Entity variant generation and normalization

• US 9,063,926 B2
• Filed: 08/27/2012
• Issued: 06/23/2015
• Est. Priority Date: 05/25/2012
• Status: Expired due to Fees

• Current Assignee: AirBNB Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Crestani Campos, Adriano, Li, Yunyao, Raghavan, Sriram, Zhu, Huaiyu
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US13/595,241
• Publication Number:
  US 20130317807A1
• Time in Patent Office: 1,030 Days
• Field of Search: 704/7
• US Class Current: 1/1
• 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

Determining variants of a text entity comprises parsing the text entity into semantic components and generating variants for each of the semantic components. The entity is recomposed in different morphological forms from the different variants of the semantic components.

Claims

1. A method for determining variants of a text entity, comprising:

parsing the text entity into semantic components;

generating variants based on input from auxiliary information and user configuration information for each of the semantic components, wherein based on the type of entity, different semantic components for each entity type are determined based on domain ontology and the user configuration information; and

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

2. The method of claim 1, further comprising parsing based on the type of the entity.

3. The method of claim 1, further comprising determining semantic components utilizing domain ontology.

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

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

6. The method of claim 1, further comprising composing the variants together into results including complete entity forms, or one normalized form, based on user configuration information.

7. The method of claim 2, wherein parsing further comprises parsing based on user configuration.

8. The method of claim 2, wherein parsing further comprises parsing based on the type of the entity and optionally auxiliary information.

9. The method of claim 8, wherein the auxiliary information comprises one or more common dictionaries.