Machine translation system, method and program for translating text having a structure

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, an interpretation word set element including the first expression, and a second expression element representing a second expression of a second language, wherein the first expression is to be translated into the second expression, and the first expression and the second expression are included in a category;

an acquiring unit for acquiring:

a predetermined expression of the first language, the predetermined expression being included in a structure of a to-be-translated document, wherein words or sentences are arranged regularly in the structure, and

a first word set element including the predetermined expression and one or more expressions having equivalent positional relationship to the predetermined expression in the structure;

a detecting unit for:

detecting a subset from the plurality of interpretation data items, each of the subset including an expression element representing the predetermined expression and one or more word set elements, and

performing matching between the first word set element and each of the one or more word set elements of the detected subset based on at least one of a number and an order of expressions of the first word set element;

a selection unit for selecting, from the detected subset, an interpretation data item according to the matching; and

a translation unit for translating 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 plurality of interpretation data items, a condition used to select an interpretation data item including a word set element corresponding to the first word set element; and

the selection unit selects the interpretation data item including the word set element corresponding to the first word set element, if the detected subset contains the condition and the expression element representing the predetermined expression satisfies the condition.

3. The system according to claim 2 , wherein the condition concerns at least one of a first condition and a second condition,

the first condition being used to determine that a number of expressions is identical between the first word set element of the to-be-translated document and each word set element included in the detected subset of the plurality of interpretation data items,

the second condition being used to determine that an order of expressions is identical between the first word set element of the to-be-translated document and each word set element included in the detected subset of the plurality of interpretation data items.

4. The system according to claim 1 , wherein the first word set element contains data representing a table structure of the to-be-translated document, and a plurality of expressions in the first word set element are arranged in rows and columns.

5. The system according to claim 1 , wherein the first word set element contains data representing an enumerated structure of the to-be-translated document, and a plurality of expressions in the first word set element are enumerated expressions.

6. The system according to claim 1 , wherein the first word set element contains data representing a chapter/section structure of the to-be-translated document, and a plurality of expressions in the first word set element are titles of chapters and titles of sections.

7. The system according to claim 1 , wherein the stored plurality of interpretation data items contain expressions of the second language corresponding to expressions of the first language and parts of speech corresponding to the expressions.

8. A machine translation method, implemented using a computer, 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, an interpretation word set element including the first expression, and a second expression element representing a second expression of a second language, wherein the first expression is to be translated into the second expression, and the first expression and the second expression are included in a category;

acquiring, by the computer, a predetermined expression of the first language, the predetermined expression being included in a structure of a to-be-translated document, wherein words or sentences are arranged regularly in the structure;

acquiring, by the computer, a first word set element including the predetermined expression and one or more expressions having equivalent positional relationship to the predetermined expression in the structure;

detecting, by the computer, a subset from the plurality of interpretation data items, each of the subset including an expression element representing the predetermined expression and one or more word set elements;

performing, by the computer, matching between the first word set element and each of the one or more word set elements of the detected subset based on at least one of a number and an order of expressions of the first word set element;

selecting, by the computer, from the detected subset, an interpretation data item according to the matching; and

translating, by the computer, 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 plurality of interpretation data items, a condition used to select an interpretation data item including a word set element corresponding to the first word set element; and

the method further includes selecting the interpretation data item including the word set element corresponding to the first word set element, if the detected subset contains the condition and the expression element representing the predetermined expression satisfies the condition.

10. The method according to claim 9 , wherein the condition concerns at least one of a first condition and a second condition,

the first condition being used to determine that a number of expressions is identical between the first word set element of the to-be-translated document and each word set element included in the detected subset of the plurality of interpretation data items,

the second condition being used to determine that an order of expressions is identical between the first word set element of the to-be-translated document and each word set element included in the detected subset of the plurality of interpretation data items.

11. The method according to claim 8 , wherein the first word set element contains data representing a table structure of the to-be-translated document, and a plurality of expressions in the first word set element are arranged in rows and columns.

12. The method according to claim 8 , wherein the first word set element contains data representing an enumerated structure of the to-be-translated document, and a plurality of expressions in the first word set element are enumerated expressions.

13. The method according to claim 8 , wherein the first word set element contains data representing a chapter/section structure of the to-be-translated document, and a plurality of expressions in the first word set element are titles of chapters and titles of sections.

14. The method according to claim 8 , wherein the stored plurality of interpretation data items contain expressions of the second language corresponding to expressions of the first language and parts of speech corresponding to the expressions.

15. A non-transitory computer-readable medium including computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a method comprising:

storing, in a storage unit, a plurality of interpretation data items each including a first expression element representing a first expression of a first language, an interpretation word set element including the first expression, and a second expression element representing a second expression of a second language, wherein the first expression is to be translated into the second expression, and the first expression and the second expression are included in a category;

acquiring a predetermined expression of the first language, the predetermined expression being included in a structure of a to-be-translated document, wherein words or sentences are arranged regularly in the structure;

acquiring a first word set element including the predetermined expression and one or more expressions having equivalent positional relationship to the predetermined expression in the structure;

detecting a subset from the plurality of interpretation data items, each of the subset including an expression element representing the predetermined expression and one or more word set elements;

performing matching between the first word set element and each of the one or more word set elements of the detected subset based on at least one of a number and an order of expressions of the first word set element;

selecting, from the detected subset, an interpretation data item according to the matching; and

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

16. The non-transitory computer-readable medium according to claim 15 ,

wherein the storage unit contains, as all or several of the plurality of interpretation data items, a condition used to select an interpretation data item including a word set element corresponding to the first word set element, and

the method further includes selecting the interpretation data item including the word set element corresponding to the first word set element, if the detected subset contains the condition and the expression element representing the predetermined expression satisfies the condition.

17. The non-transitory computer-readable medium according to claim 16 , wherein the condition concerns at least one of a first condition and a second condition,

the first condition being used to determine that a number of expressions is identical between the first word set element of the to-be-translated document and each word set element included in the detected subset of the plurality of interpretation data items,

the second condition being used to determine that an order of expressions is identical between the first word set element of the to-be-translated document word set element and each word set element included in the detected subset of the plurality of interpretation data items.

18. The non-transitory computer-readable medium according to claim 15 , wherein the first word set element contains data representing a table structure of the to-be-translated document, and a plurality of expressions in the first word set element are arranged in rows and columns.

19. The non-transitory computer-readable medium according to claim 15 , wherein the first word set element contains data representing an enumerated structure of the to-be-translated document, and a plurality of expressions in the first word set element are enumerated expressions.

20. The non-transitory computer-readable medium according to claim 15 , wherein the first word set element contains data representing a chapter/section structure of the to-be-translated document, and a plurality of expressions in the first word set element are titles of chapters and titles of sections.

21. The non-transitory computer-readable medium according to claim 15 , wherein the stored plurality of interpretation data items contain expressions of the second language corresponding to expressions of the first language and parts of speech corresponding to the expressions.