WIPO’s New Tool: Complex Patents Now Easily Translated

By Alexandra Nightingale for Intellectual Property Watch

The World Intellectual Property Organization has developed a ground-breaking new “artificial intelligence”-based translation tool for patent documents, according to the organisation.

WIPO Translate translates highly technical patent documents into a second language in a style and syntax that more closely mirrors common usage.

The WIPO press release is here.

The tool uses neural machine translation, an emerging technology, which is based on huge neural network models that “learn” from previously translated sentences. The specificity of neural machine translation, compared to previous “phrase based” statistical methods is that it produces a more natural word order, says the release.

The technology translates Chinese, Japanese and Korean patent documents into English. Patent applications in those languages accounted for some 55 percent of worldwide filings in 2014.

“One of the aims of the patent system is to make technology available… This breakthrough for WIPO Translate means that a vast, and ever-increasing, trove of patent documents will soon be more easily accessible to innovators who search these records for inspiration or technical know-how,” WIPO Director General Francis Gurry said in the release.

WIPO plans to extend the neural machine translation service to French-language patent applications, with other languages to follow.

Alexandra Nightingale is a researcher at Intellectual Property Watch. She completed her Bachelors in Law at the University of Sussex and holds an LLM degree in International Law from the School of Oriental and African Studies in London. During her Masters, she developed a strong interest in Intellectual Property, particularly patents and the aspects relating to global health. Her research interests now also include geographical indications and trademarks.

Image Credits: WIPO