US 10,540,440 B2Granted

Relation extraction using Q and A

AssigneeInternational Business Machines Corporation

InventorsBrendan C. Bull, Scott R. Carrier, Aysu Ezen Can, Dwi Sianto Mansjur

Life of this patent

Estimating the term…

Loading patent…

Abstract

Embodiments of the present invention disclose a method, a computer program product, and a computer system for extracting natural language relations between entities. A computer receives a configuration for associating one or more natural language questions with one or more entities and identifies the one or more entities annotated within a document. The computer answers the natural language questions associated with the identified one or more entities based on context surrounding the identified one or more entities. The computer may further transmit the natural language questions associated with the identified one or more entities and the surrounding context to a question and answer service, then receive answers to the natural language questions from the question and answer service. The computer may further determine whether the received answers correctly describe the relation between the identified one or more entities and other entities within the extracted surrounding context.

Claims14

Dependent claims

A computer-implemented method of extracting entity relations, wherein the method comprises:

receiving, by a computer, one or more preprogrammed questions associated with one or more entities;
identifying, by the computer, an entity of the one or more entities annotated within a document;
extracting, by the computer, a portion of content in a proximity to the identified entity;
determining, by the computer, one or more relations describing an association between the identified entity and one or more other entities within the extracted portion of content based on the extracted portion of content and answering the one or more preprogrammed questions associated with the identified entity;
and
determining, by the computer, whether the received one or more relations correctly describe the association between the identified entity and the one or more other entities by:
receiving, by the computer, an entity class associated with at least one of the one or more preprogrammed questions;
determining, by the computer, whether at least one of the received one or more relations correspond to the entity class associated with the at least one of the one or more preprogrammed questions;
and
based on determining that at least one of the received one or more relations correspond to the entity class associated with the at least one of the one or more preprogrammed questions, determining, by the computer, that the at least one of the received one or more relations is correct based on machine learning tools.

7 more elements

A computer program product for extracting entity relations, the computer program product comprising:

one or more non-transitory computer-readable storage media and program instructions stored on the one or more non-transitory computer-readable storage media, the program instructions comprising:
program instructions to receive one or more preprogrammed questions associated with one or more entities;
program instructions to identify an entity of the one or more entities annotated within a document;
program instructions to extract a portion of content in a proximity to the identified entity;
and
program instructions to determine one or more relations describing an association between the identified entity and one or more other entities within the extracted portion of content based on the extracted portion of content and answering the one or more preprogrammed questions associated with the identified entity;
and
program instructions to determine whether the received one or more relations correctly describe the association between the identified entity and the one or more other entities by:
program instructions to receive an entity class associated with at least one of the one or more preprogrammed questions;
program instructions to determine whether at least one of the received one or more relations correspond to the entity class associated with the at least one of the one or more preprogrammed questions;
and
based on determining that at least one of the received one or more relations correspond to the entity class associated with the at least one of the one or more preprogrammed questions, program instructions to determine that the at least one of the received one or more relations is correct based on machine learning tools.

9 more elements

A computer system for extracting entity relations, the computer system comprising:

one or more computer processors, one or more computer-readable storage media, and program instructions stored on one or more of the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising:
program instructions to receive one or more preprogrammed questions associated with one or more entities;
program instructions to identify an entity of the one or more entities annotated within a document;
program instructions to extract a portion of content in a proximity to the identified entity;
and
program instructions to determine one or more relations describing an association between the identified entity and one or more other entities within the extracted portion of content based on the extracted portion of content and answering the one or more preprogrammed questions associated with the identified entity;
and
program instructions to determine whether the received one or more relations correctly describe the association between the identified entity and the one or more other entities by:
program instructions to receive an entity class associated with at least one of the one or more preprogrammed questions;
program instructions to determine whether at least one of the received one or more relations correspond to the entity class associated with the at least one of the one or more preprogrammed questions;
and
based on determining that at least one of the received one or more relations correspond to the entity class associated with the at least one of the one or more preprogrammed questions, program instructions to determine that the at least one of the received one or more relations is correct based on machine learning tools.

9 more elements

Dependencies are inferred from the claim text.