By Ethan Shen, Founder of Gabble On LLC
Throughout my three years of high school Spanish and three years of college Chinese, I used automatic translation sites like Babelfish a lot. It's not because I'm a bad student, it's just that I was simultaneously interested in languages but also too lazy to expend the effort to study them properly.
I knew it was far from perfect, but I justified shamelessly turning it in because my own shitty Spanish probably wouldn't have done any better. I still remember cranking out pages of homework in a matter of minutes with a few clicks. Something for nothing, who could resist? Since those days many new engines have appeared and I assume if Moore's Law also applies to translation, it must have evolved a lot in the last 10 years.
However, one question that's never been answered is: "Which engine translates best?"
Years ago, IBM developed an algorithmic method of measuring MT quality known as the BLEU score. Google scored well here, but the BLEU score is not without its critics. Translation, like writing itself, is as much an art as it is a science.
Which is why translators are best positioned to judge the quality of machine translation engines. And although even translators are going to disagree as well, if you get enough of them together, perhaps you can begin to draw statistically significant conclusions.
In our first open research project, we will compare the three most popular free translation utilities:
- Google Translate
- Microsoft Bing Translator
- Yahoo BabelFish
We are seeking functional to fluent speakers of any two languages to take five minutes to judge and submit their opinion in our dynamic comparison engine (until March 29, 2010). At the end of the voting period, we will be publishing our results publicly in hopes that our research can to contribute meaningfully to the body of knowledge in this field.
In gratitude for your participation, we are awarding one new Apple iPad to a lucky participant. The survey can be found at www.gabble-on.com/SurveySelector.aspx.
Down the road, the Gabble On team envisions future research projects that also include non-free commercial translation engines which will be able to help people make more objective and well-informed decisions when selecting translation solutions. During the second quarter of 2010, we'd also like to use this research as a basis for free web and mobile tools that will help make these technologies more accessible and effective.
I appreciate your votes, and I hope you are as curious and excited about these questions as we are!
Like this post? Subscribe to Medical Translation Insight via email or RSS!
Categories: machine translation