TAUS Tokyo Summit: improvements in neural machine translation in Japanese are real

Not that business plans are written in stone any longer, but efforts to provide an insight by experts are always welcome. TAUS Tokyo Summit provided a much awaited for set of good news about perceived human translation improvements in neural machine translation in Japanese. English-Japanese was a well-known difficult language pair for rule-based machine translation and statistical machine translation provided a really awful experience for many Japanese audiences. It has historically been one of the hardest language combinations to automate. It seems that neural machine translation may be the answer. Day 1 – Where is the translation industry heading? Jaap began by summarizing the latest meeting of thought leaders in Amsterdam who met in Amsterdam in order to brainstorm a potential landscape and priorities for the language industry in the five years. If machine translation hype was at its peak five years ago with statistical machine translation and all sort […]

5 tips to translate a website in many languages and embed it in your business strategy

by Manuel Herranz Large enterprises and even SME’s around the world are realizing how important it is to translate a webpage in many languages. 1. A free website translator isn’t simply enough. It may do the job fairly well if you just need to understand a website in another language, but that kind of automatic translation is not good enough when you are looking to attract customers. 2. Free website translations published as good content send the wrong message to your potential audience. Google can be quoted as the best example. The search giant is very aware that it is the search engine of choice used around the world and it needs to be available to everyone. Since there are still billions of people who can’t read English or understand it, Google provides the option of translating websites and search results into the language they are familiar with – but […]

Machine translation: Can it be used to translate travel industry content?

by Manuel Herranz There have been strong opinions for and against machine Translation over the last few years. Whilst the general public has become a keen user of free online services, professional translators have poured bitter criticisms against the technology. Understandably, because the language industry is a small industry compared with other sectors where automation took place years ago (automotive industry, printing, telecommunications, to name a few). The Internet and in general any industry based on electronic communications has added to the increase in demand for multilingual websites, which means more translation for eCommerce sites and website translations. There are many supporters of machine translation technology because of the many advantages and problems it has solved where a translator could not be at hand and human translation was not an option. See the video celebrating Google Translate’s 10 years. But it has also gained something of a bad press, particularly […]

Google Translate error from vegetable to clitoris

Thanks to Google Translate error Spanish town calls for clitoris festival

Google Translate error mistranslates Galician vegetable food festival and makes town the world’s laughing stock There are 11,000 inhabitants in Spain’s town of As Pontes, Galicia. This is the rainy, Atlantic North West. Portuguese language and Portugal herself broke away in the Middle Ages as a separate country, but Galician and what later become Portuguese are closely related languages. So close, it seems, that Google Translate was having a hard time telling them apart. And due to the naivety of some town officials, what was meant to be a culinary festival celebrating the local grelo, became the world’s joke. The leafy green vegetable similar to broccoli but without the large head, also popular in Italian cuisine, was mistranslated for a Portuguese slang word. However, this small town has become rather famous because it has been marketing a very different kind of festival for the last few months. A Google Translate error […]

Multilingual web is more than translation (1/2)

by Manuel Herranz It is beyond doubt that the web has become a multilingual. The work, experiences and cross-pollination with other disciplines, from machine translation to localization and semantics, were shared at EU-sponsored Multilingual Web event which took place in Rome during 12-13th March 2013. Whilst technologies such as machine translation are already well-integrated for fast web page translation, it was reassuring to see that even large web actors, such as Google consider there is plenty of work to do in making the web truly multilingual. The release of ITS 2 and the new features and possibilities that html5 opens made the venue a meeting point for professionals, practitioners and academics dealing with the semantic web, translation, applied machine translation and CMS tool providers. Google’s experiences were shared by Mark Davis and Vladimir Weinstein and pinpointed translation and localization issues which are often overseen. We already assume that a page can […]

Minority languages also make it to Google’s Statistical MT

by Manuel Herranz Google has just added five new languages to its machine translation platform: Azerbaijani, Armenian, Basque, Urdu and Georgian. You can find the five of them on Google Translate. These new languages bringing the total number of languages on Google Translate to 57. These languages are still in alpha status, though. The translations maybe less fluent than other languages as Google has gathered less data to feed its statistical machine translation system, but they should still help you understand the multilingual web. “Good working languages” are those for which Google could find a lot of bilingual, aligned data. These included initially the 6 languages of the United Nations (English, French, Spanish, Chinese and Russian) because the UN had released large sets of parallel corpora which contained sentences aligned from one language to another. Google also used parallel corpora from the European Union and other institutions which had released large amounts […]

Google’s image-to-text translation in Barcelona

by Manuel Herranz Something is moving in the convergence of handheld devices with integrated, on-demand technology. Social networking on the mobile phone has soon been transferred and Facebook, Twitter as well as other cool apps are almost omnipresent even in medium range mobile sets. After all, transferring a 21st century technology (social networking) to a 20th century invention (mobile phone), may present some technical difficulties, but as long as we are dealing with digital technologies, someone will find a way. Language, however, is a different matter. Some bilingual apps for mobile phones have been available for some months (such as the impressive Sakhr’s Arabic app for the iPhone with speech recognition  or Jibbigo’s English-Spanish. Some are based on the old dictionary idea. Other, such as Toshiba’s (we reported in December 2009) want to integrate translation real time. Now, Google is also having a go at it. At this week’s Mobile World Exhibition […]

Translation guys should not miss Google’s predictions

by Manuel Herranz This will not be a long article or comment, as the source speaks for itself. There is very interesting food for thought in the line of this month’s Pangeanic’s blog posts. The article is a 3-page conversation with Senior Exec Alan Eustace on Innovation Strategy and the Technology. You need to read all 3 pages (slowly and digest them) in order to get the full picture. I quote the most interesting bit for translation professionals (there are more interesting quotes) “Machine translation will become ubiquitous and as good as human translation, so the language barrier will be gone. All mobile devices will have speech input. Having all local information—maps, directions, and so forth—will be commonplace.” Now, how’s that for clarity and committed statements? What are the implications for translation companies and the whole of the Translation Memory-dependent industry? (If you need the source, it is page 3 following […]

Google Adds Translation on Spreadsheets

Google Spreadsheets got clever new feature this week: support for language translation. Google Spreadsheets has added support for the Google AJAX Language API, according to Google Operating System . With this addition, you can enter any text in English, and then translate it using any of approximately 50 languages supported by Google Translate. Translations are updated every time you add anything to the document and re-publish it. Alternatively, you can also set it to re-publish automatically every time you change anything in the spreadsheet. A further option is that this gadget can be embedded into any webpage, providing your readers the ability to translate your text into the language of their choice. Using Google’s free tools, however, carries a small cost. Any data that is sent over to the online tools can be used by Google for its own statistical purposes. Google can make use of the data you provide – from translation to […]