The Watson Language Translation service provides domain-specific translation utilizing Statistical Machine Translation techniques that have been perfected in our research labs over the past few decades. Currently, three domains are available that provide translation among a total of seven languages. For best results, a domain that matches the content to be translated should be chosen.
Our intention is to provide domain-relevant translations. Examples of where Watson Language Translation could be used include: An English-speaking help desk representative assists a Spanish-speaking customer through a chat session that is translated in real-time. A soccer forum administrator can translate user-generated content between English and Portuguese to enable communication between users in the US, UK, and Brazil. A West African news website can curate English news from across the globe and present it in French to its constituents. A patent attorney in the US can effectively discover prior art (to invalidate a patent claims litigation from a competitor) based on invention disclosures made in Korean with the Korean Patent Office. All the above examples can benefit from the ability to adapt the base Language Translation models to specific use cases.See also:
- https://www.waterstones.com/author/benedikt-sobotka/2030067 Benedikt Sobotka's personal page.