In this paper we describe the implementation of a convolutional neural network (CNN) used to assess online review helpfulness. To our knowledge, this is the first use of this architecture to address this problem. We explore the impact of two related factors impacting CNN performance: different word embedding initializations and different input review lengths. We also propose an approach to combining rating star information with review text to further improve prediction accuracy. We demonstrate that this can improve the overall accuracy by 2%. Finally, we evaluate the method on a benchmark dataset and show an improvement in accuracy relative to published results for traditional methods of 2.5% for a model trained using only review text and 4.24% for a model trained on a combination of rating star information and review text.

A number of techniques have been proposed for aspect discovery using part of speech tagging (Hu and Liu, 2004), syntactic parsing (Lu et al., 2009), clustering (Mei et al., 2007; Titov and McDonald, 2008b), data mining (Ku et al., 2006), and information extraction (Popescu and Etzioni, 2005). Various lexicon and rule-based methods (Hu and Liu, 2004; Ku et al., 2006; Blair-Goldensohn et al., 2008) have been adopted for sentiment prediction together with a few learning approaches (Lu et al., 2009; Pappas and Popescu-Belis, 2017; Angelidis and Lapata, 2018). As for the summaries, a common format involves a list of aspects and the number of positive and negative opinions for each (Hu and Liu, 2004). While this format gives an overall idea of people's opinion, reading the actual text might be necessary to gain a better understanding of specific details. Textual summaries are created following mostly extractive methods (but see Ganesan et al. 2010 for an abstractive approach), and various formats ranging from lists of words (Popescu and Etzioni, 2005), to phrases (Lu et al., 2009), and sentences (Mei et al., 2007; Blair-Goldensohn et al., 2008; Lerman et al., 2009; Wang and Ling, 2016). In this paper, we present a neural framework for opinion extraction from product reviews. We follow the standard architecture for aspect-based summarization, while taking advantage of the success of neural network models in learning continuous features without recourse to preprocessing tools or linguistic annotations.

Many applications require an understanding of an image that goes beyond the simple detection and classification of its objects. In particular, a great deal of semantic information is carried in the relationships between objects. We have previously shown that the combination of a visual model and a statistical semantic prior model can improve on the task of mapping images to their associated scene description. In this paper, we review the model and compare it to a novel conditional multi-way model for visual relationship detection, which does not include an explicitly trained visual prior model. We also discuss potential relationships between the proposed methods and memory models of the human brain.

Recent machine learning strategies for segmentation tasks have shown great ability when trained on large pixel-wise annotated image datasets. It remains a major challenge however to aggregate such datasets, as the time and monetary cost associated with collecting extensive annotations is extremely high. This is particularly the case for generating precise pixel-wise annotations in video and volumetric image data. To this end, this work presents a novel framework to produce pixel-wise segmentations using minimal supervision. Our method relies on 2D point supervision, whereby a single 2D location within an object of interest is provided on each image of the data. Our method then estimates the object appearance in a semi-supervised fashion by learning object-image-specific features and by using these in a semi-supervised learning framework. Our object model is then used in a graph-based optimization problem that takes into account all provided locations and the image data in order to infer the complete pixel-wise segmentation. In practice, we solve this optimally as a tracking problem using a K-shortest path approach. Both the object model and segmentation are then refined iteratively to further improve the final segmentation. We show that by collecting 2D locations using a gaze tracker, our approach can provide state-of-the-art segmentations on a range of objects and image modalities (video and 3D volumes), and that these can then be used to train supervised machine learning classifiers.

The paper considers the problem of performing a task defined on a model parameter that is only observed indirectly through noisy data in an ill-posed inverse problem. A key aspect is to formalize the steps of reconstruction and task as appropriate estimators (non-randomized decision rules) in statistical estimation problems. The implementation makes use of (deep) neural networks to provide a differentiable parametrization of the family of estimators for both steps. These networks are combined and jointly trained against suitable supervised training data in order to minimize a joint differentiable loss function, resulting in an end-to-end task adapted reconstruction method. The suggested framework is generic, yet adaptable, with a plug-and-play structure for adjusting both the inverse problem and the task at hand. More precisely, the data model (forward operator and statistical model of the noise) associated with the inverse problem is exchangeable, e.g., by using neural network architecture given by a learned iterative method. Furthermore, any task that is encodable as a trainable neural network can be used. The approach is demonstrated on joint tomographic image reconstruction, classification and joint tomographic image reconstruction segmentation.

