Data processing: speech signal processing – linguistics – language – Linguistics – Translation machine
Reexamination Certificate
1999-04-20
2002-01-08
Edouard, Patrick N. (Department: 2744)
Data processing: speech signal processing, linguistics, language
Linguistics
Translation machine
C704S007000
Reexamination Certificate
active
06338033
ABSTRACT:
BACKGROUND OF THE INVENTION
I. Related Applications
This application is related to concurrently filed applications titled, “System and Method for Enhancing Document Translatability” Ser. No. 09/294,028, commonly assigned, and “System and Method for Internet-based Translation Brokerage Services”, Ser. No. 09/294,027 commonly assigned, and incorporates the commonly assigned applications by reference in their entirety for all purposes.
II. Field of the Invention
The present invention relates generally to language translation and, more specifically, to a system and method for network-based teletranslation.
III. Description of the Related Art
Today, as more and more businesses operate across international borders, they are often required to conduct business in more than one language. Also, businesses often encounter a need to translate documents from one natural language to another natural language.
In the past, businesses have utilized human-based translation (HT) to translate documents. Although HT generally produces high quality work, it is labor intensive, inherently slow, and often expensive. Human translators are quite often specialists in a given language pair (e.g., English/French). Hence, there is a limitation on how the human translators can be allocated to different translation tasks, thus resulting in certain rigidity for a business employing the human translators.
Because HT is labor intensive, it is difficult to scale up when need increases and difficult to scale down when need decreases. The capacity of any group of translators is fairly well defined. When a sudden need arises to increase the capacity for a particular language pair, adding additional translators to the process creates various problems, such as harmonizing different styles, sharing glossaries and context information, and merging translated text. Moreover, it can be difficult to hire additional translators when a sudden need arises.
The document to be translated is often submitted to the translators in different formats, for example, computer printouts, faxes, word processing files, e-mail attachments, web pages. The translators are then left to handle the formats and extract translatable contents. While requesters of translation services prefer that the translated document be in the same format as it was originally submitted, this is often not possible, because different translators have varying technical skills and often are unable to reformat the translated document into the original format.
For these reasons, machine translation software programs, also known as machine translation engines, have been developed to provide computerized translations. Today, the term Machine Translation (MT) is widely used in the industry to refer to computerized systems that translate documents from one natural language to another, with or without human assistance. It is important to note that the term MT does not include computer-based tools that support translators by providing access to dictionaries and terminology databases, or tools that facilitate the transmission and reception of machine-readable texts, or tools that interact with word processing, text editing or printing equipment. The term MT does, however, include systems in which translators or other users assist computers in the production of translations, including combinations of text preparation, on-line interactions and subsequent revisions of machine translated documents.
While MT engines appear promising, the technology is often under-used or miss-used. Businesses frequently encounter difficulty in determining the right use of MT and to evaluate the cost/benefit of MT. Businesses require a level of technical expertise to use MT (for example, computer, software and/or system management expertise), which is often not available. Access to various MT functionalities is not integrated with routine translation tasks in a business, making its use irregular at best. Businesses unfamiliar with MT may not be aware that there is not one best MT engine for their particular business, but rather, the suitability of any particular MT engine depends on the application, which often varies even within a given business. Consequently, a business may acquire a MT engine that is sub-optimal for its need.
MT engines often translate documents of only certain types of computer formats. For example, some MT engines accept rich text format (RTF) only, while others accept only ASCII files. As a result, businesses often are forced to turn down translation jobs because their MT engines cannot handle a particular computer format or at best implement a non-trivial way of extracting the text for translation from the format information and reinserting the translated text back into the format information.
MT engines typically have a limited bandwidth, i.e., the amount of text they can translate in a given time period. If a business needs additional machine translation bandwidth, it must buy and setup additional MT engines. However, the ability to dispatch translation jobs to various MT engines and balance the workload among the MT engines is not a trivial task. Failure to balance the workload among various MT engines results in under-performing equipment. More specifically, failure to balance the workload properly among various MT engines considerably slows down the time required to translate a document when compared to the combined output of the separate MT Engines. On the other hand, failure to provide the necessary translation bandwidth to users results in lower productivity.
Even if businesses acquire new MT engines to meet increased demand or the need for new language pairs, the new MT engines are often incompatible with each other. Thus, businesses simply cannot connect a new MT engine to their existing environment. The new MT engines are often not interchangeable with the old MT engines, and often do not work alongside the old MT engines.
For these reasons, it has been recognized that there is a need for a teletranslation system and method that is capable of handling a wide variety of language pairs and computer formats. There is a need for a teletranslation system and method that is compatible with various MT engines, and that uses the computing power of the network in a scalable and flexible way. There is a need for a teletranslation system and method that increases the bandwidth and speed by distributing the workload among several computers in the network in a balanced way.
SUMMARY OF THE INVENTION
The present invention is a network-based teletranslation system and method that translates documents from one natural language to another natural language. In one embodiment, the teletranslation system comprises a client application layer having a plurality of client applications, the client application layer receiving translation documents from one or more software applications and outputting a translated text, a server layer having a plurality of servers, each server having a plurality of filters, the server layer calling a plurality of filters in an appropriate order based on the translation request and existing parameters, each filter preprocessing a translation document to facilitate further preprocessing by subsequent filters, at least one of the filters processing the translation request and returning the translated document, and an intermediate layer coupling the client application layer to the server layer and arbitrating the translation documents among the servers in the server layer, wherein the teletranslation system handles a wide variety of language pairs and formats, and wherein the teletranslation system utilizes the computing power of the network in a scalable and flexible way, and wherein the teletranslation system increases the bandwidth and speed by distributing the translation request among the servers in the network.
In one embodiment, the present invention is a network-based filter architecture embodied in a teletranslation system for translating documents from one natural language to another. The filter architecture comprises one or more atomic filters each
Bourbonnais Jean
Walker Martin
Alis Technologies, Inc.
Bell Michael J.
Edouard Patrick N.
Howrey Simon Arnold & White
LandOfFree
System and method for network-based teletranslation from one... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for network-based teletranslation from one..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for network-based teletranslation from one... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2855406