Is Google Translate Good Enough for Commercial Websites? : A Machine Translation evaluation of text from English websites into four different languages
利用統計を見る
This study is a Machine Translation evaluation of output from Google Translate, an online translation service that uses Statistical Machine Translation. The purpose of the study is to ascertain whether Google Translate is able to produce output of sufficiently high quality for use on commercial websites. Twenty sentences from the websites of four different language schools that use the Google Translate powered Google Website Translator plugin were selected. The sentences were translated into French, German, Japanese and Spanish. Native speakers of the languages volunteered to evaluate the translated output using two sets of scales; one for intelligibility and the other for accuracy. It was found that the results for accuracy and intelligibility were similar, with the German output receiving the worst evaluations for both metrics. The Japanese output for both metrics received the second worst evaluations. The Spanish output had the highest evaluation for intelligibility, and received the joint highest evaluation along with French for accuracy. Overall it was found that the majority of the French and Spanish output was of a reasonably high quality, but should still be post-edited before appearing on a website. The German and Japanese output was of lower quality and needed more substantial correcting before being fit for publication on a website.
Is Google Translate Good Enough for Commercial Websites? : A Machine Translation evaluation of text from English websites into four different languages
.png)
94-116 Anthony Tobin
(460.26KB)
