One of the problems a lot of crowdsourcing projects have is that they end up pulling in massive amounts of data from the web, Twitter and other channels from around the world. This means content arrives in many different languages, often languages that the deployer doesn’t speak.
Currently in Sweeper and soon in Ushahidi, users can translate real-time content from one language into another, on the fly, as they receive it. This is done using our Google Translate plugin. Google Translate currently supports 50+ languages.
For the Sweeper deployment we’re using to monitor the situation in Japan internally, we’re using this feature to monitor events, since we can’t manually translate every single message coming through. We’ve found it a significant timesaver. You can also see below that we’re showing the user what language the message was translated from, or if it’s been translated at all…
It’s important to understand, that this is machine translation, so it’s far from perfect. But if you’re monitoring feeds from multiple countries across Twitter, RSS, Email or SMS it’s sometimes useful enough to get a quick sense of what’s being said, where to potentially look for more info, or perhaps where to direct human translators.


3 Responses
Stay in touch with the conversation, subscribe to the RSS feed for comments on this post.
The translator is great – its actually much better then most machine translators I have used in the past. With languages like Japanese such tool is crucial especially when time is of essense. Thank you sharing.
In the above example, the translation should be “temporary shuttle bus between Shin Shirakawa and Sukagawa” not “between temporary and Shirakawa Shin Sukagawa” — the latter could easily be misinterpreted in other ways. If you’re using the translation to direct human translators, then that’s fine, but there is a danger that people will jump on this information and misinterpret it.
This is exactly a situation where I would be wary of MT — it’s not necessarily always the case that “anything is better than nothing”, and cases like this require a lot of caution.
How can we get traction for the minor languages. In the South Pacific none of the languages are in google translate.