Every day we use different technologies without even knowing how exactly they work. In fact, it's not very easy to understand engines powered by machine learning. The Statsbot team wants to make machine learning clear by telling data stories in this blog. Today, we've decided to explore machine translators and explain how the Google Translate algorithm works. Years ago, it was very time consuming to translate the text from an unknown language.

Geospatial imagery as well as facial recognition and other biometrics are driving the intelligence community's research into artificial intelligence. Other intelligence activities, such as human language translation and event warning and forecasting, also stand to gain from advances being pursued in government, academic and industry research programs funded by the community's research arm. The Intelligence Advanced Research Projects Activity (IARPA) is working toward breakthroughs in artificial intelligence, or AI, through a number of research programs. All these AI programs tap expertise in government, industry or academia. IARPA is one of the biggest financial backers of AI research, states its director, Jason Matheny, and imagery is the biggest growth area for intelligence AI.

Google's latest take on machine translation could make it easier for people to communicate with those speaking a different language, by translating speech directly into text in a language they understand. The team trained its system on hundreds of hours of Spanish audio with corresponding English text. After a learning period, Google's system produced a better-quality English translation of Spanish speech than one that transcribed the speech into written Spanish first. And text translation service Google Translate already uses neural networks on its most popular language pairs, which lets it analyse entire sentences at once to figure out the best written translation.

We are excited to share our recent work on supporting a recurrent neural network (RNN). We did not support RNN models at our open source launch in April. So, over the last several months, we have developed state-of-the-art RNN building blocks to support RNN use cases (machine translation and speech recognition, for example). Using Caffe2, we significantly improved the efficiency and quality of machine translation systems at Facebook. We got an efficiency boost of 2.5x, which allows us to deploy neural machine translation models into production.

"The World is a small place". You may have heard this phrase many times in many places. One pillar that holding the stability and sustainability of this community is communication. The answer to that simple question is "using languages". The linguistic research estimates that there are 5000 to 7000 languages in this world.

Tech giants Google, Microsoft and Facebook are all applying the lessons of machine learning to translation, but a small company called DeepL has outdone them all and raised the bar for the field. Its translation tool is just as quick as the outsized competition, but more accurate and nuanced than any we've tried. I only speak a smattering of French in addition to my passable English, but luckily my colleague Frederic is a man of many tongues. We both agreed that DeepL's translations were generally superior to those from Google Translate and Bing. As Frederic puts it: "Whereas Google Translate often goes for a very literal translation that misses some nuances and idioms (or gets the translation of these idioms dead wrong), DeepL often provides a more natural translation that comes closer to that of a trained translator."

DeepL's networks consistently outperform other translation systems, making ours the world's best translation machine. Try it out for yourself or read on to see a quantitative comparison of our system to others. The gold standard for comparison of machine translation systems is the direct blind test. DeepL Translator, Google Translate, Microsoft Translator, and Facebook are fed 100 sentences to translate. Professional translators are then asked to assess the translations, without knowing which system produced which results.

SQL is about as easy as it gets in the world of programming, and yet its learning curve is still steep enough to prevent many people from interacting with relational databases. Salesforce's AI research team took it upon itself to explore how machine learning might be able to open doors for those without knowledge of SQL. Their recent paper, Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning, builds on sequence to sequence models typically employed in machine translation. A reinforcement learning twist allowed the team to obtain promising results translating natural language database queries into SQL. In practice this means that you could simply ask who the winningest team in college football is and an appropriate database could be automatically queried to tell you that it is in fact the University of Michigan.

We discuss memory models which are based on tensor decompositions using latent representations of entities and events. We show how episodic memory and semantic memory can be realized and discuss how new memory traces can be generated from sensory input: Existing memories are the basis for perception and new memories are generated via perception. We relate our mathematical approach to the hippocam-pal memory indexing theory. We describe the first detailed mathematical models for the complete processing pipeline from sensory input and its semantic decoding, i.e., perception, to the formation of episodic and semantic memories and their declarative semantic decodings. Our main hypothesis is that perception includes an active semantic decoding process, which relies on latent representations of entities and predicates, and that episodic and semantic memories depend on the same decoding process. We contribute to the debate between the leading memory consolidation theories, i.e., the standard consolidation theory (SCT) and the multiple trace theory (MTT). The latter is closely related to the complementary learning systems (CLS) framework. In particular, we show explicitly how episodic memory can teach the neocortex to form a semantic memory, which is a core issue in MTT and CLS.

One central mystery of neural NLP is what neural models know'' about their subject matter. When a neural machine translation system learns to translate from one language to another, does it learn the syntax or semantics of the languages? Can this knowledge be extracted from the system to fill holes in human scientific knowledge? Existing typological databases contain relatively full feature specifications for only a few hundred languages. Exploiting the existance of parallel texts in more than a thousand languages, we build a massive many-to-one NMT system from 1017 languages into English, and use this to predict information missing from typological databases.