Using top-ranked documents in response to a query has been shown to be an effective approach to improve the quality of query translation in dictionary-based cross-language information retrieval. In this paper, we propose a new method for dictionary-based query translation based on dimension projection of embedded vectors from the pseudo-relevant documents in the source language to their equivalents in the target language. To this end, first we learn low-dimensional vectors of the words in the pseudo-relevant collections separately and then aim to find a query-dependent transformation matrix between the vectors of translation pairs appeared in the collections. At the next step, representation of each query term is projected to the target language and then, after using a softmax function, a query-dependent translation model is built. Finally, the model is used for query translation. Our experiments on four CLEF collections in French, Spanish, German, and Italian demonstrate that the proposed method outperforms a word embedding baseline based on bilingual shuffling and a further number of competitive baselines. The proposed method reaches up to 87% performance of machine translation (MT) in short queries and considerable improvements in verbose queries.

Google Translate has become a quick-and-dirty translation solution for millions of people worldwide since it debuted a decade ago. But Google's engineers have been quietly tweaking their machine translation service's algorithms behind the scenes. They recently delivered a huge Google Translate upgrade that harnesses the popular artificial intelligence technique known as deep learning. Machine translation services such as Google Translate have mostly used a "phrase-based" approach of breaking down sentences into words and phrases to be independently translated. But several years ago, Google began experimenting with a deep-learning technique, called neural machine translation, that can translate entire sentences without breaking them down into smaller components.

Have you ever been in a situation where knowing another language would have come in handy? I remember standing on the platform at Tokyo Station watching my train to Nagano -- the last train of the day -- pulling away without me on it. What ensued was a frustrating hour of gestures, confused smiles, and head-shaking as I wandered the station looking for someone who spoke English (my Japanese is unfortunately nonexistent). It would have been really helpful to have a bilingual pal along with me to translate. Bilingual pals can be hard to find, but Google's new translation software may be an equally useful alternative.

Google says that with certain languages, its new system -- dubbed Google Neural Machine Translation -- reduces errors by 60 percent. But the company plans to roll it out for the more than 10,000 language pairs now handled by Google Translate.

No one would accuse Google Translate, the favored tool of unscholarly high school language students everywhere, of being an inaccurate interpreter. The 10-year-old internet interpreter can fluently translate more than 100 tongues, recognize foreign restaurant menus and signage, and differentiate between dialects in real time. The project is called Google Neural Machine Translation, or GNMT, and it isn't strictly speaking new. It was first employed to improve the efficiency of single-sentence translations, explained Google engineers Quoc V. Le and Mike Schuster, and did so ingesting individual words and phrases before spitting out a translation. But the team discovered that the algorithm was just as effective at handling entire sentences -- even reducing errors by as much as 60 percent.

No one would accuse Google Translate, the favored tool of unscholarly high school language students everywhere, of being an inaccurate interpreter. The 10-year-old internet interpreter can fluently translate more than 100 tongues, recognize foreign restaurant menus and signage, and differentiate between dialects in real time. The project is called Google Neural Machine Translation, or GNMT, and it isn't strictly speaking new. It was first employed to improve the efficiency of single-sentence translations, explained Google engineers Quoc V. Le and Mike Schuster, and did so ingesting individual words and phrases before spitting out a translation. But the team discovered that the algorithm was just as effective at handling entire sentences -- even reducing errors by as much as 60 percent.

Translating from one language to another is hard, and creating a system that does it automatically is a major challenge, partly because there are just so many words, phrases and rules to deal with. Fortunately, neural networks eat big, complicated data sets for breakfast. Google has been working on a machine learning translation technique for years, and today is its official debut. The Google Neural Machine Translation system, deployed today for Chinese-English queries, is a step up in complexity from existing methods. Here's how things have evolved (in a nutshell). A very simple technique for translating -- one a kid or simple computer could do -- would be to simply look up each word encountered and switch it with the equivalent word in another language.

Welcome back to Across the Network -- Lab41's weekly look at what is going on in the world of AI. As always these are all links that I pulled from the Lab41 Slack channels. A Neural Network for Machine Translation -- I have a 3-year old son, who, thanks to his mother (whose family is from Taiwan) and our Chinese au-pair, speaks Mandarin fluently. And while I'm proud of this fact (and a bit miffed that he is so much more capable at picking up language than me), his fluency has required me to become a regular user of Google Translate. So I was excited to see the details behind the latest technology being used by the Google Translate team.

A jump in the fluency of Google's language software will help efforts to make chatbots less lame. Google's latest advance in machine learning could make the world a little smaller. The company is reëngineering its translation service after Google researchers invented a system that is significantly more accurate. In a competition that pitted the new software against human translators, it came close to matching the fluency of humans for some languages, such as when translating from English to Spanish. Google has already begun rolling out the new system for translations from Chinese to English (see examples showing the improvement).

Facebook CEO and cofounder Mark Zuckerberg at an event at Facebook's Menlo Park, Calif., headquarters to celebrate Facebook Friends Day with users from around the world. SAN FRANCISCO -- Facebook has been translated into three new languages -- and it has its users to thank. Be it "what's on your mind?" or the "like" or "share" buttons, a dedicated community of Facebook users want to make sure all the words and phrases on the social networking service are accurately translated into their native tongues. In all, Facebook is now available in 101 languages with the addition on Friday of Maltese (the official language of Malta that has more than 400,000 native speakers), Pulaar (a dialect of Fula spoken by more than 7 million across West and Central Africa), and Corsican (spoken by some 200,000 people and listed on UNESCO's Atlas of the World's Languages in Danger.) Human-powered translation is critical to Facebook's growth.