A new multilingual search tool developed at the University of Washington’s Turing Center makes searching for pictures on the internet a lot easier.
The tool, dubbed ‘PanImages’, which was recently presented at the Machine Translation Summit in Copenhagen, Denmark, allows people to search for images on the Web using hundreds of languages.
Search engines such as Google look for images by detecting the search term in captions and other nearby text. But since the process looks for a string of letters, the results are limited to the seeker’s mother tongue.
PanImages, from the Greek prefix, “pan,” meaning whole or all-inclusive, automatically translates the search term into about 300 other languages, suggests a few that might work and then displays images from Google and the online photo database Flickr.
PanImages promises to help people who speak languages that have a small Web presence.
‘Imagine you are a Zulu speaker looking for a picture of a refrigerator’, said Oren Etzioni, a professor of computer science and engineering at the University of Washington. ‘You type the Zulu word for refrigerator (“ifriji”) into an image search and get two results. The same search using PanImages generates 472,000 hits.’
In a test of so-called minor languages, PanImages was able to find 57 times more results, on average, than a Google image search.
A Google image search for the Zulu word “ifriji” yields only two results.
A search for the Zulu word “ifriji” using PanImages that selects matches in Japanese and Russian generates 472,000 images.
‘We want to serve the vast number of people who don’t speak one of the major languages,’ added Prof Etzioni. ‘As the internet becomes more widely available outside of the major industrialised nations, it becomes increasingly important to serve people who don’t speak English, French or Chinese.’
‘Our goal is to promote pan-lingual translation,’ said Prof Etzioni. ‘With this first step, we’ve created a service we hope will be a handy tool.’