Pre-defined Term Translator for Accurate Document Translation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Document translation often results in improper meanings due to multiple meanings of terms in the source language being misinterpreted in the target language, and some words lacking direct translations, leading to cumbersome phrases.

Innovation Solution

A computer-implemented method and system that prioritize the use of pre-defined term translators and glossaries over machine translation, ensuring accurate translation by maintaining specific terms and phrases in the source language, particularly for trade names, within a networked translation environment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If machine translation is used to translate text from source language to target language, then translation speed and productivity are improved, but translation accuracy and proper meaning preservation deteriorate

Engineering Contradiction:

Improvetranslation speedVSAvoidtranslation accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The translation process is segmented into multiple stages: first applying pre-defined term translators and glossaries to translate specific terms, then applying machine translation to the remaining text. This segmentation allows the system to maintain accuracy for critical terms while preserving overall translation speed.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary translation of specific terms using pre-defined term translators and glossaries before applying machine translation to the rest of the text. This preliminary action ensures that important terms are translated accurately before the general machine translation process, preventing accuracy deterioration.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If pre-defined term translators and glossaries are applied to translate specific terms, then translation accuracy and proper meaning preservation are improved, but translation time and processing complexity increase

Engineering Contradiction:

Improvetranslation accuracyVSAvoidtranslation time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system applies different translation qualities to different parts of the text: pre-defined term translators and glossaries are applied locally to specific terms that require accurate translation, while machine translation is applied to the remaining text. This local quality approach ensures accuracy where needed without unnecessarily increasing overall translation time.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system applies pre-defined term translators and glossaries partially only to specific terms that require them, rather than applying them to all text. This partial action reduces unnecessary processing time while maintaining accuracy for critical terms.

Inventive Principle:

Principle #16Partial or excessive action

3Productivity

If all terms are translated using machine translation, then translation simplicity and processing speed are improved, but term fidelity and proper terminology preservation deteriorate

Engineering Contradiction:

Improveprocessing speedVSAvoidterm fidelity

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system introduces pre-defined term translators and glossaries as intermediary components between the source text and machine translation. These intermediaries ensure that specific terms maintain their fidelity and proper terminology before the machine translation process, preventing term fidelity deterioration.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS9116886B2Document translation including pre-defined term translator and translation model

Publication Date: 2015.08.25 GOOGLE LLC

AI summary

A computer-implemented method includes receiving, at a translation server in communication with a network, a request for a translation of text in a source language to a target language. At least a portion of the text is translated at the translation server from the source language to the target language to obtain a translated version of the text in the target language. Translating the text includes determining one or more terms from the text corresponding to a pre-defined term translator, applying the pre-defined term translator to the one or more terms, and translating a set of additional terms from the text from the source language to the target language via a translation model. The method additionally includes providing, via the translation server, the translated version of the text to a web server.