contact us | support Technology to Bridge the Language Gap
Products
| TransSphere OCR |
 |
 |
 |
|
|
Fully Integrated Arabic, Farsi, Pashtu Optical Character Recognition (OCR) and Machine Translation Apptek has partnered with NovoDynamics to produce an integrated solution powered by NovoDynamics’ Optical Character Recognition (OCR) engine and AppTek’s Machine Translation (MT) engine to transform hard-copy documents into electronic text and seamlessly translate that text into English. Languages covered by the OCR include Arabic, Persian/Farsi/Dari, and Pashto. Translators don’t always receive electronic documents to work with; what happens when translators receive paper documents in languages they don’t know? Typing the material is very time-consuming and extremely expensive. Introducing TranSphere OCR, an integrated solution offering OCR technology from NovoDynamics® and Machine Translation capability from AppTek. NovoDynamics offers a unique combination of technology breadth and depth, a strong customer-focused culture, and established business relationships with major companies. NovoDynamics’ key scientists have two decades’ experience in multiple end-use domains and have worked as a team for more than 15 years. They have worked with conventional and unconventional analytical techniques across the entire informatics spectrum and have adapted these techniques to build effective software solutions that fit specific customer’s objectives. The discovery informatics “tool box” employed by NovoDynamics’ scientists covers a broad range of software tools for data mining, image analysis, and pattern recognition, as well as many enabling tools for data management, storage, and accessibility. This combination of technological skills and application experience enables NovoDynamics to meet the challenges of extracting value from the most difficult data and documents. This applies to data that, because of their size, complexity, “noise,” and existence in disparate databases and legacy systems, represent serious issues of accessibility and utility to users. This also applies to documents that are difficult to “read and mine” by conventional OCR technology because they are in difficult-to-handle languages and are of low visual quality. AppTek Machine Translation uses computer software to translate text from one natural language into another. This definition accounts for the grammatical structure of each language and uses rules and assumptions to transfer the grammatical structure of the source language (text to be translated) into the target language (translated text). TranSphere® was developed after several years of extensive linguistic research in the United States, Europe, Asia, and the Middle East. Its technology reaches beyond simple rudimentary translations, which have been close to mere word replacement. Instead, TranSphere® serves real-life, high-volume, industrial and commercial applications. TranSphere’s® state-of-the-art computational linguistic technology supports the following available languages to and from English:
There are two components for the MT system: an engine that processes the translation, and an environment that allows a user to submit text for translation, receive the results, and manipulate the text before and after the translation. This environment is compatible with a stand-alone MT workstation, client-server architecture, and Web-based solutions. TranSphere® also supports MS Office, MS IE, and includes an API for third party integration. The client-server solution provides greater flexibility than a stand-alone workstation. The client environment can be ported to multiple platforms without impacting the server application. This provides the capability to tailor the user environment to a particular platform, using all of the commercially available products and tools inherent to that platform. Servers can be Windows NT, UNIX, SUN, SCO, LINUX, etc. Since an MT engine is both CPU and memory intensive, the selection of a hardware platform should focus on disk, memory, CPU performance; expandability; commercial availability; and in-country support. The platform should also have the capability to support multiple processors to provide increased performance. Requirements for the client platform are much less stringent. Any standard desktop platform that supports a Windows environment is suitable.
|
