Entity and attribute resolution in conversational applications

• US 9,892,208 B2
• Filed: 04/02/2014
• Issued: 02/13/2018
• Est. Priority Date: 04/02/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Anastasakos, Tasos, Rochette, Alexandre, Sarikaya, Ruhi
• Primary Examiner(s): Alam, Hosain
• Assistant Examiner(s): Phan, Tuan-Khanh
• Application Number:
  US14/243,826
• Publication Number:
  US 20150286747A1
• Time in Patent Office: 1,413 Days
• Field of Search: 707776, 455456, 701410-533
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/86 Mapping to a database
• CPC Class Codes: G06F 16/9017 using directory or table look-up use of a directory or look-up table in file systems G06F16/13
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

User input expressed as text may be analyzed for determining a type of response, such as an application response, and/or determining a type of task that is requested by the user input. Entity representations may be identified, classified and/or or tagged based on a type of response, type of task and/or a set of entity types. A surface form of an entity, ambiguous entity representation and/or other type of expression within the user input may be resolved, normalized and/or mapped to a normalized value. Normalizing entities and/or entity attributes may involve using a set of normalization rules, a lookup table, one or more machined learned methods, and/or an entity normalization index that associates entities with alternate surface forms derived from web corpora. The normalized value may be used to construct a request to a structured knowledge source and/or an application.

Claims

1. A computer-implemented method, comprising:

converting verbal user input into text at a computing device that includes a plurality of applications stored in a memory device;

analyzing, by the computing device, the text to determine a type of response that is requested by the verbal user input;

identifying, by the computing device, an entity representation that includes a phrase contained in the text;

determining, by the computing device, a set of entity types utilized by a structured knowledge source to provide the type of response;

determining, by the computing device, one or more requirements of the structured knowledge source;

tagging, by the computing device, the entity representation that includes the phrase with an entity type from the set of entity types;

detecting, by the computing device, whether the entity representation that includes the phrase is a surface form of an entity and requires normalization to comply with the one or more requirements of the structured knowledge source;

when it is determined that the surface form of the entity requires normalization, mapping, by the computing device, the surface form of the entity to a normalized value that complies with the one or more requirements of the structured knowledge source; and

constructing, by the computing device, a request, wherein the request includes the normalized value instead of the entity representation.

2. The computer-implemented method of claim 1, wherein analyzing the text to determine the type of response that is requested by the verbal user input includes one or more of:

detecting a domain of the verbal user input, and

detecting an intent of the verbal user input.

3. The computer-implemented method of claim 1, wherein the set of entity types corresponds to a set of domain-dependent entity attributes.

4. The computer-implemented method of claim 1, further comprising:

tagging one or more words contained in the phrase with a different entity type from the set of entity types.

5. The computer-implemented method of claim 1, wherein:

mapping the surface form to the normalized value is performed deterministically using a set of normalization rules to normalize one of a temporal expression, a geographic expression, or a numerical expression to a canonical format.

6. The computer-implemented method of claim 1, wherein mapping the surface form to the normalized value is performed using a lookup table to normalize a variant of the entity to a canonical name.

7. The computer-implemented method of claim 1, wherein mapping the surface form to the normalized value is performed using one or more machined learned methods to map a natural language expression to a normalized condition.

8. The computer-implemented method of claim 1, wherein mapping the surface form to the normalized value is performed using an entity normalization index that associates entities with alternate surface forms derived from web corpora.

9. The computer-implemented method of claim 8, further comprising:

extracting a set of entities from an entity knowledge source;

extracting related links that are relevant to the set of entities from a knowledge graph;

data mining one or more web search logs using the related links to discover related queries; and

building the entity normalization index by associating the related queries with the set of entities as alternate surface forms of the entities.

10. The computer-implemented method of claim 1, further comprising:

receiving, by the computing device, a response to the request that includes information from the structured knowledge source.

11. The computer-implemented method of claim 1, wherein the normalized value is used to construct a request that causes a task-based application to perform a particular task.

12. A computer-readable storage medium storing computer-readable instructions that, when executed by a processor of a computing device, causes the computing device to perform a method, comprising:

converting verbal user input into text;

analyzing the text to determine a type of response that is requested by the verbal user input;

identifying an entity representation that includes a phrase contained in the text;

determining a set of entity types utilized by a structured knowledge source to provide the type of response;

tagging the entity representation that includes the phrase with an entity type from the set of entity types;

detecting whether the entity representation that includes the phrase is a surface form of an entity and requires normalization to comply with one or more determined requirements of the structured knowledge source;

when it is determined that the surface form of the entity requires normalization, mapping the surface form of the entity to a normalized value that complies with the one or more determined requirements of the structured knowledge source; and

constructing a request, wherein the request includes the normalized value instead of the entity representation.

13. The computer-readable storage medium of claim 12, wherein mapping the surface form of the entity to the normalized value comprises using a set of normalization rules, a lookup table, a machine learned method, and an index that associates entities with alternate surface forms derived from web corpora.

14. The computer-readable storage medium of claim 12, wherein the surface form is one or more of:

a temporal expression, a geographic expression, a numerical expression, or a natural language expression.

15. The computer-readable storage medium of claim 12, wherein the request is configured for causing an application to perform a particular task that involves querying a remote resource for information related to the verbal user input.

16. The computer-readable storage medium of claim 12, wherein the set of entity types corresponds to a set of domain-dependent entity attributes.

17. A computing device, comprising:

a processor coupled to memory storing a plurality of applications and computer-readable instructions configured to;

convert verbal user input into text;

analyze the text to determine a type of response that is requested by the verbal user input;

identify an entity representation that includes a phrase contained in the text;

determine a set of entity types utilized by a structured knowledge source to provide the type of response;

tag the entity representation that includes the phrase with an entity type from the set of entity types;

detect whether the entity representation that includes the phrase is a surface form of an entity and requires normalization to comply with one or more determined requirements of the structured knowledge source;

when it is determined that the surface form of the entity requires normalization, map the surface form of the entity to a normalized value that complies with the one or more requirements of the structured knowledge source; and

construct a request for the structured knowledge source, wherein the request includes the normalized value instead of the entity representation.

18. The computing device of claim 17, wherein the computer-executable instructions stored in the memory implement a conversational intelligent personal assistant that communicates with an application.

19. The computing device of claim 17, wherein the surface form is one or more of:

a temporal expression, a geographic expression, a numerical expression, or a natural language expression.

20. The computing device of claim 17, wherein the application response is one or more of:

answering a question, playing a media item, or scheduling an event.