for each document in the plurality of documents, generating a classification list comprising a ranking of the one or more subjects based on the relevance of each subject to the document; for each classification list, calculating the semantic distance between each subject present on the classification list; aggregating the plurality of classification lists; and creating a distance matrix containing the relative semantic distances between each member of the set of subjects.

Phenomenological semantic distance from latent dirichlet allocations (LDA) classification

Embodiments provide a system and method for semantic distance calculation. The method can involve ingesting a plurality of documents; extracting a set of subjects from the plurality of documents using latent dirichlet allocation; for each document in the plurality of documents, generating a classification list comprising a ranking of the one or more subjects based on the relevance of each subject to the document; for each classification list, calculating the semantic distance between each subject present on the classification list; aggregating the plurality of classification lists; and creating a distance matrix containing the relative semantic distances between each member of the set of subjects.

Growing community of inventors

Redwood City, CA, United States of America

Jennifer Ann English