Discovering discovery patterns with Predication-based Semantic Indexing.

In this paper we utilize methods of hyperdimensional computing to mediate the identification of therapeutically useful connections for the purpose of literature-based discovery. Our approach, named Predication-based Semantic Indexing, is utilized to identify empirically sequences of relationships known as "discovery patterns", such as "drug x INHIBITS substance y, substance y CAUSES disease z" that link pharmaceutical substances to diseases they are known to treat. These sequences are derived from semantic predications extracted from the biomedical literature by the SemRep system, and subsequently utilized to direct the search for known treatments for a held out set of diseases.

EpiphaNet: An Interactive Tool to Support Biomedical Discoveries.

Unlabelled: Background. EpiphaNet is an interactive knowledge discovery system which enables researchers to explore visually sets of relations extracted from MEDLINE using a combination of language processing techniques. In this paper, we discuss the theoretical and methodological foundations of the system, and evaluate the utility of the models that underlie it for literature-based discovery.

The trajectory of scientific discovery: concept co-occurrence and converging semantic distance.

The paradigm of literature-based knowledge discovery originated by Swanson involves finding meaningful associations between terms or concepts that have not occurred together in any previously published document. While several automated approaches have been applied to this problem, these generally evaluate the literature at a point in time, and do not evaluate the role of change over time in distributional statistics as an indicator of meaningful implicit associations. To address this issue, we develop and evaluate Symmetric Random Indexing (SRI), a novel variant of the Random Indexing (RI) approach that is able to measure implicit association over time.

Predication-based semantic indexing: permutations as a means to encode predications in semantic space.

Corpus-derived distributional models of semantic distance between terms have proved useful in a number of applications. For both theoretical and practical reasons, it is desirable to extend these models to encode discrete concepts and the ways in which they are related to one another. In this paper, we present a novel vector space model that encodes semantic predications derived from MEDLINE by the SemRep system into a compact spatial representation.