Acquiring accurate machine translation

• US 8,965,750 B2
• Filed: 11/17/2011
• Issued: 02/24/2015
• Est. Priority Date: 11/17/2011
• Status: Expired due to Fees

• Current Assignee: ABBYY Production LLC (ABBYY Software)
• Original Assignee: ABBYY InfoPoisk LLC
• Inventors: Danielyan, Tatiana
• Primary Examiner(s): Vo, Huyen X.
• Application Number:
  US13/299,111
• Publication Number:
  US 20130132065A1
• Time in Patent Office: 1,195 Days
• Field of Search: 704 1- 10, 704/251, 704/255, 704/257, 704/270, 704/277
• US Class Current: 704/3
• CPC Class Codes: G06F 40/47 Machine-assisted translation, e.g. using translation memory

Abstract

A method is disclosed for translating a sentence from a source language or input language into an output language. The method includes analyzing a source sentence using linguistic descriptions of the source language, constructing a language-independent semantic structure to represent the meaning of the source sentence, and generating an output sentence to represent the meaning of the source sentence using linguistic descriptions of the output language. To improve the accuracy of translation, the analysis or synthesis stage may include ratings or statistics obtained by analyzing a corpus of parallel texts. Disambiguation is remedied automatically or through user input such as through user interface elements.

Claims

1. A method for providing language translation, the method comprising:

receiving at a computer device a plurality of words in an input language;

determining, via a processor at the computer device, a linguistic structure of the plurality of words in the input language;

determining, via the processor, semantics of the plurality of words in the input language;

determining, via the processor, the plurality of words in the input language using linguistic descriptions of the input language;

translating, via the processor, the plurality of words in the input language to an expression in an output language;

identifying, via the processor, at least one word of the plurality of words in the input language that has a syntactic ambiguity or a semantic ambiguity;

displaying on a user interface two or more options corresponding to two or more meanings associated with said syntactic ambiguity or said semantic ambiguity;

receiving, at the processor, an indication of selection of one or more of the two or more options corresponding to two or more meanings;

displaying an indication of the selection of the one or more of the two or more options corresponding to said two or more meanings;

searching a subject area of further options, the subject area corresponding to one or more respective subject areas corresponding to the said one or more of the two or more options; and

displaying on the user interface one or more further options.

2. The method of claim 1, wherein displaying the indication of the selection of the one or more of the two or more options corresponding to said two or more meanings includes modifying the identified at least one word of the plurality of words in the output language.

3. The method of claim 1, wherein displaying the indication of the selection of the one or more of the two or more options corresponding to said two or more meanings includes changing, to one or more new words, the identified at least one word of the plurality of words in the output language.

4. The method of claim 1, wherein the options correspond to synonyms.

5. The method of claim 1, wherein receiving an indication of selection of more than one of the two or more options includes receiving an indication of a semantic class of meanings for the at least one word of the plurality of words in the input language.

6. The method of claim 1, wherein said one or more further options are in the output language.

7. The method of claim 1, wherein the two or more options corresponding to two or more meanings are presented in an order influenced by statistics related to the two or more meanings.

8. The method of claim 1, wherein the two or more options corresponding to two or more meanings are presented in an order influenced by a frequency of occurrence of the options in the input language.

9. The method of claim 1, wherein the two or more options corresponding to two or more meanings are presented in an order influenced by a frequency of occurrence of a translation of the respective options in the output language.

10. The method of claim 1, wherein the two or more options corresponding to two or more meanings are presented in an order influenced by statistics related to expressions in the output language.

11. The method of claim 1, wherein the two or more options corresponding to two or more meanings are presented in an order influenced by a statistical analysis of parallel corpora in the input language and in the output language.

12. The method of claim 1, wherein the method further comprises displaying on the user interface an option for selecting one of the two or more options corresponding to two or more meanings for accepting said one option for all instances of said ambiguity in the plurality of words in the input language.

13. A device for providing language translation, the device comprising:

a processor;

a memory in electronic communication with the processor, the memory configured with instructions for;

receiving a plurality of words in an input language;

determining a linguistic structure of the plurality of words in the input language;

determining a semantic relation among two or more of the plurality of words in the input language;

determining the plurality of words in the input language using linguistic descriptions of the input language;

translating the plurality of words in the input language to an expression in an output language;

identifying at least one word of the plurality of words in the input language that has a syntactic ambiguity or a semantic ambiguity;

displaying on a user interface two or more options corresponding to two or more meanings associated with said syntactic ambiguity or said semantic ambiguity;

receiving an indication of selection of one or more of the two or more options corresponding to two or more meanings;

displaying an indication of the selection of the one or more of the two or more options corresponding to said two or more meanings;

searching a subject area of further options, the subject area corresponding to one or more respective subject areas corresponding to the said one or more of the two or more options; and

displaying on the user interface one or more further options.

14. The device of claim 13, wherein displaying the indication of the selection of the one or more of the two or more options corresponding to said two or more meanings includes changing, to one or more new words, the identified at least one word of the plurality of words in the output language.

15. A non-transitory computer-accessible media encoded with instructions for performing a method, the method comprising:

receiving at a computer device a plurality of words in an input language;

determining, via a processor at the computer device, a linguistic structure of the plurality of words in the input language;

determining, via the processor, semantics of the plurality of words in the input language;

determining, via the processor, the plurality of words in the input language using linguistic descriptions of the input language;

translating, via the processor, the plurality of words in the input language to an expression in an output language;

identifying, via the processor, at least one word of the plurality of words in the input language that has a syntactic ambiguity or a semantic ambiguity;

displaying on a user interface two or more options corresponding to two or more meanings associated with said syntactic ambiguity or said semantic ambiguity;

receiving, at the processor, an indication of selection of one or more of the two or more options corresponding to two or more meanings;

displaying an indication of the selection of the one or more of the two or more options corresponding to said two or more meanings;

searching a subject area of further options, the subject area corresponding to one or more respective subject areas corresponding to the said one or more of the two or more options; and

displaying on the user interface one or more further options.

16. The non-transitory computer-accessible media of claim 15, wherein the two or more options corresponding to two or more meanings are presented in an order influenced by a frequency of occurrence of a translation of the respective options in the output language.

17. The non-transitory computer-accessible media of claim 15, wherein the two or more options corresponding to two or more meanings are presented in an order influenced by a statistical analysis of parallel corpora in the input language and in the output language.