While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite the potential of this approach for low-resource settings, existing systems are far behind their supervised counterparts, limiting their practical interest. In this paper, we propose an alternative approach based on phrase-based Statistical Machine Translation (SMT) that significantly closes the gap with supervised systems. Our method profits from the modular architecture of SMT: we first induce a phrase table from monolingual corpora through cross-lingual embedding mappings, combine it with an n-gram language model, and fine-tune hyperparameters through an unsupervised MERT variant. In addition, iterative backtranslation improves results further, yielding, for instance, 14.08 and 26.22 BLEU points in WMT 2014 English-German and English-French, respectively, an improvement of more than 7-10 BLEU points over previous unsupervised systems, and closing the gap with supervised SMT (Moses trained on Europarl) down to 2-5 BLEU points. Our implementation is available at https:// github.com/artetxem/monoses.

Structured scene descriptions of images are useful for the automatic processing and querying of large image databases. We show how the combination of a semantic and a visual statistical model can improve on the task of mapping images to their associated scene description. In this paper we consider scene descriptions which are represented as a set of triples (subject, predicate, object), where each triple consists of a pair of visual objects, which appear in the image, and the relationship between them (e.g. man-riding-elephant, man-wearing-hat). We combine a standard visual model for object detection, based on convolutional neural networks, with a latent variable model for link prediction. We apply multiple state-of-the-art link prediction methods and compare their capability for visual relationship detection. One of the main advantages of link prediction methods is that they can also generalize to triples, which have never been observed in the training data. Our experimental results on the recently published Stanford Visual Relationship dataset, a challenging real world dataset, show that the integration of a semantic model using link prediction methods can significantly improve the results for visual relationship detection. Our combined approach achieves superior performance compared to the state-of-the-art method from the Stanford computer vision group.

Scientists have used artificial intelligence to predict how cancers will progress and evolve, which could help doctors design the most effective treatment for each patient. A team led by the Institute of Cancer Research, London (ICR) and the University of Edinburgh developed a new technique known as Revolver (Repeated evolution of cancer), which picks out patterns in DNA mutation within cancers and uses the information to forecast future genetic changes. They said the ever-changing nature of tumours is one of the biggest challenges of treatment – with cancers often evolving to a drug-resistant form. Parents think children should be taught signs of cancer, poll finds'Exciting' cancer drug combination shrinks tumours and stops growth Parental cancer has lifetime impact on children's education and earnin Vaping causes DNA mutations which could lead to cancer, says study'Exciting' cancer drug combination shrinks tumours and stops growth Parental cancer has lifetime impact on children's education and earnin But if doctors can predict how a tumour will evolve, they could intervene earlier to stop cancer in its tracks before it has had a chance to evolve or develop resistance, increasing the patient's chances of survival. The team also found a link between certain sequences of repeated tumour mutations and survival outcome.

Search has always been a key enterprise technology going back to the days of the first enterprise content management systems. This is hardly surprising given how important finding the right data is for any of the applications used by enterprises in their business processes. Since the rise of big data and the use of big data sets, search has become even more important. If enterprise data is the real wealth of a business, then search is the tool that uncovers that wealth. But what do you do with the increasingly large amounts of data that enterprises now have access to?

As a teenager in Nigeria, I tried to build an artificial intelligence system. I was inspired by the same dream that motivated the pioneers in the field: That we could create an intelligence of pure logic and objectivity that would free humanity from human error and human foibles. I was working with weak computer systems and intermittent electricity, and needless to say my AI project failed. Eighteen years later--as an engineer researching artificial intelligence, privacy, and machine-learning algorithms--I'm seeing that so far, the premise that AI can free us from subjectivity or bias is also disappointing. We are creating intelligence in our own image.

