Machine Translation, HTML and Openness of the Web

Hi, folks,

Recent progress on neural machine translation gives us better translation
result, and the industry invests a vast amount of money in this area for a
promising future - the first time our human can communicate with only small
language obstacles. But does the web technology prepared very well for this
trend?

I think we need another level of i18n standards for a better content
translation. And this is crucial for the openness of the Web in next ten
years. People from different nations and cultures can read articles written
in different languages very quickly, it will improve the mutual
understanding of each part, especially in a very uncertain future of our
humankind nowadays.

This is not only an idea but a fact happening in China. We, a small
startup, Colorful-Clouds Tech.,  in Beijing delivered a translation tool
can translate any English webpage into Chinese with very high translation
quality.

Except for the high translation quality, the translation tool also offers a
creative way of re-arranging the HTML elements in any English webpage to
merge the text and translation.
You can add a browser plugin from page https://caiyunapp.com/#xiaoyi-web to
have a try, just drag and bookmark the 'star' on the page in your browser,
you can translate any English webpage into Chinese.

I don't want this email to be a promotional one, but want to elaborate more
technological issues behind. The browser plugin is just a javascript to
manipulate the DOM; it can work very well. But this is not a perfect
solution.

I think, in the very near future, the ability of machine translation will
be a standard infrastructure of the internet, we need gives related
standards to make this into reality, which including:
- the interaction between web pages, browsers and translation service
providers
- the way to author web pages, maybe new attributes will be introduced
- the way to show a web page with translation, for example, the way Google
translation take, or the way our tool take

In the end of this email, I only want to emphasize it is an important
direction in the near future because it can expand the total quantity of
web pages globally just by multiplying the total number of languages,
towards a more peaceful world.

Regards,
Mingli

Received on Sunday, 17 December 2017 17:04:26 UTC