Local Translation Cache Using Remote Utility Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional computer-aided translation systems face delays and inconveniences due to the time required to process and transmit translation memories over networks, especially with insufficient bandwidth or storage capacity, preventing timely access to remote translation memories for translators.

Innovation Solution

A method and system for local computer-aided translation using remotely-generated translation predictions, where a remote translation memory determines the utility of a translation for a document portion before a request is made, and transmits this translation along with an identification to a local machine, allowing the local machine to generate subsequent translations through reuse, thereby reducing reliance on network transmission and improving efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If translation memory is stored remotely on a server, then storage capacity is sufficient and multiple translators can access shared translations, but network transmission delays and insufficient bandwidth prevent timely access to translations

Engineering Contradiction:

Improvestorage capacityVSAvoidnetwork transmission delay

Core Design Contradiction:

Quantity of substanceVSLoss of time

Solution Approach 1:

The system performs preliminary actions by determining the utility of translations before a translator actually requests them. The remote translation memory analyzes the source document, identifies segments that are likely to need translation, and pre-processes these segments so that when a translator requests a translation, the system can quickly retrieve and transmit the translated segments without delays

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies local quality by transmitting only the specific translated segments that are useful for the current document to the local machine, rather than transmitting the entire translation memory. This allows the local machine to have quick access to relevant translations while maintaining a lightweight local cache

Inventive Principle:

Principle #3Local quality

2Speed

If translation memory is transmitted to local machine, then access speed improves and translators can work without network dependency, but network bandwidth and storage capacity requirements increase

Engineering Contradiction:

Improvetranslation access speedVSAvoidnetwork bandwidth consumption

Core Design Contradiction:

SpeedVSQuantity of substance

Solution Approach 1:

The system extracts only the necessary translated segments from the remote translation memory and transmits them to the local machine. By identifying and transmitting only the useful translations for the current document rather than the entire translation memory, the system reduces network bandwidth consumption while still providing fast local access to relevant translations

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The translation memory is segmented into individual translated segments that can be selectively transmitted. The system divides the large translation memory into manageable, relevant portions and transmits only those segments that are useful for the current translation task, reducing the overall data transmission requirement

Inventive Principle:

Principle #1Segmentation

3Use of energy by moving object

If conventional translation systems wait for translator requests before processing, then system resources are conserved, but translators experience inconvenience and delays when accessing translations

Engineering Contradiction:

Improvesystem resource consumptionVSAvoidtranslator convenience

Core Design Contradiction:

Use of energy by moving objectVSEase of operation

Solution Approach 1:

The system performs preliminary processing by determining the utility of translations before the translator actually requests them. The remote translation memory proactively analyzes the source document and identifies which translated segments will be useful, preparing these segments in advance so that when the translator requests a translation, the system can quickly provide the translated segments without delays

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback mechanisms where the translation agent on the local machine monitors the translator's work and makes intelligent requests to the remote translation memory based on the current translation context. This feedback loop allows the system to anticipate needs and retrieve translations more efficiently, improving translator convenience while managing resources effectively

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS8374843B2Methods and systems for local, computer-aided translation incorporating translator revisions to remotely-generated translation predictions

Publication Date: 2013.02.12 LIONBRIDGE TECH LLC

AI summary

A method for local, computer-aided translation using remotely-generated translation predictions includes the step of determining that a translation stored in a remote translation memory is useful in translating a first portion of a local document. A local machine receives the translation of the first portion of the document. The local machine stores, in a local cache, an alternate version of the translation created by a translator. The alternate version of the translation is identified as useful in translating a second portion of the document. The local machine generates a translation of the second portion of the document through reuse of the alternate version of the translation of the first portion of the document, responsive to the received identification of the utility of the alternate version of the translation of the first portion of the document to the second portion of the document.