The damaging effects of hate speech in social media are evident during the last few years, and several organizations, researchers and the social media platforms themselves have tried to harness them without great success. Recently, following the advent of deep learning, several novel approaches appeared in the field of hate speech detection. However, it is apparent that such approaches depend on large-scale datasets in order to exhibit competitive performance. In this paper, we present a novel, publicly available collection of datasets in five different languages, that consists of tweets referring to journalism-related accounts, including high-quality human annotations for hate speech and personal attack. To build the datasets we follow a concise annotation strategy and employ an active learning approach. Additionally, we present a number of state-of-the-art deep learning architectures for hate speech detection and use these datasets to train and evaluate them. Finally, we propose an ensemble model that outperforms all individual models.

Optimization algorithms inspired by the geometry of dissipative systems Alessandro Bravetti 1, Maria L. Daza-Torres 2, Hugo Flores-Arguedas 3, and Michael Betancourt 4 1 Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas (IIMAS), Universidad Nacional Autónoma de México, A.P. 70-543, 04510 Ciudad de México, México alessandro.bravetti@iimas.unam.mx 2 Universidad de Guadalajara, Guadalajara, México, mdazatorres@cimat.mx 3 Centro de Investigación en Matemáticas (CIMAT), Guanajuato, México, hugo.flores@cimat.mx 4 Symplectomorphic LLC, New York, USA, betan@symplectomorphic.com Abstract Accelerated gradient methods are a powerful optimization tool in machine learning and statistics but their development has traditionally been driven by heuristic motivations. Recent research, however, has demonstrated that these methods can be derived as discretizations of dynamical systems, which in turn has provided a basis for more systematic investigations, especially into the structure of those dynamical systems and their structure preserving discretizations. In this work we introduce dynamical systems defined through a contact geometry which are not only naturally suited to the optimization goal but also subsume all previous methods based on geometric dynamical systems. These contact dynamical systems also admit a natural, robust discretization through geometric contact integrators. We demonstrate these features in paradigmatic examples which show that we can indeed obtain optimization algorithms that achieve oracle lower bounds on convergence rates while also improving on previous proposals in terms of stability. Keywords: optimization, accelerated gradient, geometric integrators, contact geometry 1 arXiv:1912.02928v1 Despite their practical utility and explicit convergence bounds, accelerated gradient methods have long been difficult to motivate from a fundamental theory.

Machine learning has started to be deployed in fields such as healthcare and finance, which propelled the need for and growth of privacy-preserving machine learning (PPML). We propose an actively secure four-party protocol (4PC), and a framework for PPML, showcasing its applications on four of the most widely-known machine learning algorithms -- Linear Regression, Logistic Regression, Neural Networks, and Convolutional Neural Networks. Our 4PC protocol tolerating at most one malicious corruption is practically efficient as compared to the existing works. We use the protocol to build an efficient mixed-world framework (Trident) to switch between the Arithmetic, Boolean, and Garbled worlds. Our framework operates in the offline-online paradigm over rings and is instantiated in an outsourced setting for machine learning. Also, we propose conversions especially relevant to privacy-preserving machine learning. The highlights of our framework include using a minimal number of expensive circuits overall as compared to ABY3. This can be seen in our technique for truncation, which does not affect the online cost of multiplication and removes the need for any circuits in the offline phase. Our B2A conversion has an improvement of $\mathbf{7} \times$ in rounds and $\mathbf{18} \times$ in the communication complexity. In addition to these, all of the special conversions for machine learning, e.g. Secure Comparison, achieve constant round complexity. The practicality of our framework is argued through improvements in the benchmarking of the aforementioned algorithms when compared with ABY3. All the protocols are implemented over a 64-bit ring in both LAN and WAN settings. Our improvements go up to $\mathbf{187} \times$ for the training phase and $\mathbf{158} \times$ for the prediction phase when observed over LAN and WAN.

Recently there has been an increase in the studies on time - series data mining specifically time - series clustering due to the vast existe nce of time - series in various domains. The large volume of data in the form of time - series make s it necessary to employ various techniques such as clustering to understand the data and to extract information and hidden patterns. In the field of clustering specifically, time - series clustering, the most important aspects are the similarity measure used and the algorithm employed to conduct the clustering. In this paper, a new similarity measure for time - series clustering is developed based on a combination of a simple representation of time - series, slope of each segment of time - series, Euclidean distance and the so - called dynamic time warping. It is proved in this paper that the proposed distance measure is metric and thus indexing can be applied. For the task of clustering, the Particle Swarm Optimization algorithm is employed. The proposed similarity measure is compared to three existing measures in terms of various criteria used for the evaluation of clustering algorithms. The results indicate that the propo sed similarity measure outperforms the rest in almost every dataset used in this paper.

