Apparatus, method, and computer program product for supporting communication through translation between languages

• US 7,873,508 B2
• Filed: 03/07/2006
• Issued: 01/18/2011
• Est. Priority Date: 05/25/2005
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Digital Solutions Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Chino, Tetsuro, Kamatani, Satoshi
• Primary Examiner(s): Hudspeth; David R
• Assistant Examiner(s): Neway; Samuel G
• Application Number:
  US11/368,406
• Publication Number:
  US 20060271350A1
• Time in Patent Office: 1,778 Days
• Field of Search: None
• US Class Current: 704/2
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/45 Example-based machine translation; Alignment

Abstract

A communication support apparatus includes a speech recognizer that recognizes a first speech of a source language as a first source language sentence, and recognizes a second speech of the source language following the first speech as a second source language sentence; a determining unit that determines whether the second language sentence is similar to the first language sentence; and a language converter that translates the first source language sentence into a first translation sentence, and translates the second source language sentence into a second translation sentence different from the first translation sentence when the determining unit determines that the second language sentence is similar to the first language sentence.

Claims

1. A communication support apparatus comprising:

a processing system comprising at least one processor; and

a memory comprising one or more tangible computer-readable media containing instructions for execution by the processing system, wherein the instructions, when executed by the processing system, programmatically define;

a speech recognizer that recognizes a first speech of a source language as a first source language sentence, and recognizes a second speech of the source language following the first speech as a second source language sentence;

a determining unit that determines whether the second source language sentence is similar to the first source language sentence; and

a language converter that translates the first source language sentence into a first translation sentence, and translates the second source language sentence into a second translation sentence different from the first translation sentence when the determining unit determines that the second language sentence is similar to the first source language sentence.

2. The communication support apparatus according to claim 1, further comprising a translation data storage that stores a source language sentence and at least one translation candidate sentence which is a target language sentence having the same meaning as the source language sentence, the source language sentence and the translation candidate sentence being associated with each other,

wherein when the determining unit determines that the second source language sentence is similar to the first source language sentence, the language converter searches the translation data storage for at least one translation candidate sentence with the first source language sentence and the second source language sentence being each a search key, selects a first translation candidate sentence from the at least one translation candidate sentence as the first translation sentence, and selects a second translation candidate sentence different from the first translation candidate sentence from the at least one translation candidate sentence as the second translation sentence.

3. The communication support apparatus according to claim 1, wherein the instructions further programmatically define:

a source language analyzer that analyzes a meaning of the first source language sentence to output at least one first analysis result candidate, and analyzes a meaning of the second source language sentence to output at least one second analysis result candidate,

wherein when the determining unit determines that the second source language sentence is similar to the first source language sentence, the language converter selects one of the at least one first analysis result candidate, selects one of the at least second analysis result candidate different from the one of the at least one first analysis result candidate, translates the first source language sentence into the first translation sentence based on the first analysis result candidate selected, and translates the second source language sentence into the second translation sentence based on the second analysis result candidate selected.

4. The communication support apparatus according to claim 3,

wherein the source language analyzer morphologically analyzes the first source language sentence to output at least one first morphological analysis result candidate as the at least one first analysis result candidate, and analyzes the second source language sentence to output at least one second morphological analysis result candidate as the at least one second analysis result candidate,

when the determining unit determines that the second source language sentence is similar to the first source language sentence, the language converter selects one of the at least one first morphological analysis result candidate, selects one of the at least second morphological analysis result candidate different from the one of the at least one first morphological analysis result candidate, translates the first source language sentence into the first translation sentence based on the first morphological analysis result candidate selected, and translates the second source language sentence into the second translation sentence based on the second morphological analysis result candidate selected.

5. The communication support apparatus according to claim 3,

wherein the source language analyzer parses the first source language sentence to output at least one first parsing analysis result candidate as the at least one first analysis result candidate, and analyzes the second source language sentence to output at least one second parsing analysis result candidate as the at least one second analysis result candidate,

when the determining unit determines that the second source language sentence is similar to the first source language sentence, the language converter selects one of the at least one first parsing analysis result candidate, selects one of the at least second parsing analysis result candidate different from the one of the at least one first parsing analysis result candidate, translates the first source language sentence into the first translation sentence based on the first parsing analysis result candidate selected, and translates the second source language sentence into the second translation sentence based on the second parsing analysis result candidate selected.

6. The communication support apparatus according to claim 3,

wherein the source language analyzer subjects the first source language sentence to a modification analysis to output at least one first modification analysis result candidate as the at least one first analysis result candidate, and subjects the second source language sentence to the modification analysis to output at least one second modification analysis result candidate as the at least one second analysis result candidate,

when the determining unit determines that the second source language sentence is similar to the first source language sentence, the language converter selects one of the at least one first modification analysis result candidate, selects one of the at least second modification analysis result candidate different from the one of the at least one first modification analysis result candidate, translates the first source language sentence into the first translation sentence based on the first modification analysis result candidate selected, and translates the second source language sentence into the second translation sentence based on the second modification analysis result candidate selected.

7. The communication support apparatus according to claim 3,

wherein the source language analyzer anaphorically analyzes the first source language sentence to output at least one first anaphorical analysis result candidate as the at least one first analysis result candidate, and anaphorically analyzes the second source language sentence to output at least one second anaphorical analysis result candidate as the at least one second analysis result candidate,

when the determining unit determines that the second source language sentence is similar to the first source language sentence, the language converter selects one of the at least one first anaphorical analysis result candidate, selects one of the at least second anaphorical analysis result candidate different from the one of the at least one first anaphorical analysis result candidate, translates the first source language sentence into the first translation sentence based on the first anaphorical analysis result candidate selected, and translates the second source language sentence into the second translation sentence based on the second anaphorical analysis result candidate selected.