The recent CIO Summit saw executives across Australia coming together to discuss cutting-edge technology trends and management strategies. The event featured a heavyweight line-up of speakers and moderators, carefully selected to encourage discussion and challenge the status quo. IT Brief spoke to Huawei Australia chief technology officer David Soldani about his key takeaways from the event. That the world is changing fast, profoundly impacting every person, home, and organisation. For example, by 2025, 80% of people will have access to mobile broadband and the mobile traffic per day will rise from 30MB to 4GB per day; 75% of households will enjoy broadband services with 20 billion devices connected, with 12% of those being smart robots.

Artificial intelligence (AI) has fuelled science fiction for decades. Yet now, with technology having caught up with and overtaken human imagination, its capabilities are becoming science fact and too powerful for business leaders to ignore. AI, even in its relative infancy, is enabling C-suiters to redraw all aspects of their organisations. Those who embrace AI and related nascent digital technologies – automation, robotics, machine-learning, big data – are already gaining a significant advantage over laggards. "Everything invented in the past 150 years will be reinvented using AI within the next 15 years," predicts Randy Dean, San Francisco-based chief business officer at Launchpad.AI.

The best asset that anyone has actually--looking at work for the future--the best thing is the ability to learn. And the reason I say the ability to learn is that in the future, when you look at how fast technology is really [moving]--it's exploding. We have artificial intelligence, machine learning. These are algorithms that iterate on themselves. As things get smarter and faster and quicker, the reason our greatest asset is the ability to learn is that it's no longer about what we knew from the past or the degree we earned. All of these things that we're talking about are not found in books, and so this is why I say what's most important is your ability to learn because you're going to be in the moment, learning new things, and adjusting and being quite agile with what you might be doing. What your job title might be might change many, many times because, as technology shifts and changes, so do the roles that are available, and so does the creativity that we apply to it as a human being change, as well. SEE: IT Jobs in 2020: A Leader's Guide (ZDNet) Download as a PDF (TechRepublic) What I think is really unique about human learning versus, say, what artificial intelligence with their algorithms learns is that with human beings, what we're learning is we're learning how to apply what's uniquely human, and that's creativity. How do we apply this piece that artificial intelligence doesn't yet have, and I say yet because I do believe, in the future, artificial intelligence will also acquire the ability to be emotive, to express creativity because if you look at this, if we can teach a chatbot to mimic Shakespeare, then, over time, these algorithms will iterate enough times to actually crack the code on creativity. I believe that to be the future future, but before that time, we might as well capitalize on our greatest human gift, and that is our ability to create, to form from nothingness something truly unique and special and to solve problems with creativity versus, say, set rules.

AI's influence over our world will continue to grow, but it remains a technology in its infancy – however, missteps along the way shouldn't detract from the greater good it promises, says Lenore Kerrigan, country sales director for enterprise information management group, OpenText. In Davos 2018, the great and powerful debated the ethics of Artificial Intelligence (AI), with UK Prime Minister Theresa May launching the UK's Centre for Data Ethics and Innovation. The aim of this advisory body is to work closely with international partners to build a common understanding of how to ensure the safe, ethical and innovative deployment of AI. The move echoes a 2000-year-old debate by Roman poet Juvenal who asked, "Who guards the guardsmen?" The question probed at the very heart of power and its abuse, because if powerful people dictate how the world works, who keeps them in check?

Taking place in German capital Berlin from Friday for a six-day run, IFA 2018 will serve as a place for world-leading tech giants -- around 1,800 exhibitors -- to boast their latest technology highlights ranging from intelligent and interconnected home appliances, artificial intelligence and TVs featuring even better picture quality. Korea's two largest electronics manufacturers Samsung and LG are gearing up for presentations of their visions for smart living with AI and connected devices. On the opening day of the event, LG Electronics CEO & Vice Chairman Jo Seong-jin will deliver a keynote speech for the first time, titled "Think Wise, Be Free: Living Freer with AI," which will offer his insight into how the Korean company's AI strategy can change customers' lives. Other keynote speakers include Richard Yu, CEO of Huawei's consumer business group, who will talk about AI on mobile devices, and Daniel Rausch, vice president of smart home division at Amazon, about how voice is expanding and improving everyday experiences. At its exhibition venue, LG will be showcasing the newest development of AI-powered robots, including its first wearable robot CLOi SuitBot, which the company aggressively has sought for its next growth engine.