We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL). Standard RL predicts rewards, while UDRL instead uses rewards as task-defining inputs, together with representations of time horizons and other computable functions of historic and desired future data. UDRL learns to interpret these input observations as commands, mapping them to actions (or action probabilities) through SL on past (possibly accidental) experience. UDRL generalizes to achieve high rewards or other goals, through input commands such as: get lots of reward within at most so much time! A separate paper [61] on first experiments with UDRL shows that even a pilot version of UDRL can outperform traditional baseline algorithms on certain challenging RL problems. We also introduce a related simple but general approach for teaching a robot to imitate humans. First videotape humans imitating the robot's current behaviors, then let the robot learn through SL to map the videos (as input commands) to these behaviors, then let it generalize and imitate videos of humans executing previously unknown behavior. This Imitate-Imitator concept may actually explain why biological evolution has resulted in parents who imitate the babbling of their babies.

Search methods, such as Genetic Algorithms and Simulated Annealing are typically used to achieve the required scalability in challenging problems for which it is hard to find optimal, or even just "good enough' solutions. The majority of these methods involve steps where the state of the algorithm is modified in some way to escape a local optimum. The aim is to avoid premature convergence, which is when the search method converges (usually very early in the search) to a local optimum of poor quality [1, 2]. Previous research has shown that the performance of search strategies is affected by the structure of the fitness landscape [3, 4]. A fitness landscape is defined by three components: i) the search space, which is the set of all candidate solutions, ii) the fitness function, which assigns a fitness value to each solution, and the neighbourhood operator, which defines how solutions are connected, and as a results how the search strategy can traverse the landscape.

The recognition of emotion and dialogue acts enrich conversational analysis and help to build natural dialogue systems. Emotion makes us understand feelings and dialogue acts reflect the intentions and performative functions in the utterances. However, most of the textual and multi-modal conversational emotion datasets contain only emotion labels but not dialogue acts. To address this problem, we propose to use a pool of various recurrent neural models trained on a dialogue act corpus, with or without context. These neural models annotate the emotion corpus with dialogue act labels and an ensemble annotator extracts the final dialogue act label. We annotated two popular multi-modal emotion datasets: IEMOCAP and MELD. We analysed the co-occurrence of emotion and dialogue act labels and discovered specific relations. For example, Accept/Agree dialogue acts often occur with the Joy emotion, Apology with Sadness, and Thanking with Joy. We make the Emotional Dialogue Act (EDA) corpus publicly available to the research community for further study and analysis.

Videos showing autonomous or self-driving vehicles weaving in and out of crossroads at speed without colliding suggest this technology will solve traffic problems. You almost never see pedestrians or cyclists in these videos. The reality is that they don't fit. The vision of autonomous traffic is either of a large convoy of vehicles just a metre apart moving along road corridors at 100km/h, or of vehicles in an urban setting where their sensors are picking up every pedestrian movement and slowing or stopping. In the first case, the vehicles form an impenetrable barrier to pedestrians or cyclists (who, like on a freeway, will probably be banned).

Last week, the Australian state of New South Wales announced a plan to crack down on drivers using their phones on the road. The state's transport agency said it had integrated machine vision into roadside cameras to spot offenders. The AI automatically flags suspects, humans confirm what's going on, and a warning letter is sent out to the driver. "It's a system to change the culture," the assistant police commissioner of New South Wales, Michael Corboy, told Australian media, noting that police hoped the technology would cut fatalities on the road by a third over two years. It seems an admirable scheme, top to bottom.

More than half of companies in Australia (54%) hope to invest in inventory planning and logistics, compared to 39% of organisations elsewhere in the world. Meanwhile, 46% of Australian firms plan to expand their CRM, compared to 39% of companies in other countries. READ MORE: Half of existing jobs will be extinct by 2025 – is HR safe? While 45% of global business leaders want to invest in industrial automation, only 28% of those in Australia plan to do the same. Overall, international respondents claim AI would boost their company's productivity. However, only 21% of leaders in Australia predict it would result in a lower headcount in their industry.