Machine translation system, method and program

• US 20060116866A1
• Filed: 11/01/2005
• Published: 06/01/2006
• Est. Priority Date: 11/02/2004
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Digital Solutions Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Kumano, Akira, Suzuki, Hirokazu
• Granted Patent: US 7,979,265 B2
• Time in Patent Office: Days
• US Class Current: 704/2
• CPC Class Codes: G06F 40/55 Rule-based translation

Abstract

Machine translation system includes storage unit configured to store interpretation data items each including first expression element representing first expression of first language, word set element including first expression, and second expression element representing second expression of second language, first expression being to be translated into second expression, first expression and second expression belonging to category, acquiring unit configured to acquire predetermined expression of first language, predetermined expression being contained in to-be-translated text having structure, detecting unit configured to detect, from interpretation data items, interpretation data items each including expression element representing predetermined expression, selection unit configured to select, from detected interpretation data items, interpretation data item including word set element corresponding to same attribute or equivalent positional relationship in structure, and translation unit configured to translate predetermined expression into second language, using selected interpretation data item.

Claims

1. A machine translation system comprising:

a storage unit configured to store a plurality of interpretation data items each including a first expression element representing a first expression of a first language, a word set element including the first expression, and a second expression element representing a second expression of a second language, the first expression being to be translated into the second expression, the first expression and the second expression belonging to a category;

an acquiring unit configured to acquire a predetermined expression of the first language, the predetermined expression being contained in a to-be-translated text having a structure;

a detecting unit configured to detect, from the interpretation data items, a plurality of interpretation data items each including an expression element representing the predetermined expression;

a selection unit configured to select, from the detected interpretation data items, an interpretation data item including a word set element corresponding to a same attribute or an equivalent positional relationship in the structure; and

a translation unit configured to translate the predetermined expression into the second language, using the selected interpretation data item.

2. The system according to claim 1, wherein:

the storage unit contains, as all or several of the interpretation data items, a condition used to select the interpretation data item including the word set element corresponding to a same attribute or an equivalent positional relationship in the structure; and

the selection unit select the interpretation data item including the word set element corresponding to a same attribute or an equivalent positional relationship in the structure, if the detected interpretation data items contain the condition and the expression element representing the predetermined expression satisfies the condition.

3. The system according to claim 1, wherein the word set element has a table structure, and a plurality of expressions in the word set element are arranged in rows and columns.

4. The system according to claim 1, wherein the word set element has an enumerated structure, and a plurality of expressions in the word set element are enumerated expressions.

5. The system according to claim 1, wherein the word set element has a chapter/section structure, and a plurality of expressions in the word set element are titles of chapters and titles of sections.

6. The system according to claim 1, wherein the stored interpretation data items contains expressions of the second language corresponding to expressions of the first language, and articles.

7. The system according to claim 2, wherein the condition concerns at least one of a condition used to determine that number of expressions is identical between the word set element and each of word set elements included in the detected interpretation data items and a condition used to determine that order of expressions is identical between the word set element and the each of word set elements included in the detected interpretation data items.

8. A machine translation method comprising:

preparing a storage unit configured to store a plurality of interpretation data items each including a first expression element representing a first expression of a first language, a word set element including the first expression, and a second expression element representing a second expression of a second language, the first expression being to be translated into the second expression, the first expression and the second expression belonging to a category;

acquiring a predetermined expression of the first language, the predetermined expression being contained in a to-be-translated text having a structure;

detecting, from the interpretation data items, a plurality of interpretation data items each including an expression element representing the predetermined expression;

selecting, from the detected interpretation data items, an interpretation data item including a word set element corresponding to a same attribute or an equivalent positional relationship in the structure; and

translating the predetermined expression into the second language, using the selected interpretation data item.

9. The method according to claim 8, wherein:

the storage unit contains, as all or several of the interpretation data items, a condition used to select the interpretation data item including the word set element corresponding to a same attribute or an equivalent positional relationship in the structure; and

selecting the interpretation data item including the word set element corresponding to a same attribute or an equivalent positional relationship in the structure, if the detected interpretation data items contain the condition and the expression element representing the predetermined expression satisfies the condition.

10. The method according to claim 8, wherein the word set element has a table structure, and a plurality of expressions in the word set element are arranged in rows and columns.

11. The method according to claim 8, wherein the word set element has an enumerated structure, and a plurality of expressions in the word set element are enumerated expressions.

12. The method according to claim 8, wherein the word set element has a chapter/section structure, and a plurality of expressions in the word set element are titles of chapters and titles of sections.

13. The method according to claim 8, wherein the stored interpretation data items contains expressions of the second language corresponding to expressions of the first language, and articles.

14. The method according to claim 9, wherein the condition concerns at least one of a condition used to determine that number of expressions is identical between the word set element and each of word set elements included in the detected interpretation data items and a condition used to determine that order of expressions is identical between the word set element and the each of word set elements included in the detected interpretation data items.

15. A program stored in a computer readable recording medium, comprising:

means for instructing a computer to access a storage unit configured to store a plurality of interpretation data items each including a first expression element representing a first expression of a first language, a word set element including the first expression, and a second expression element representing a second expression of a second language, the first expression being to be translated into the second expression, the first expression and the second expression belonging to a category;

means for instructing the computer to acquire a predetermined expression of the first language, the predetermined expression being contained in a to-be-translated text having a structure;

means for instructing the computer to detect, from the interpretation data items, a plurality of interpretation data items each including an expression element representing the predetermined expression;

means for instructing the computer to select, from the detected interpretation data items, an interpretation data item including a word set element corresponding to a same attribute or an equivalent positional relationship in the structure; and

means for instructing the computer to translate the predetermined expression into the second language, using the selected interpretation data item.

16. The program according to claim 15, wherein:

the storage unit contains, as all or several of the interpretation data items, a condition used to select the interpretation data item including the word set element corresponding to a same attribute or an equivalent positional relationship in the structure; and

the selection unit select the interpretation data item including the word set element corresponding to a same attribute or an equivalent positional relationship in the structure, if the detected interpretation data items contain the condition and the expression element representing the predetermined expression satisfies the condition.

17. The program according to claim 15, wherein the word set element has a table structure, and a plurality of expressions in the word set element are arranged in rows and columns.

18. The program according to claim 15, wherein the word set element has an enumerated structure, and a plurality of expressions in the word set element are enumerated expressions.

19. The program according to claim 15, wherein the word set element has a chapter/section structure, and a plurality of expressions in the word set element are titles of chapters and titles of sections.

20. The program according to claim 15, wherein the stored interpretation data items contains expressions of the second language corresponding to expressions of the first language, and articles.

21. The program according to claim 16, wherein the condition concerns at least one of a condition used to determine that number of expressions is identical between the word set element and each of word set elements included in the detected interpretation data items and a condition used to determine that order of expressions is identical between the word set element and the each of word set elements included in the detected interpretation data items.