LANGUAGE PROCESSING SYSTEMS AND METHODS

• US 20100121630A1
• Filed: 11/07/2008
• Published: 05/13/2010
• Est. Priority Date: 11/07/2008
• Status: Abandoned Application

• Current Assignee: Lingupedia Investments S A R L
• Original Assignee: Lingupedia Investments S A R L
• Inventors: Bruckner, Yaron, Mende, Michael
• Application Number:
  US12/267,461
• Publication Number:
  US 20100121630A1
• Time in Patent Office: Days
• US Class Current: 704/7
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

Embodiments of the present disclosure include an electronic translation system employing a language-independent central representation of language to be translated. The system may include a language parser to translate to the language-independent representation, and a renderer to translate from the representation to a desired language supported by the system. In an embodiment, users of the translation system can add or modify their own languages.

Claims

1. A system for processing natural language including one or more data processing devices individually or together configured to execute software comprising:

a language-independent module, wherein the module manipulates a plurality of objects representing terms and relationships between the objects;

a plurality of language-dependent dictionary modules, each dictionary module having a plurality of entries, each entry of the dictionaries linked to one of the plurality of objects stored in the language-independent module;

a text parser associated with one or more of the language-dependent dictionary modules; and

a sentence generator associated with one or more of the language-dependent dictionary,

wherein the text parser accepts input, extracts key terms from the input, and uses a graph representation of the key terms based on the plurality of objects from the language-independent core module and wherein the sentence generator formulates output text in one of its associated languages based on the graph representation.

2. The system for processing natural language of claim 1 wherein the input comprises written text.

3. The system for processing natural language of claim 1 wherein the input comprises oral text.

4. The system for processing natural language of claim 1 comprising at least one linguistic syntactic module associated with one or more of the language-dependent dictionaries, the linguistic syntactic module including the text parser, a set of grammar rules, and a set of templates.

5. The system for processing natural language of claim 4 wherein each language-dependent dictionary is associated with a different linguistic syntactic module.

6. The system for processing natural language of claim 4 wherein the language-dependent dictionaries of at least two closely related languages are associated with the same linguistic syntactic module.

7. The system for processing natural language of claim 1 wherein the language-independent module further stores media representations of associated terms stored in the module.

8. The system for processing natural language of claim 7 wherein the media representations comprise pictures.

9. The system for processing natural language of claim 7 wherein the media representations comprise sounds.

10. The system for processing natural language of claim 7 further comprising an editing component module, wherein the editing component module facilitates the alteration of the dictionary entries and their links to the one of the plurality of objects stored in the language-independent module.

11. The system for processing natural language of claim 10 wherein the editing component module is further adapted to facilitate adding entries to the plurality of language-dependent dictionaries.

12. The system for processing natural language of claim 10 wherein the editing component module is adapted to be accessible from a website.

13. The system for processing natural language of claim 12 wherein the media representations of terms can be displayed within a virtual world.

14. The system for processing natural language of claim 12 wherein the editing component module restricts access to qualified users.

15. A computerized method for processing natural language, the steps of the method comprising:

receiving text input;

parsing said text input using a first language syntactic module to extract key terms and relationships between the key terms;

translating the key terms into language-independent object terms using a language-independent object world data structure and associations from a first language dictionary module;

generating a language-independent graph of the object terms and the relationships;

processing the language-independent graph; and

outputting the results.

16. The computerized method of claim 15 wherein the processing step comprises translating the language-independent graph into a second language using a second language dictionary module and a second language module and the results are output text in the second language.

17. The computerized method of claim 15 wherein the processing step comprises generating a search query.

18. A method of developing a language processing system comprising:

developing a language-independent core, the core comprising language term objects, each language term object comprising media representations of language terms, and links between associated language terms;

adding a dictionary object, associated with a specific language;

adding words from the specific language to the dictionary object; and

linking the words to the appropriate core language term objects.

19. The method of building a language processing system of claim 18 wherein the links between associated language terms include relational links and hierarchy links.

20. The method of building a language processing system of claim 18 comprising creating a language parser for the specific language based on grammar and syntax rules.