Decades ago, Star Trek introduced the idea of a "universal translator," a small baton that let crew members converse with aliens in their native languages simply by flipping a switch. This app isn't part of the pre-installed loadout on most phones, but it's indispensable when you travel. It's so overflowing with features, in fact, you might not even realize everything it can do. So here are the six most awesome and useful things you can do with Google Translate on your smartphone. You won't always have the best mobile data connection while traveling the world, so it's a good idea to have an offline backup in Translate.

In this paper, we present Neural Phrase-based Machine Translation (NPMT). Our method explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling method. To mitigate the monotonic alignment requirement of SWAN, we introduce a new layer to perform (soft) local reordering of input sequences. Different from existing neural machine translation (NMT) approaches, NPMT does not use attention-based decoding mechanisms. Instead, it directly outputs phrases in a sequential order and can decode in linear time. Our experiments show that NPMT achieves superior performances on IWSLT 2014 German-English/English-German and IWSLT 2015 English-Vietnamese machine translation tasks compared with strong NMT baselines. We also observe that our method produces meaningful phrases in output languages.

Learning meaningful representations that maintain the content necessary for a particular task while filtering away detrimental variations is a problem of great interest in machine learning. In this paper, we tackle the problem of learning representations invariant to a specific factor or trait of data. The representation learning process is formulated as an adversarial minimax game. We analyze the optimal equilibrium of such a game and find that it amounts to maximizing the uncertainty of inferring the detrimental factor given the representation while maximizing the certainty of making task-specific predictions. On three benchmark tasks, namely fair and bias-free classification, language-independent generation, and lighting-independent image classification, we show that the proposed framework induces an invariant representation, and leads to better generalization evidenced by the improved performance.

Out-of-vocabulary word translation is a major problem for the translation of low-resource languages that suffer from a lack of parallel training data. This paper evaluates the contributions of target-language context models towards the translation of OOV words, specifically in those cases where OOV translations are derived from external knowledge sources, such as dictionaries. We develop both neural and non-neural context models and evaluate them within both phrase-based and self-attention based neural machine translation systems. Our results show that neural language models that integrate additional context beyond the current sentence are the most effective in disambiguating possible OOV word translations. We present an efficient second-pass lattice-rescoring method for wide-context neural language models and demonstrate performance improvements over state-of-the-art self-attention based neural MT systems in five out of six low-resource language pairs.

Craig Stern is the Marketing Director for the Americas at Systran Software Inc. a market leader in secure neural machine translation. An SDSU graduate, his feats have included: filing a patent in college, built and launched a machine translation mobile app and a social venture in the eyewear industry. He has in-depth expertise with disruptive technology. In addition, he is a prolific content writer, covering the convergence of neural machine translation, voice-to-text, economics and culture. His content has been published in Forbes, Inc., Entrepreneur and The Next Web, in addition to his articles in Disruptor Daily.

The code has been copied to your clipboard. Some machines can take something written in one language and give users the same or similar wording in another language. These machines are designed to do this kind of work quickly and without mistakes. Some of the devices are so small they can be carried around the world. The quality of translation software programs has greatly improved in recent years, thanks to new, fast-developing technologies.

To understand the potential of these new systems, it helps to know how current machine translation works. The current de facto standard is Google Translate, a system that covers 103 languages from Afrikaans to Zulu, including the top 10 languages in the world–in order, Mandarin, Spanish, English, Hindi, Bengali, Portuguese, Russian, Japanese, German, and Javanese. Google's system uses human-supervised neural networks that compare parallel texts–books and articles that have been previously translated by humans. By comparing extremely large amounts of these parallel texts, Google Translate learns the equivalences between any two given languages, thus acquiring the ability to quickly translate between them. Sometimes the translations are funny or don't really capture the original meaning but, in general, they are functional and, overtime, they're getting better and better.

Deep Learning is being aggressively used in day-to-day tasks. It especially excels in areas where there is a degree of'humanness' involved, e.g. Probably the most useful feature of Deep Networks, unlike other Machine Learning algorithms, is that their performance increases as it gets more data. So if it is possible to get more data, a performance increase can be expected. One of the tasks where deep networks excel is machine translation.

Machine translation (MT) was one of the first applications of artificial intelligence technology that was deployed to solve real-world problems. Since the early 1960s, researchers have been building and utilizing computer systems that can translate from one language to another without requiring extensive human intervention. In the late 1990s, Ford Vehicle Operations began working with Systran Software Inc. to adapt and customize its machine-translation technology in order to translate Ford's vehicle assembly build instructions from English to German, Spanish, Dutch, and Portuguese. The use of machine translation was made necessary by the vast amount of dynamic information that needed to be translated in a timely fashion. The assembly build instructions at Ford contain text written in a controlled language as well as unstructured remarks and comments.

In this article, we investigate the possibility of cross-language communication using a synergy of words and pictures on mobile devices. On the one hand, communicating with only pictures is in itself a very powerful strategy, but is limited in expressiveness. On the other hand, words can express everything you could wish to say, but they are cumbersome to work with on mobile devices and need to be translated in order for their meaning to be understood. Automatic translations can contain errors that pervert the communication process, and this may undermine the users' confidence when expressing themselves across language barriers. Our idea is to create a user interface for cross-language communication that uses pictures as the primary mode of input, and words to express the detailed meaning.