Systems and method for investigating relationships among entities
Connections among two different entities are identified by processing a collection of documents to identify one or more documents that contain co-occurring mentions of each of the two different entities. This relationship may be graphically displayed in a user interface with an icon or the like for each of the two entities, along with a graphical link interconnecting the entities. The graphical link can be an active element of the user interface that responds to user interactions by providing access to evidence within the collection of documents that substantiates the connection between the two entities. In one aspect, a search input form field in a user interface may be used to explicitly request documents that substantiate a relationship between two entities. In another aspect, a user may ground entity mentions by explicitly selecting documents that mention an entity of interest.
1. A non-transitory machine-readable storage medium that provides instructions that, if executed by a processor, are configurable to cause the processor to perform operations comprising:
receiving a keyword search from a user via a search input form field of a user interface for a search engine;
applying a coreference algorithm to the keyword search to predict an entity intended by the user and characterized by one or more entity-related groups of mentions;
presenting a first search result to the user in the user interface, the first search result including a first plurality of entity tags and a plurality of documents from a collection of documents, each one of the plurality of documents containing a mention located by the search engine in at least one of the one or more entity-related groups of mentions, and each one of the first plurality of entity tags corresponding to at least one of the mentions;
receiving a first selection from the user of a first entity tag for a first entity characterized by a first entity-related group of mentions from the first plurality of entity tags, the first selection indicative of a user confirmation that the keyword search was intended to reference the first entity;
adding the first entity tag to the search input form field;
applying a relevance algorithm to identify a text comprising an evidence passage within a second plurality of documents, the evidence passage providing evidence indicating an existence or nature of a relationship between the first entity and one or more other entities characterized by one or more other entity-related groups of mentions, the relevance algorithm predicting that the text provides evidence of a relationship between the first entity and the one or more other entities;
presenting a second plurality of entity tags, each corresponding to one of the one or more other entities in the user interface;
receiving a second selection from the user of a second entity tag from the second plurality of entity tags; and
presenting a second search result including one or more of the second plurality of documents that substantiate a relationship between the first entity and a second entity based on the evidence passage.
2. The computer program product of claim 1 further comprising code that performs the step of displaying the relationship graphically in the user interface as a first icon for the first entity, a second icon for the second entity, and a connector visually coupling the first icon to the second icon.
3. The computer program product of claim 1 further comprising code that performs the step of displaying the relationship within the search input form field as the first entity tag coupled to the second entity tag by a relationship operator.
4. The computer program product of claim 3 wherein the relationship operator includes a “<>” symbol.
5. The computer program product of claim 1 wherein the collection of documents includes documents hosted locally on a user device where the keyword search is received.
6. The computer program product of claim 1 wherein the collection of documents includes documents distributed on a wide area network.
7. The computer program product of claim 1 wherein the plurality of documents includes documents hosted on a remote cloud storage facility.
8. The computer program product of claim 1 wherein presenting the second search result includes graphically presenting a plurality of entity tags each connected to the first entity by an edge in a graph.
9. A method comprising:
receiving a keyword search from a user in a search input form field of a user interface for a search engine;
predicting one or more entities intended by the user;
presenting a first search result to the user in the user interface, the first search result including a first plurality of entity tags and a plurality of documents, each one of the plurality of documents containing a mention located by the search engine of at least one of the one or more entities, and each one of the first plurality of entity tags corresponding to at least one of the mentions;
receiving a first selection from the user of a first entity tag for a first entity from the first plurality of entity tags, the first selection indicative of a user confirmation that the keyword search was intended to reference the first entity;
adding the first entity tag to the search input form field;
identifying a text comprising an evidence passage within a second plurality of documents, the evidence passage providing evidence indicating an existence or nature of a relationship between the first entity and one or more other entities;
presenting a second plurality of entity tags for the one or more other entities in the user interface;
receiving a second selection from the user of a second entity tag for a second entity from the second plurality of entity tags; and
presenting a second search result including one or more of the second plurality of documents that substantiate a relationship between the first entity and the second entity based on the evidence text.
