Relation extraction from a corpus using an information retrieval based procedure

A computer usable program product comprising one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices, the stored program instructions comprising:

• program instructions to receive an input entity pair including a first entity and a second entity, the first entity and the second entity being associated by a particular relation;
• program instructions to retrieve a first set of statements containing the first entity from a corpus;
• program instructions to retrieve a second set of statements containing the second entity from the corpus;
• program instructions to identify, by a processor and a memory, a first set of discriminative words in the first set of statements;
• program instructions to identify, by the processor and the memory, a second set of discriminative words in the second set of statements;
• program instructions to identify perceptions in the first set of discriminative words and the second set of discriminative words;
• program instructions to retrieve a predetermined number of ranked statements from the corpus using the identified perceptions as a query;
• program instructions to identify, in response to the query, candidate entity pairs, the candidate entity pairs including a third entity and a fourth entity;
• and
• program instructions to extract candidate entity pairs from the predetermined number statements, the candidate entity pairs having a relation therebetween analogous to the relation between the first entity and the second entity.

A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:

• program instructions to receive an input entity pair including a first entity and a second entity, the first entity and the second entity being associated by a particular relation;
• program instructions to retrieve a first set of statements containing the first entity from a corpus;
• program instructions to retrieve a second set of statements containing the second entity from the corpus;
• program instructions to identify, by a processor and a memory, a first set of discriminative words in the first set of statements;
• program instructions to identify, by the processor and the memory, a second set of discriminative words in the second set of statements;
• program instructions to identify perceptions in the first set of discriminative words and the second set of discriminative words;
• program instructions to retrieve a predetermined number of ranked statements from the corpus using the identified perceptions as a query;
• program instructions to identify, in response to the query, candidate entity pairs, the candidate entity pairs including a third entity and a fourth entity;
• and
• program instructions to extract candidate entity pairs from the predetermined number statements, the candidate entity pairs having a relation therebetween analogous to the relation between the first entity and the second entity.