Recent work in graph models has found that probabilistic hyperedge replacement grammars (HRGs) can be extracted from graphs and used to generate new random graphs with graph properties and substructures close to the original. In this paper, we show how to add latent variables to the model, trained using Expectation-Maximization, to generate still better graphs, that is, ones that generalize better to the test data. We evaluate the new method by separating training and test graphs, building the model on the former and measuring the likelihood of the latter, as a more stringent test of how well the model can generalize to new graphs. On this metric, we find that our latent-variable HRGs consistently outperform several existing graph models and provide interesting insights into the building blocks of real world networks.

Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine comprehension methods, but currently there exist no resources to train and test this capability. We propose a novel task to encourage the development of models for text understanding across multiple documents and to investigate the limits of existing methods. In our task, a model learns to seek and combine evidence - effectively performing multi-hop (alias multi-step) inference. We devise a methodology to produce datasets for this task, given a collection of query-answer pairs and thematically linked documents. Two datasets from different domains are induced, and we identify potential pitfalls and devise circumvention strategies. We evaluate two previously proposed competitive models and find that one can integrate information across documents. However, both models struggle to select relevant information, as providing documents guaranteed to be relevant greatly improves their performance. While the models outperform several strong baselines, their best accuracy reaches 42.9% compared to human performance at 74.0% - leaving ample room for improvement.

A paraphrase is a restatement of the meaning of a text in other words. Paraphrases have been studied to enhance the performance of many natural language processing tasks. In this paper, we propose a novel task iParaphrasing to extract visually grounded paraphrases (VGPs), which are different phrasal expressions describing the same visual concept in an image. These extracted VGPs have the potential to improve language and image multimodal tasks such as visual question answering and image captioning. How to model the similarity between VGPs is the key of iParaphrasing. We apply various existing methods as well as propose a novel neural network-based method with image attention, and report the results of the first attempt toward iParaphrasing.

When Amazon launched in 1995, only 3% of Americans had ever been on the Internet, let alone purchased anything online. Both the concept of the web and e-commerce were startlingly new. Just a year earlier in fact, the New York Times had run a story with the headline: "Attention Shoppers: Internet Is Open", breathlessly reporting the first online transaction, the sale of a Sting CD. Also in 1995, Auction Web went live, which was to become eBay. A broken laser pointer – to a collector of broken laser pointers no less – for $14.83.

Monday, the 29th, marked the beginning of the EU Green Week, an event organized by the European Commission's Directorate-General for Environment to discuss environmental policies. This year, the focus is "Green jobs for a greener future." The organizers stressed how traditional specializations will be characterized by additional sets of new skills. Being able to deal with technology is certainly one of them, and many jobs in the environmental sciences are already adopting these innovative tools. People working in this sector are no longer restricted to field work and laboratory analyses.

Growing up in Egypt in the 1980s, Rana el Kaliouby was fascinated by hidden languages--the rapid-fire blinks of 1s and 0s computers use to transform electricity into commands and the infinitely more complicated nonverbal cues that teenagers use to transmit volumes of hormone-laden information to each other. Culture and social stigma discouraged girls like el Kaliouby in the Middle East from hacking either code, but she wasn't deterred. When her father brought home an Atari video game console and challenged the three el Kaliouby sisters to figure out how it worked, Rana gleefully did. When she wasn't allowed to date, el Kaliouby studied her peers the same way that she did the Atari. "I was always the first one to say'Oh, he has a crush on her' because of all of the gestures and the eye contact," she says.

We consider semidefinite programs (SDPs) of size n with equality constraints. In order to overcome scalability issues, Burer and Monteiro proposed a factorized approach based on optimizing over a matrix Y of size $n$ by $k$ such that $X = YY^*$ is the SDP variable. The advantages of such formulation are twofold: the dimension of the optimization variable is reduced and positive semidefiniteness is naturally enforced. However, the problem in Y is non-convex. In prior work, it has been shown that, when the constraints on the factorized variable regularly define a smooth manifold, provided k is large enough, for almost all cost matrices, all second-order stationary points (SOSPs) are optimal. Importantly, in practice, one can only compute points which approximately satisfy necessary optimality conditions, leading to the question: are such points also approximately optimal? To this end, and under similar assumptions, we use smoothed analysis to show that approximate SOSPs for a randomly perturbed objective function are approximate global optima, with k scaling like the square root of the number of constraints (up to log factors). We particularize our results to an SDP relaxation of phase retrieval.

Global Artificial Intelligence in Retail Market is Expected to Grow From US$ 712.6 Million in 2016 to US$ 27,238.6 Inception of exponential technologies such as sensors, robotics, virtual reality, and artificial intelligence in the retail industry has enabled the retailers to enhance their interactions with consumers and transformed the way retail operations were performed. This change in the industry is prominently driven by the seismic shift in the shopping pattern of the consumers, and their preferences backed by demographic dividend across regions. The report focuses on an in-depth segmentation of this market based by retail format, technology, and application. The geographic segmentation of the report covers five major regions including; North Americas, Europe, Asia-Pacific (APAC), Middle East and Africa (MEA) and South America (SA).

Artificial intelligence evokes hope and anxiety. Will we master it, or will it control us? Kwame A. A Opoku and Tendai Joe think a lot about artificial intelligence -- where it's come from and what lies ahead -- from different perspectives. Opoku is a futurist, global business speaker and founder of the think tank, Idea Factory Africa. Joe is involved in software and mobile application development, and digital publishing.

In 1998, while looking for topics for her Master's thesis at the American University in Cairo, [Rana] el Kaliouby stumbled upon a book by MIT researcher Rosalind Picard. It argued that, since emotions play a large role in human decision-making, machines will require emotional intelligence if they are to truly understand human needs. El Kaliouby was captivated by the idea that feelings could be measured, analyzed, and used to design systems that can genuinely connect with people. Today, el Kaliouby is the CEO of Affectiva, a company that's building the type of emotionally intelligent AI systems Picard envisioned two decades ago. Affectiva's software measures a user's emotional response through algorithms that identify key facial landmarks and analyze pixels in those regions to classify facial expressions.