Translation tool

• US 20050171758A1
• Filed: 12/16/2004
• Published: 08/04/2005
• Est. Priority Date: 12/17/2003
• Status: Active Grant

• Current Assignee: Speechgear Incorporated
• Original Assignee: Speechgear Incorporated
• Inventors: Palmquist, Robert D.
• Granted Patent: US 7,359,849 B2
• Time in Patent Office: Days
• US Class Current: 704/4
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

In general, the invention is directed to text translation tools that are especially useful for translation of related electronic documents. Related electronic documents are any documents in electronic form that are related to one another, such as electronic slides, spreadsheet entries, pages of a book, a set of collected text files, and a set of drawings that including text and the like. The invention provides for translating source text from a source document in a source language into target text in a target language. The invention further provides for mapping the target text to target document according to one or more format characteristics of the source text. As a result, the target document preserves some of the “look and feel” of the source document. In source documents that include one or more graphic elements, the invention supports mapping the graphic elements to the target document.

Claims

1. A method comprising:

presenting a source document to a user, the source document including a source text in a source language and at least one graphic element;

mapping the graphic element to a target document;

generating a target text by translating the source text into a target language; and

mapping the target text to the target document.

2. The method of claim 1, wherein the source text defines a format characteristic and wherein mapping the target text to the target document comprises mapping the target text to the target document according to the format characteristic of the source text.

3. The method of claim 2, wherein the format characteristic comprises at least one of a source text size, a position of the source text in the source document, and a font of the source text.

4. The method of claim 1, further comprising presenting the source document and the target document to a user simultaneously.

5. The method of claim 1, further comprising:

interrogating the user about an aspect of the source text;

receiving a response from the user to the interrogation; and

translating the source text into the target language based at least in part on the response.

6. The method of claim 5, further comprising:

identifying a potential acronym in the source text; and

expanding the acronym,

wherein interrogating the user about the aspect of the source text comprises interrogating the user about an intended meaning of the potential acronym.

7. The method of claim 1, further comprising:

identifying an ambiguity in the source text;

determining whether the user has previously responded to an interrogation that resolves the ambiguity; and

translating the source text into the target language based at least in part on the previous response.

8. A method comprising:

for a first source document in a set of related electronic documents, the first source document including a first source text in a source language, identifying a first instance of an ambiguity in the first source text;

interrogating a user about the ambiguity;

receiving a response from the user to the interrogation;

translating the first source text into the target language based at least in part on the response;

identifying a second instance of the ambiguity in a second source document in the set of related electronic documents, the second source document including a second source text in the source language; and

translating the second source text into the target language based at least in part on the response.

9. The method of claim 8, wherein translating the first source text into the target language comprises generating a first target text and wherein translating the second source text into the target language comprises generating a second target text, the method further comprising:

mapping the first target text to a first target document; and

mapping the second target text to a second target document.

10. The method of claim 9, wherein the first source text includes at least one graphic element, the method further comprising mapping the graphic element to the first target document.

11. The method of claim 9, wherein the first source text defines a format characteristic and wherein mapping the first target text to the first target document comprises mapping the first target text to the first target document according to the format characteristic of the first source text.

12. The method of claim 8, wherein the ambiguity comprises an ambiguity about an intended meaning of a potential acronym.

13. The method of claim 8, further comprising:

following identification of the second instance of the ambiguity, interrogating the user a second time about the ambiguity, wherein interrogating the user the second time comprises presenting a list of meanings ordered as a function of the response.

14. A method comprising:

presenting a source document to a user, the source document including a source text defining at least one format characteristic;

generating a target text by translating the source text into a target language; and

mapping the target text to a target document according to the format characteristic.

15. The method of claim 14, wherein the source document further comprises a graphic element, the method further comprising mapping the graphic element to the target document.

16. The method of claim 14, wherein the format characteristic comprises at least one of a source text size, a position of the source text in the source document, and a font of the source text.

17. The method of claim 14, further comprising:

identifying a potential acronym in the source text;

interrogating the user about an intended meaning of the potential acronym;

receiving a response from the user to the interrogation; and

translating the potential acronym text into the target language based at least in part on the response.

18. A system comprising:

a display configured to present to a user a source document including a source text in a source language, to simultaneously present to the user a target document including a target text in a target language; and

a processor configured to translate the source text into the target text, and further configured to map the target text to the target document according to a format characteristic of the source text.

19. The system of claim 18, wherein the processor is further configured to interrogate a user about an instance of an ambiguity in the source text, to receive a response from the user to the interrogation, and to translate the source text into the target text based at least in part on the response.

20. The system of claim 19, further comprising memory to store a resolution of the ambiguity as a function of the response.