8. The communication support apparatus according to claim 3,

wherein the source language analyzer analyzes an ellipsis resolution of the first source language sentence to output at least one first ellipsis analysis result candidate as the at least one first analysis result candidate, and analyzes an ellipsis resolution of the second source language sentence to output at least one second ellipsis analysis result candidate as the at least one second analysis result candidate,

when the determining unit determines that the second source language sentence is similar to the first source language sentence, the language converter selects one of the at least one first ellipsis analysis result candidate, selects one of the at least second ellipsis analysis result candidate different from the one of the at least one first ellipsis analysis result candidate, translates the first source language sentence into the first translation sentence based on the first ellipsis analysis result candidate selected, and translates the second source language sentence into the second translation sentence based on the second ellipsis analysis result candidate selected.

9. The communication support apparatus according to claim 3,

wherein the source language analyzer analyzes a communicative intention of the first source language sentence to output at least one first communicative intention analysis result candidate as the at least one first analysis result candidate, and analyzes a communicative intention of the second source language sentence to output at least one second communicative intention analysis result candidate as the at least one second analysis result candidate,

when the determining unit determines that the second source language sentence is similar to the first source language sentence, the language converter selects one of the at least one first communicative intention analysis result candidate, selects one of the at least second communicative intention analysis result candidate different from the one of the at least one first communicative intention analysis result candidate, translates the first source language sentence into the first translation sentence based on the first communicative intention analysis result candidate selected, and translates the second source language sentence into the second translation sentence based on the second communicative intention analysis result candidate selected.

10. The communication support apparatus according to claim 1, wherein the instructions further programmatically define:

a source language analyzer that analyzes a meaning of the first source language to output at least one first analysis result, and analyzes a meaning of the second source language to output at least one second analysis result,

wherein when the determining unit determines that the second source language sentence is similar to the first source language sentence, the language converter outputs at least one first translation word candidate indicating the same meaning as the first source language sentence based on the first analysis result, outputs at least one second translation word candidate indicating the same meaning as the second source language sentence based on the second analysis result, selects one of the at least first translation word candidate, selects one of the at least second translation word candidate different from the one of the at least one first translation word candidate, translates the first source language sentence into the first translation sentence based on the first translation word candidate selected, and translates the second source language sentence into the second translation sentence based on the second translation word candidate selected.

11. The communication support apparatus according to claim 1,

wherein when the determining unit determines that the second source language sentence is similar to the first source language sentence, the language converter selects a first translation direction of the first source language sentence, selects a second translation direction of the second source language sentence different from the first translation direction, translates the first source language sentence into the first translation sentence based on the first translation direction, and translates the second source language sentence into the second translation sentence based on the second translation direction.

12. A communication support apparatus comprising:

a processing system comprising at least one processor; and

a memory comprising one or more tangible computer-readable media containing instructions for execution by the processing system, wherein the instructions, when executed by the processing system, programmatically define;

a speech recognizer that recognizes a first speech of a source language as a first source language sentence, and recognizes a second speech of the source language following the first speech as a second source language sentence;

a determining unit that determines whether the second source language sentence is similar to the first source language sentence;

a language converter that translates the first source language sentence into a first translation sentence, and translates the second source language sentence into a second translation sentence; and

a speech synthesizer that synthesizes the first translation sentence into a third speech in accordance with a first phonation type, and synthesizes the second translation sentence into a fourth speech in accordance with a second phonation type different from the first phonation type when the determining unit determines that the second source language sentence is similar to the first source language sentence.

13. A communication support method comprising:

recognizing a first speech of a source language as a first source language sentence;

translating the first source language sentence into a first translation sentence;

recognizing a second speech of the source language following the first speech as a second source language sentence;

determining whether the second source language sentence is similar to the first source language sentence; and

translating the second source language sentence into a second translation sentence different from the first translation sentence when it is determined that the second source language sentence is similar to the first source language sentence.

14. A communication support method comprising:

recognizing a first speech of a source language as a first source language sentence;

translating the first source language sentence into a first translation sentence;

recognizing a second speech of the source language following the first speech as a second source language sentence;

determining whether the second source language sentence is similar to the first source language sentence;

translating the second source language sentence into a second translation sentence; and

synthesizing the first translation sentence into a third speech in accordance with a first phonation type, and synthesizing the second translation sentence into a fourth speech in accordance with a second phonation type different from the first phonation type when it is determined that the second source language sentence is similar to the first source language sentence.

15. A computer program product having a non-transitory computer readable medium including programmed instructions for supporting a communication, wherein the instructions, when executed by a computer, cause the computer to perform:

recognizing a first speech of a source language as a first source language sentence;

translating the first source language sentence into a first translation sentence; and

recognizing a second speech of the source language following the first speech as a second source language sentence;

determining whether the second source language sentence is similar to the first source language sentence;

translating the second source language sentence into a second translation sentence different from the first translation sentence when it is determined that the second source language sentence is similar to the first source language sentence.

16. A computer program product having a non-transitory computer readable medium including programmed instructions for supporting a communication, wherein the instructions, when executed by a computer, cause the computer to perform:

recognizing a first speech of a source language as a first source language sentence;

translating the first source language sentence into a first translation sentence;

recognizing a second speech of the source language following the first speech as a second source language sentence;

determining whether the second language sentence is similar to the first language sentence;

translating the second source language sentence into a second translation sentence; and

synthesizing the first translation sentence into a third speech in accordance with a first phonation type, and synthesizing the second translation sentence into a fourth speech in accordance with a second phonation type different from the first phonation type when it is determined that the second source language sentence is similar to the first source language sentence.