10. The method of claim 9 further comprising displaying the relationship graphically in the user interface as a first icon for the first entity, a second icon for the second entity, and a connector visually coupling the first icon to the second icon.
11. The method of claim 9 further comprising displaying the relationship within the search input form field as the first entity tag coupled to the second entity tag by a relationship operator.
12. The method of claim 11 wherein the relationship operator includes a “<>” symbol.
13. The method of claim 9 wherein predicting one or more entities intended by the user in the keyword search includes applying a coreference algorithm to the keyword search to predict one or more entities intended by the user.
14. The method of claim 9 wherein identifying text in the plurality of documents that provides evidence of a relationship between the first entity and one or more other entities includes applying a relevance algorithm to identify text in the plurality of documents that provides evidence of a relationship between the first entity and one or more other entities, the relevance algorithm predicting that the text provides evidence of a relationship between the first entity and the one or more other entities.
15. The method of claim 9 wherein the plurality of documents includes documents obtained from a collection of documents hosted locally on a user device where the keyword search is received.
16. The method of claim 9 wherein the plurality of documents includes documents obtained from a collection of documents distributed on a wide area network.
17. The method of claim 9 wherein the plurality of documents includes documents obtained from a collection of documents hosted on a remote cloud storage facility.
18. The method of claim 9 further comprising storing a relation description characterizing a relationship between the first entity and the second entity for further use by the user within the user interface.
19. The method of claim 9 further comprising graphically displaying a first icon for the first entity, a second icon for the second entity, and a connector visually coupling the first icon to the second icon to illustrate the relationship, wherein the connector includes a user interface element providing access by a user to evidence of the relationship within the second plurality of documents.
20. A system comprising:
a search engine;
a data network;
a computing device coupled to the search engine through the data network, the computing device including a processor, a memory, and a display, the memory storing code executable by the processor to perform the steps of receiving a keyword search from a user in a search input form field of a user interface, predicting one or more entities intended by the user; presenting a first search result to the user in the user interface, the first search result including a first plurality of entity tags and a plurality of documents, each one of the plurality of documents containing a mention located by the search engine of at least one of the one or more entities, and each one of the first plurality of entity tags corresponding to at least one of the mentions; receiving a first selection from the user of a first entity tag for a first entity from the first plurality of entity tags, the first selection indicative of a user confirmation that the keyword search was intended to reference the first entity; adding the first entity tag to the search input form field; identifying a text comprising an evidence passage within a second plurality of documents, the evidence passage providing evidence indicating an existence or nature of a relationship between the first entity and one or more other entities; presenting a second plurality of entity tags for the one or more other entities in the user interface; receiving a second selection from the user of a second entity tag for a second entity from the second plurality of entity tags; and presenting a second search result including one or more of the second plurality of documents that substantiate a relationship between the first entity and the second entity based on the evidence text.
21. A non-transitory machine-readable storage medium that provides instructions that, if executed by a processor, are configurable to cause the processor to perform operations comprising:
displaying a user interface for a search engine, the user interface including a search input form field;
receiving a user input to the search input form field;
parsing the user input to identify a first text string identifying a first entity, a second text string identifying a second entity, and an operator between the first text string and the second text string specifying to the search engine a request to search for evidence of a relationship between the first entity and the second entity;
in response to the operator, searching for one or more documents in a collection of documents that contain mentions that a coreference algorithm predicts are mentions that an author intended to refer to the first entity and other mentions that a coreference algorithm predicts are mentions that the author intended to refer to the second entity, and that provide a text comprising an evidence passage that a relevance algorithm predicts provides evidence of a relationship between the first entity and the second entity, the evidence passage providing evidence indicating an existence or nature of a relationship between the first entity and the second entity; and
presenting a plurality of the one or more documents in the user interface that substantiates a relationship between the first entity and the second entity based on the evidence text.