[Case Study] Achieved a 37% cost reduction and 50% reduction in translation time through optimal engine selection - Office equipment user manual.

This time, we would like to introduce a case where our company conducted consulting for machine translation engine selection.

From the person in charge of handling instruction manuals for a domestic office equipment manufacturer in 2014

・I want to achieve simultaneous release of Japanese, English, and multiple language instruction manuals.

・I want to respond timely to frequent updates of instruction manuals.
Therefore, I want to shorten the time required for translation.

We received a request to introduce machine translation due to the following reasons.

 

——————————————————————————————–

●Project Overview

Translated Item: Office Equipment User Manual
Language: English → French, Italian, German, Spanish, Brazilian Portuguese
Volume: 400,000-500,000 words per year
Corpus available for use with statistical-based engine: Approximately 20,000 sentences

——————————————————————————————–

When implementing machine translation, our customers

It is not clear whether introducing machine translation will actually shorten translation time and reduce costs.

I don't know which engine to choose from dozens of commercially available engines

You had concerns such as

 

Therefore, we have selected three engines that are suitable for our projects and clients' budgets. We compared each engine from the perspectives of quality, return on investment, integration with previously used tools, and whether we can utilize our accumulated translation assets (translation memory data). We have submitted a report.

 

Machine Translation Engine Evaluation Report

 

Based on the verification results, using the engine with the best quality,
the translation cost can be reduced by approximately 37%, and the translation period can be shortened by approximately 50%.

This is the cost reduction and translation period shortening effect while maintaining the quality at the same level as the previous "human translation".

When using the second best quality engine,
the estimated reduction rate of translation costs is approximately 25%.

 

As such, the reduction rate of translation costs varies greatly depending on the machine translation engine selected.

The better the quality of machine translation immediately after translation, the less burden there is for human correction work (post-edit),
which can lead to greater cost savings and shorter translation periods.
Depending on the content and corpus used,
the optimal engine may vary,
so it is recommended to compare the quality of several engines using actual data beforehand.

Human Science provides consulting services for machine translation engine selection from a neutral standpoint without its own engine.
If you can provide us with the target content or corpus, we can also conduct quality evaluations and cost simulations based on the current situation.
Please feel free to contact us.

 

>>Contact Form

If the form is not available, please send your inquiry to hsweb_inquiry@science.co.jp.

Please send it by email.

Alternatively, please feel free to contact us at TEL: 03-5321-3111 or by phone.

 

Blog Writing Team

Tokuda Ai

・As a machine translation consultant, I provide consulting services for Japanese companies on machine translation implementation and process building.
・I place importance on the quality of the source text, which affects multilingual translation, and also provide consulting services for manual creation suitable for machine translation in the Japanese writing process.
・I also give presentations on the following topics related to machine translation.
- Presentation at the 23rd JTF (Japan Translation Federation) Translation Festival in 2013
"Approaches to Machine Translation in Multilingual Environments
- From the Perspectives of Evaluation and Process"
- Presentation at the 2014 AAMT (Asia-Pacific Association for Machine Translation) Machine Translation Fair
"Mastering Machine Translation - Improving Quality and Productivity"