Data processing: speech signal processing – linguistics – language – Linguistics – Translation machine
Reexamination Certificate
1999-12-09
2003-03-18
Edouard, Patrick N. (Department: 2644)
Data processing: speech signal processing, linguistics, language
Linguistics
Translation machine
C704S005000
Reexamination Certificate
active
06535842
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention is directed to a system for translating text from a source language, such as English, into a target language, such as French. In operation, the invention creates a database comprised of text fragments in the source language, together with their counterparts in the target language. When presented with untranslated text in the source language, the invention locates the untranslated text in the database, and then retrieves, from the database, corresponding text fragments in the target language. The invention has particular utility in connection with interactive text translation systems; although the invention can be implemented in automatic text translation systems as well.
2. Description of the Related Art
With the globalization of the economy, there has come an increased need for systems which translate text from one language into another language. Currently, there are two different types of translation systems available on the market—interactive systems and automatic systems. Automatic translation systems input text from a first language and translate that text to a second language without any significant user interaction. Such systems are extremely difficult to implement due to differences in language grammar and vocabulary, and are often prone to errors.
More common are the interactive systems. In these systems, a human translator (hereinafter “the translator”) queries a language database for translations of untranslated text. An example of such a system is the Trados™ Translator Workbench. One problem with conventional systems of this type is that they are limited to use with sentences. That is, differences in sentence structures between various languages have caused developers of conventional systems to design databases based on sentence structures. As a result, these systems allow a translator to search for a translation of an entire sentence, but not portions thereof. This is a significant shortcoming of the conventional systems, since it effectively limits their use to sentences which have counterparts in the database, of which, not surprisingly, there are few.
Accordingly, there exists a need for a text translation system which is able to translate text fragments comprised, e.g., of less than an entire sentence, from one language into another language.
SUMMARY OF THE INVENTION
The present invention addresses the foregoing needs by providing a system (e.g., a method, an apparatus, and computer-executable process steps) which builds a database comprised of text fragments in a source language and translations of those text fragments into a target language. This database can then be queried to provide for translations of sentence fragments from the source to the target language. By providing the ability to translate sentence fragments, the invention provides a significant advantage over the prior art. That is, since there is a greater likelihood of sentence fragments being stored in the database, than there is of entire sentences, more text can be translated by the present invention than by the conventional systems described above.
According to one aspect, the present invention is a system that builds a text fragment database for use in translating fragments of text from a source language into a target language. The system first stores a sentence database in memory, the sentence database comprising a plurality of sentence pairs, each sentence pair including a sentence in the source language and a corresponding sentence in the target language. The system then locates corresponding source and target text fragments in corresponding source and target language sentences, respectively, and stores the source text fragment together with the target text fragment in the text fragment database. The text fragment database can then be used to translate text from the source language into the target language. To this end, the system inputs text in the source language, extracts a text fragment from the input text, and locates the extracted text fragment in the text fragment database. The system then retrieves, from the text fragment database, a text fragment in the target language that corresponds to the extracted text fragment, and outputs the retrieved text fragment.
This brief summary has been provided so that the nature of the invention may be understood quickly. A more complete understanding of the invention can be obtained by reference to the following detailed description of the preferred embodiment thereof in connection with the attached drawings.
REFERENCES:
patent: 5535120 (1996-07-01), Chong et al.
patent: 5548508 (1996-08-01), Nagami
patent: 5587902 (1996-12-01), Kugimiya
patent: 5659765 (1997-08-01), Nii
patent: 5724593 (1998-03-01), Hargrave, III et al.
patent: 5826219 (1998-10-01), Kutsumi
patent: 5842159 (1998-11-01), Nakamura et al.
patent: 5848386 (1998-12-01), Motoyama
patent: 5867811 (1999-02-01), O'Donoghue
patent: 6139201 (2000-10-01), Carbonell et al.
patent: 6119077 (2000-12-01), Shinozaki
Harris, B., “Bi-text, a new concept in translation theory”,Language Monthly, XP-000747663, 8-11, 1988.
“Interlinear Bitext”,Language Technology, XP 000747836, 9108, 12-13, 1988.
“Translation Method By Sentence Examples”,IBM Technical Disclosure Bulletin, XP 000049761, 31, 438-439, Oct. 1988.
“Translation-Example Retrieving Method”,IBM Technical Disclosure Bulletin, XP 000023398, 31, 59-61, Aug. 31, 1988.
Roche Emmanuel
Schabes Yves
Choate Hall & Stewart
Edouard Patrick N.
Global Information Research and Technologies LLC
LandOfFree
Automatic bilingual translation memory system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Automatic bilingual translation memory system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Automatic bilingual translation memory system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3045250