System and method for enhancing document translatability
First Claim
1. A teletranslation system for enhancing document translatability, the teletranslation system translating a document from one natural language to another, comprising:
- an aggregate filter having a plurality of sections, each of the sections adapted to process the document, each section having at least one atomic filter, wherein the plurality of sections include a format conversion section, a text improvement section, a word tagging section, and a translation section adapted to translate a portion of the document; and
a machine translation engine for translating the processed document.
6 Assignments
0 Petitions
Accused Products
Abstract
A teletranslation system and method for enhancing document translatability. The teletranslation system translates a document from one natural language to another. The system comprises an aggregate filter having a plurality of sections, each section performing a specific process or processes on the document in a predetermined order, each section having at least one atomic filter, and at least one MT engine for translating the processed document. The aggregate filter comprises a format conversion section, a text improvement section, a word tagging section, and a translation section. The aggregate filter analyzes the document based on a source text, format information, and a target language. The method for enhancing document translatability comprises processing the document by an aggregate filter having a plurality of sections, each of the sections processing the document in a predetermined order, each section having at least one atomic filter, and translating the processed document by a MT engine. The method further comprises changing the format of the document at a format conversion section, modifying the text at a text improvement section, tagging words at a word tagging section, and translating the document at a translation section. The method further comprises preprocessing the document at the atomic filters in a first pass, and post-processing it at the atomic filters in a second pass. The method further comprises the step of gathering specific data on the document at some atomic filters during the preprocessing step of their first pass, and using such specific data during the post-processing step of their second pass.
-
Citations
20 Claims
-
1. A teletranslation system for enhancing document translatability, the teletranslation system translating a document from one natural language to another, comprising:
-
an aggregate filter having a plurality of sections, each of the sections adapted to process the document, each section having at least one atomic filter, wherein the plurality of sections include a format conversion section, a text improvement section, a word tagging section, and a translation section adapted to translate a portion of the document; and
a machine translation engine for translating the processed document. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
source text;
format information; and
target language.
-
-
3. The system as recited in claim 1, the document comprising:
-
a list of words that should not be translated; and
a list of pretranslated words.
-
-
4. The system as recited in claim 1, wherein the aggregate filter comprises one or more aggregate filters.
-
5. The system as recited in claim 1, wherein the aggregate filter comprises one or more load-balancing filters.
-
6. The system as recited in claim 1, wherein the aggregate filter comprises a combination of one or more atomic, aggregate and load-balancing filters.
-
7. The system as recited in claim 1, wherein said at least one atomic filter is a one-pass filter programmed to perform a preprocessing step in a single pass.
-
8. The system as recited in claim 1, wherein said at least one atomic filter is a two-pass filter programmed to perform a preprocessing step and a post-processing step in a first and a second pass, respectively.
-
9. The system as recited in claim 8, wherein specific data is gathered by the two-pass filter during the preprocessing step in the first pass and this specific data is used during the post-processing step in the second pass.
-
10. The system as recited in claim 1, wherein said at least one atomic filter processes the document or a part thereof.
-
11. A method for enhancing document translatability of a teletranslation system translating a document from one natural language to another, comprising the steps of:
-
processing the document by an aggregate filter having of sections, each of the sections processing the document, each section having at least one atomic filter, wherein the plurality of sections include a format conversion section, a text improvement section, a word tagging section, and a translation section; and
translating the processed document by a machine translation engine. - View Dependent Claims (12, 13, 14, 15, 16)
changing the format of the document at the format conversion section;
modifying a portion of the text at the text improvement section;
tagging words at the word tagging section; and
translating the document at the translation section.
-
-
13. The method as recited in claim 11, further comprising the step of preprocessing the document at said at least one atomic filter in a first pass.
-
14. The method as recited in claim 13, further comprising the step of post-processing the document at said at least one atomic filter in a second pass.
-
15. The method as recited in claim 11, further comprising the step of gathering specific data on the document at said at least one atomic filter during a preprocessing step of a first pass of said at least one atomic filter, and using the specific data during a post-processing step of a second pass of said at least one atomic filter.
-
16. The method as recited in claim 11, further comprising the step of processing the document or a part thereof at said at least one atomic filter.
-
17. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform method steps for enhancing document translatability of a teletranslation system translating a document from one natural language to another, the method comprising the steps of:
-
processing the document by an aggregate filter having a plurality of sections, each of the sections processing the document in a predetermined order, each section having at least one atomic filter, wherein the plurality of sections include a format conversion section, a text improvement section, a word tagging section, and a translation section adapted to translate a portion of the document; and
translating the processed document by a machine translation engine. - View Dependent Claims (18, 19, 20)
changing the format of the document at the format conversion section;
modifying text at the text improvement section;
tagging words at the word tagging section; and
translating the document at the translation section.
-
-
19. The program storage device as recited in claim 17, the method for enhancing document translatability further comprising the step of preprocessing the document at said at least one atomic filter in a first pass.
-
20. The program storage device as recited in claim 19, the method for enhancing document translatability further comprising the step of post-processing the document at said at least one atomic filter in a second pass.
Specification