Abstract--Requirements elicitation requires extensive knowledge and deep understanding of the problem domain where the final system will be situated. However, in many software development projects, analysts are required to elicit the requirements from an unfamiliar domain, which often causes communication barriers between analysts and stakeholders. In this paper, we propose a requirements ELICitation Aid tool (ELICA) to help analysts better understand the target application domain by dynamic extraction and labeling of requirementsrelevant knowledge. To extract the relevant terms, we leverage the flexibility and power of Weighted Finite State Transducers (WFSTs) in dynamic modeling of natural language processing tasks. In addition to the information conveyed through text, ELICA captures and processes nonlinguistic information about the intention of speakers such as their confidence level, analytical tone, and emotions. The extracted information is made available to the analysts as a set of labeled snippets with highlighted relevant terms which can also be exported as an artifact of the Requirements Engineering (RE) process. The application and usefulness of ELICA are demonstrated through a case study. This study shows how preexisting relevant information about the application domain and the information captured during an elicitation meeting, such as the conversation and stakeholders' intentions, can be captured and used to support analysts achieving their tasks.

We demonstrate how to learn efficient heuristics for automated reasoning algorithms through deep reinforcement learning. We consider search algorithms for quantified Boolean logics, that already can solve formulas of impressive size - up to 100s of thousands of variables. The main challenge is to find a representation which lends to making predictions in a scalable way. The heuristics learned through our approach significantly improve over the handwritten heuristics for several sets of formulas.

Robotic systems, working together as a team, are becoming valuable players in different real-world applications, from disaster response to warehouse fulfillment services. Centralized solutions for coordinating multi-robot teams often suffer from poor scalability and vulnerability to communication disruptions. This paper develops a decentralized multi-agent task allocation (Dec-MATA) algorithm for multi-robot applications. The task planning problem is posed as a maximum-weighted matching of a bipartite graph, the solution of which using the blossom algorithm allows each robot to autonomously identify the optimal sequence of tasks it should undertake. The graph weights are determined based on a soft clustering process, which also plays a problem decomposition role seeking to reduce the complexity of the individual-agents' task assignment problems. To evaluate the new Dec-MATA algorithm, a series of case studies (of varying complexity) are performed, with tasks being distributed randomly over an observable 2D environment. A centralized approach, based on a state-of-the-art MILP formulation of the multi-Traveling Salesman problem is used for comparative analysis. While getting within 7-28% of the optimal cost obtained by the centralized algorithm, the Dec-MATA algorithm is found to be 1-3 orders of magnitude faster and minimally sensitive to task-to-robot ratios, unlike the centralized algorithm.

The main contribution of this paper is to introduce and describe a new recommender-systems dataset (RARD II). It is based on data from a recommender-system in the digital library and reference management software domain. As such, it complements datasets from other domains such as books, movies, and music. The RARD II dataset encompasses 89m recommendations, covering an item-space of 24m unique items. RARD II provides a range of rich recommendation data, beyond conventional ratings. For example, in addition to the usual ratings matrices, RARD II includes the original recommendation logs, which provide a unique insight into many aspects of the algorithms that generated the recommendations. In this paper, we summarise the key features of this dataset release, describing how it was generated and discussing some of its unique features.

Increased information sharing through short and long-range skip connections between layers in fully convolutional networks have demonstrated significant improvement in performance for semantic segmentation. In this paper, we propose Competitive Dense Fully Convolutional Networks (CDFNet) by introducing competitive maxout activations in place of naive feature concatenation for inducing competition amongst layers. Within CDFNet, we propose two architectural contributions, namely competitive dense block (CDB) and competitive unpooling block (CUB) to induce competition at local and global scales for short and long-range skip connections respectively. This extension is demonstrated to boost learning of specialized sub-networks targeted at segmenting specific anatomies, which in turn eases the training of complex tasks. We present the proof-of-concept on the challenging task of whole body segmentation in the publicly available VISCERAL benchmark and demonstrate improved performance over multiple learning and registration based state-of-the-art methods.

ABSTRACT This paper addresses the problem of stylized text generation in a multilingual setup. A version of a language model based on a long short-term memory (LSTM) artificial neural network with extended phonetic and semantic embeddings is used for stylized poetry generation. Phonetics is shown to have comparable importance for the task of stylized poetry generation as the information on the target author. The quality of the resulting poems generated by the network is estimated through bilingual evaluation understudy (BLEU), a survey and a new cross-entropy based metric that is suggested for the problems of such type. The experiments show that the proposed model consistently outperforms random sample and vanilla-LSTM baselines, humans also tend to attribute machine generated texts to the target author. Index Terms-- stylized text generation, poetry generation, artificial neural networks, multilingual models 1. INTRODUCTION The problem of making machine-generated text feel more authentic has a number of industrial and scientific applications, see, for example, [1] or [2]. Most modern generative models are trained on huge corpora of texts which include different contributions from various authors.

Goodwood Festival of Speed is the place to be if you're into cars and tech. The huge event in West Sussex has evolved a lot over the 25 years of its existence too, much like the vehicles it showcases. While a lot of those creations are from yesteryear, FOS always features the latest in cutting edge technology, some of which could be found in the Goodwood Festival of Speed Future Lab for 2018. Inside there you could also enjoy a virtual reality autonomous trip, but we managed to go one better and experience the real thing. This year, as part of the 25th FOS anniversary celebrations, Siemens came up with a cool idea by fitting out a 1965 Ford Mustang with all the kit to make it fully autonomous.

Last week, at the International Conference on Machine Learning (ICML) in Stockholm, a group of researchers described a turtle they had 3D printed. Most people would say it looks just like a turtle, but an artificial intelligence (AI) algorithm that can normally recognize turtles saw it differently. Most of the time, it thought the turtle was a rifle. Similarly, it saw a 3D-printed baseball as an espresso. These are examples of "adversarial attacks"--subtly altered images, objects, or sounds that fool AIs without setting off human alarm bells.

The Tour de France is one of the toughest and -- in my opinion -- most exciting sporting events in the world. Aside from the occasional rest day, it's a non-stop marathon that pushes competitors and their carbon bicycles to the limit. Lung-busting mountain climbs are punctuated with deadly descents and hard-fought sprints. Only the fittest, smartest and luckiest athletes stand a chance of winning the tour's ultimate prize: the yellow jersey. With this year's race in full swing, I recently decided to try the official video game.

Dropping your phone might be about to become slightly less painful. Gorilla Glass – which makes the glass for just about every premium phone – has been upgraded and so newer phones should be far less likely to smash. Manufacturer Corning claims the new glass is twice as likely to survive drops as its predecessor. It can also can survive 15 drops from 1m in height onto rough surfaces, it claimed. The I.F.O. is fuelled by eight electric engines, which is able to push the flying object to an estimated top speed of about 120mph.