Providing search query results based on entity variant generation and normalization

• US 9,679,025 B2
• Filed: 04/17/2015
• Issued: 06/13/2017
• Est. Priority Date: 05/25/2012
• Status: Active Grant

• Current Assignee: AirBNB Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Crestani Campos, Adriano, Raghavan, Sriram, Li, Yunyao, Zhu, Huaiyu
• Primary Examiner(s): Abebe, Daniel
• Application Number:
  US14/689,885
• Publication Number:
  US 20150220608A1
• Time in Patent Office: 788 Days
• Field of Search: 704 7
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence

Abstract

Search results are provided for a search query. A search query including an entity and entity type is received. The entity is parsed into semantic components. Variants are generated based on input from auxiliary information and user configuration information for each of the semantic components. The entity is recomposed in different morphological forms from different variants of the semantic components. At least one morphological form for the entity is presented as a search result.

Claims

1. A method for providing search results for a search query, comprising:

receiving a search query including an entity and entity type;

parsing the entity into semantic components;

generating variants based on input from auxiliary information and user configuration information for each of the semantic components;

recomposing the entity in different morphological forms from different variants of the semantic components; and

presenting at least one morphological form for the entity as a search result.

2. The method of claim 1, wherein the at least one morphological form comprises a single normalized form for the different morphological forms.

3. The method of claim 1, wherein facets are generated dynamically to assist refining the search query.

4. The method of claim 1, wherein based on type of entity, different semantic components for each entity type are determined based on domain ontology and the user configuration information.

5. The method of claim 1, further comprising:

parsing based on the entity type;

determining semantic components utilizing domain ontology; and

recomposing the entity by selectively including different semantic components for combining the different variants of the semantic components.

6. The method of claim 1, further comprising recomposing the entity by selectively excluding different semantic components for combining the different variants of the semantic components.

7. The method of claim 1, wherein parsing further comprises parsing based on the entity type and auxiliary information.

8. A computer program product for providing search results for a search query, the computer program product comprising a non-transitory computer readable storage medium having instructions embodied therewith, the program instructions executable by a computer to cause the computer to:

receive, by the computer, a search query including an entity and entity type;

parse, by the computer, the entity into semantic components;

generate, by the computer, variants based on input from auxiliary information and user configuration information for each of the semantic components;

recompose, by the computer, the entity in different morphological forms from different variants of the semantic components; and

present, by the computer, at least one morphological form for the entity as a search result.

9. The computer program product of claim 8, wherein the at least one morphological form comprises a single normalized form for the different morphological forms.

10. The computer program product of claim 8, wherein facets are generated dynamically to assist refining the search query.

11. The computer program product of claim 8, wherein based on the entity type, different semantic components for each entity type are determined based on domain ontology and the user configuration information.

12. The computer program product of claim 8, further comprising program instructions executable by the computer to cause the computer to:

parse, by the computer, based on the entity type;

determine, by the computer, semantic components utilizing domain ontology; and

recompose, by the computer, the entity by selectively including different semantic components for combining the different variants of the semantic components.

13. The computer program product of claim 8, further comprising program instructions executable by the computer to cause the computer to:

recompose, by the computer, the entity by selectively excluding different semantic components for combining the different variants of the semantic components.

14. The computer program product of claim 8, wherein parse, by the computer, comprises parsing based on the entity type and auxiliary information.

15. A search query computing system, comprising:

an interface that receives a search query including an entity and entity type;

a parser that parses the entity into semantic components based on the entity type;

a variant generator that generates variants based on input from auxiliary information and user configuration information for each of the semantic components; and

a composer that recomposes the entity in different morphological forms from different variants of the semantic components;

wherein at least one morphological form for the entity is presented as a search result.

16. The search query computing system of claim 15, wherein the at least one morphological form comprises a single normalized form for the different morphological forms.

17. The search query computing system of claim 15, wherein facets are generated dynamically to assist refining the search query.

18. The search query computing system of claim 15, wherein based on entity type, different semantic components for each entity type are determined based on domain ontology and the user configuration information.

19. The search query computing system of claim 15, wherein:

the parser parses based on the entity type;

the variant generator determines semantic components utilizing domain ontology; and

the composer recomposes the entity by selectively including different semantic components for combining the different variants of the semantic components.

20. The search query computing system of claim 15, wherein:

the composer recomposes the entity by selectively excluding different semantic components for combining the different variants of the semantic components; and

the parser further parses based on the entity type and auxiliary information.