Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Translation Memory Structure and the memory access method that enable the multiple languages' translation (any to any) at the same time

IP.com Disclosure Number: IPCOM000015593D
Original Publication Date: 2002-Jul-01
Included in the Prior Art Database: 2003-Jun-20
Document File: 2 page(s) / 59K

Publishing Venue

IBM

Abstract

Disclosed is a method to translate a sentence (any language) to multiple languages in high quality (human translation level quality) within the reasonable cycle time (1/10 1 second). Huge asset of the translation of English to national languages (Japanese, Chinese, Korean, German, French, Italian, Spanish, and so on) has been produced in the past 5 or 6 years in many international companies or translation companies during their work for the product localization. There is a big opportunity to generate any language to any language translation (for example, Japanese to German) using the huge asset without spending money for translating from Japanese to German. The approach to translate a given sentence into multiple languages consists of (1) the introduction of the new translation memory structure, (2) the use of English sentence as a pivot, and (3) the access method with the compressed key for fast search. The new Translation Memory structure is as follows: One unit of Translation Memory segment (The Translation Memory consists of multiple Translation Memory segments):

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 53% of the total text.

Page 1 of 2

  Translation Memory Structure and the memory access method that enable the multiple languages' translation (any to any) at the same time

   Disclosed is a method to translate a sentence (any language) to multiple languages in high quality (human translation level quality) within the reasonable cycle time (1/10 - 1 second). Huge asset of the translation of English to national languages (Japanese, Chinese, Korean, German, French, Italian, Spanish, and so on) has been produced in the past 5 or 6 years in many international companies or translation companies during their work for the product localization. There is a big opportunity to generate any language to any language translation (for example, Japanese to German) using the huge asset without spending money for translating from Japanese to German.

The approach to translate a given sentence into multiple languages consists of (1) the introduction of the new translation memory structure, (2) the use of English sentence as a pivot, and (3) the access method with the compressed key for fast search.

The new Translation Memory structure is as follows:

One unit of Translation Memory segment (The Translation Memory consists of multiple Translation Memory segments):

+---------------------------------------+

| Meta information in XML format |
|---------------------------------------|

| Source sentence |
|---------------------------------------|

| Target sentence |
+---------------------------------------+

Note: Definition of Trans...