Pre-rendering Localization Syntax for Translation Quality

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current content management systems (CMS) and translation management systems (TMS) face inefficiencies when used together, particularly in leveraging content dimensions for language translation, pre-rendering content to remove localization-related syntax, scoring content for localizability, and refining translations continuously.

Innovation Solution

Implementing a system that allows content dimensions to be associated with content items in a CMS, pre-renders content to remove localization-specific syntax, scores content for localizability before translation, and continuously refines translations using automated delivery mechanisms within a TMS.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If content items with localization-specific syntax are translated directly, then translation coverage is maintained, but translation quality deteriorates due to syntax interference

Engineering Contradiction:
Improvetranslation qualityVSAvoidlocalization syntax
Core Design Contradiction:
Manufacturing precisionVSLoss of information

Solution Approach 1:

The system segments the content item into two distinct parts: localization-specific syntax elements and translatable text content. By separating these components, the system can process each independently - preserving the syntax structure while translating only the textual content, thereby eliminating syntax interference from the translation process while maintaining complete translation coverage.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system extracts localization-specific syntax elements from the content item before translation. By removing these potentially interfering elements temporarily, the translation engine can focus solely on translating the text content without being confused by syntax markers, then the extracted syntax is reapplied to the translated output.

Inventive Principle:
Principle #2Taking out (Extraction)

2Manufacturing precision

If pre-rendering is performed to remove localization syntax, then translation quality improves, but computational resources increase

Engineering Contradiction:
Improvetranslation qualityVSAvoidcomputational resources
Core Design Contradiction:
Manufacturing precisionVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary action by pre-rendering content items to remove localization syntax before they are submitted for translation. This upfront processing prepares the content in an optimal state for translation, eliminating the need for complex syntax handling during the translation process itself, thereby improving translation quality while the computational cost is paid only once during pre-rendering.

Inventive Principle:
Principle #10Preliminary action

3Productivity

If content dimensions are associated with content items, then translation efficiency improves, but system complexity increases

Engineering Contradiction:
Improvetranslation efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system introduces content dimensions as an additional organizational layer beyond traditional content structure. By adding this dimensional attribute that captures contextual information about the content item, the system enables more intelligent translation routing and processing decisions, improving translation efficiency through better contextual matching while organizing complexity in a structured, manageable way.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS10223356B1Abstraction of syntax in localization through pre-rendering
Publication Date: 2019.03.05 AMAZON TECH INC
  • US10223356B1 patent drawing
  • US10223356B1 patent drawing
  • US10223356B1 patent drawing

AI summary

A content management system (CMS) and a translation management system (TMS) can utilize content dimensions for content items to manage and translate the content items between languages. Machine and human translations of complex dynamic content can also be improved by pre-rendering the content to remove localization-related syntax prior to machine or human translation. Content items can also be scored as to their suitability for localization prior to translation, and translation can be skipped for content items that do not have a sufficiently high score. Semantic and natural language processing (NLP) techniques can also be utilized for content categorization and routing. Translations of content items can also be continuously refined and higher quality re-translated content can be provided in an automated fashion.