Autonomous system for hypotheses generation
AssigneeInternational Business Machines Corporation
InventorsVishrawas Gopalakrishnan, Kevin N. Tran, Fang Lu, Gigi Y. C. Yuen-Reed
Life of this patent
Estimating the term…
Abstract
A bioinformatics system for autonomous hypothesis generation for relatedness of seemingly independent concepts having tenuous or no prior known relationship in a knowledgebase. Independent concept pairs are identified in a question, and they are evaluated in light of lists of their similar concepts, and in light input documents, word embeddings, and co-occurrence matrices that are organized as a time series. Relationships between the independent concepts are hypothesized based on temporal analysis of relatedness measures of their similar concepts, measured via candidate connecting concepts.
Claims20
A method for evaluating relatedness of a pair of independent concepts by a bioinformatics system, the method comprising:
- receiving a query input comprising a pair of independent concepts comprising a first independent concept and a second independent concept, the first and second independent concepts having no formally recognized relationship in a knowledgebase of a domain of knowledge;
- generating a plurality of lists of similar concepts for the pair of independent concepts, the plurality of lists comprising a first list of concepts deemed similar to the first independent concept, and further comprising a second list of concepts deemed similar to the second independent concept;
- identifying a plurality of candidate connecting concepts for at least one pair of similar concepts, wherein a first concept in the at least one pair of similar concepts is selected from the first list of concepts and a second concept in the at least one pair of similar concepts is selected from the second list of concepts, and wherein the plurality of candidate connecting concepts co-occur, in a plurality of input documents, with the first and second concepts in the at least one pair of similar concepts;
- and
- generating a hypothesis for the pair of independent concepts based on the identified candidate connecting concepts, wherein the hypothesis represents a proposition that the first and second independent concepts are related.
A computer program product for evaluating relatedness of a pair of independent concepts by a bioinformatics system, the computer program product comprising a non-transitory tangible storage device having program code embodied therewith, the program code executable by a processor of a computer to perform a method, the method comprising:
- receiving, by the processor, a query input comprising a pair of independent concepts comprising a first independent concept and a second independent concept, the first and second independent concepts having no formally recognized relationship in a knowledgebase of a domain of knowledge;
- generating, by the processor, a plurality of lists of similar concepts for the pair of independent concepts, the plurality of lists comprising a first list of concepts deemed similar to the first independent concept, and further comprising a second list of concepts deemed similar to the second independent concept;
- identifying, by the processor, a plurality of candidate connecting concepts for at least one pair of similar concepts, wherein a first concept in the at least one pair of similar concepts is selected from the first list of concepts and a second concept in the at least one pair of similar concepts is selected from the second list of concepts, and wherein the plurality of candidate connecting concepts co-occur, in a plurality of input documents, with the first and second concepts in the at least one pair of similar concepts;
- and
- generating, by the processor, a hypothesis for the pair of independent concepts based on the identified candidate connecting concepts, wherein the hypothesis represents a proposition that the first and second independent concepts are related.
A computer system for evaluating relatedness of a pair of independent concepts by a bioinformatics system, comprising:
- one or more computer devices each having one or more processors and one or more tangible storage devices;
- and
- a program embodied on at least one of the one or more storage devices, the program having a plurality of program instructions for execution by the one or more processors, the program instructions comprising instructions for:
- receiving a query input comprising a pair of independent concepts comprising a first independent concept and a second independent concept, the first and second independent concepts having no formally recognized relationship in a knowledgebase of a domain of knowledge;
- generating a plurality of lists of similar concepts for the pair of independent concepts, the plurality of lists comprising a first list of concepts deemed similar to the first independent concept, and further comprising a second list of concepts deemed similar to the second independent concept;
- identifying a plurality of candidate connecting concepts for at least one pair of similar concepts, wherein a first concept in the at least one pair of similar concepts is selected from the first list of concepts and a second concept in the at least one pair of similar concepts is selected from the second list of concepts, and wherein the plurality of candidate connecting concepts co-occur, in a plurality of input documents, with the first and second concepts in the at least one pair of similar concepts;
- and
- generating a hypothesis for the pair of independent concepts based on the identified candidate connecting concepts, wherein the hypothesis represents a proposition that the first and second independent concepts are related.
Dependencies are inferred from the claim text.