Dimension reduction is a main step in learning process which plays a essential role in many applications. The most popular methods in this field like SVD, PCA, and LDA, only can apply to vector data. This means that for higher order data like matrices or more generally tensors, data should be fold to a vector. By this folding, the probability of overfitting is increased and also maybe some important spatial features are ignored. Then, to tackle these issues, methods are proposed which work directly on data with their own format like GLRAM, MPCA, and MLDA. In these methods the spatial relationship among data are preserved and furthermore, the probability of overfitiing has fallen. Also the time and space complexity are less than vector-based ones. Having said that, because of the less parameters in multilinear methods, they have a much smaller search space to find an optimal answer in comparison with vector-based approach. To overcome this drawback of multilinear methods like GLRAM, we proposed a new method which is a general form of GLRAM and by preserving the merits of it have a larger search space. We have done plenty of experiments to show that our proposed method works better than GLRAM. Also, applying this approach to other multilinear dimension reduction methods like MPCA and MLDA is straightforwar

The on-chip implementation of learning algorithms would speed-up the training of neural networks in crossbar arrays. The circuit level design and implementation of backpropagation algorithm using gradient descent operation for neural network architectures is an open problem. In this paper, we proposed the analog backpropagation learning circuits for various memristive learning architectures, such as Deep Neural Network (DNN), Binary Neural Network (BNN), Multiple Neural Network (MNN), Hierarchical Temporal Memory (HTM) and Long-Short Term Memory (LSTM). The circuit design and verification is done using TSMC 180nm CMOS process models, and TiO2 based memristor models. The application level validations of the system are done using XOR problem, MNIST character and Yale face image databases

AAAS analyst assists a human rights organization in gathering data during an exhumation. Against a backdrop of summer heat and a constant roar of distant howler monkeys, a scientific analyst piloted a drone to collect data from a hillside in northern Guatemala. At his side, anthropologists affiliated with a regional human rights group painstakingly cleared soil and roots from human remains in a mass grave. "Remains contorted, overlapping, interlaced, a cruel, tragic mashup of Hieronymus Bosch and H.R. Giger," noted Jonathan Drake, senior program associate of the American Association for the Advancement of Science's Geospatial Technologies Project, summoning images from 15th- and 20th-century artists to describe the nightmarish remnants of an atrocity estimated to have occurred sometime after 1980, during Guatemala's lengthy civil war. Clothing with burnt edges stuck to the bones of some.

From facial recognition for unlocking our smartphones to speech recognition and intent analysis for voice assistance, artificial intelligence is all around us today. In the business world, AI is helping us uncover new insight from data and enhance decision-making. For example, online retailers use AI to recommend new products to consumers based on past purchases. And, banks use conversational AI to interact with clients and enhance their customer experiences. However, most of the AI in use now is "narrow AI," meaning it is only capable of performing individual tasks. In contrast, general AI – which is not available yet – can replicate human thought and function, taking emotions and judgment into account.

Text representations using neural word embeddings have proven effective in many NLP applications. Recent researches adapt the traditional word embedding models to learn vectors of multiword expressions (concepts/entities). However, these methods are limited to textual knowledge bases (e.g., Wikipedia). In this paper, we propose a novel and simple technique for integrating the knowledge about concepts from two large scale knowledge bases of different structure (Wikipedia, and Probase) in order to learn concept representations. We adapt the efficient skip-gram model to seamlessly learn from the knowledge in Wikipedia text and Probase concept graph. We evaluate our concept embedding models on two tasks: 1) analogical reasoning, where we achieve a stateof-the-art performance of 91% on semantic analogies, 2) concept categorization, where we achieve a state-of-the-art performance on two benchmark datasets achieving categorization accuracy of 100% on one and 98% on the other. Additionally, we present a case study to evaluate our model on unsupervised argument type identification for neural semantic parsing. We demonstrate the competitive accuracy of our unsupervised method and its ability to better generalize to out of vocabulary entity mentions compared to the tedious and error prone methods which depend on gazetteers and regular expressions. In this paper, we use the terms "concept" and "entity" interchangeably. Hongxia Jin Samsung Research America 665 Clyde Avenue, Mountain View, CA 94043, USA Email: hongxia.jin@samsung.com 2 Walid Shalaby et al. Figure 1 Integrating knowledge from Wikipedia text (left) and Probase concept graph (right). Local concept-concept, concept-word, and word-word contexts are generated from both KBs and used for training the skip-gram model.