Recent developments in Neural Relation Extraction (NRE) have made significant strides towards Automated Knowledge Base Construction (AKBC). While much attention has been dedicated towards improvements in accuracy, there have been no attempts in the literature to our knowledge to evaluate social biases in NRE systems. We create WikiGenderBias, a distantly supervised dataset with a human annotated test set. WikiGenderBias has sentences specifically curated to analyze gender bias in relation extraction systems. We use WikiGenderBias to evaluate systems for bias and find that NRE systems exhibit gender biased predictions and lay groundwork for future evaluation of bias in NRE. We also analyze how name anonymization, hard debiasing for word embeddings, and counterfactual data augmentation affect gender bias in predictions and performance.

Take all the help you can get. If parallel computing has a central tenet, that might be it. Some of the crazy-complex computations asked of today's hardware are so demanding that the compute burden must be borne by multiple processors, effectively "parallelizing" whatever task is being performed. Perhaps the most notable push toward parallelism happened around 2006, when tech hardware powerhouse Nvidia approached Wen-mei Hwu, a professor of electrical and computer engineering at the University of Illinois-Urbana Champaign. Nvidia was designing graphics processing units (GPUs) -- which, thanks to large numbers of threads and cores, had far higher memory bandwidth than the traditional central processing unit (CPUs) -- as a way to process huge numbers of pixels.

Are the Liberal Arts Degrees Useless?

As Vietnam moves from low-tech manufacturing to a service-oriented economy, the country's information technology (IT) market is increasingly gaining traction, giving competition to IT firms in China and India. This has partly been encouraged by the growth of Vietnam as a regional market for domestic enterprises and global technology vendors. As Vietnam adopts Industry 4.0 across all industries, investors should consider the benefits of locating their IT business to the country. Most of the industry is foreign-invested, with multinationals funding projects to build electronic components in the country. At least 86 percent of total IT revenues in 2017 were derived from hardware.

Despite the growing use of artificial-intelligence tools on a global basis, there is no universal code of ethics to govern its use. This is a key question the technology industry is beginning to wrestle with as the use of AI generates results both positive and negative. The technology has already been used for positive outcomes in a number of areas, including improving Australia's beaches, delivering reliable weather forecasts, and detecting human disease more accurately. There is also the other side of the coin, where AI has come under fire for injecting racial bias into criminal sentencing decisions and reinforcing gender discrimination. AI-powered facial recognition tools have been subjected to especially harsh criticism by privacy and human rights organizations.

Perhaps the simplest type of multilingual transfer learning is instance-based transfer learning, in which data from the target language and the auxiliary languages are pooled, and a single model is learned from the pooled data. It is not immediately obvious when instance-based transfer learning will improve performance in this multilingual setting: for instance, a plausible conjecture is this kind of transfer learning would help only if the auxiliary languages were very similar to the target. Here we show that at large scale, this method is surprisingly effective, leading to positive transfer on all of 35 target languages we tested. We analyze this improvement and argue that the most natural explanation, namely direct vocabulary overlap between languages, only partially explains the performance gains: in fact, we demonstrate target-language improvement can occur after adding data from an auxiliary language with no vocabulary in common with the target. This surprising result is due to the effect of transitive vocabulary overlaps between pairs of auxiliary and target languages.

Classical stochastic models, such as the Erd os-R enyi, Barabasi-Albert, and the stochastic block model generate graphs based on a predefined set of parameters, such as the probability of edge formation within and between communities [1]. In contrast, modern approaches to graph generation based on deep learning, including NetGAN [2], GraphGAN [3], and GraphRNN [4], are flexible enough to learn multiple different properties of an input graph simultaneously. The graphs generated by these architectures may be used for downstream learning tasks such as data augmentation [5], recommendation [6], and link prediction [7]. Many real-world networks consist of entities with complex mutual interrelations. Such networks cannot be modeled effectively as graphs with simple pairwise relations, despite the fact that pairwise relations provide a wealth of information for learning. Studying higher-order relationships in a graph is fundamental for our understanding of the network behavior and function. Higher-order relationships are usually termed hyperedges (collections of more than two nodes) [8, 9] or network motifs (recurrent node connectivity patterns that are statistically significant compared to some ground truth random graph model) [10]. These higher-order structures are the actual building blocks of complex networks, as they capture fundamental functional properties.

We propose a novel text generation task, namely Curiosity-driven Question Generation. We start from the observation that the Question Generation task has traditionally been considered as the dual problem of Question Answering, hence tackling the problem of generating a question given the text that contains its answer. Such questions can be used to evaluate machine reading comprehension. However, in real life, and especially in conversational settings, humans tend to ask questions with the goal of enriching their knowledge and/or clarifying aspects of previously gathered information. We refer to these inquisitive questions as Curiosity-driven: these questions are generated with the goal of obtaining new information (the answer) which is not present in the input text. In this work, we experiment on this new task using a conversational Question Answering (QA) dataset; further, since the majority of QA dataset are not built in a conversational manner, we describe a methodology to derive data for this novel task from non-conversational QA data. We investigate several automated metrics to measure the different properties of Curious Questions, and experiment different approaches on the Curiosity-driven Question Generation task, including model pre-training and reinforcement learning. Finally, we report a qualitative evaluation of the generated outputs.

In the travelling thief problem (TTP), a thief undertakes a cyclic tour through a set of cities, and according to a picking plan, picks a subset of available items into a rented knapsack with limited capacity. The overall aim is to maximise profit while minimising renting cost. TTP combines two interdependent components: the travelling salesman problem (TSP) and the knapsack problem (KP). Existing TTP approaches typically solve the TSP and KP components in an interleaved fashion: the solution of one component is fixed while the solution of the other is changed. This indicates poor coordination between solving the two components, which may lead to poor quality TTP solutions. The 2-OPT heuristic is often used for solving the TSP component, which reverses a segment in the tour. Within the TTP context, 2-OPT does not take into account the picking plan, which can result in a lower objective value. This in turn can result in the tour modification to be rejected by a solver. To address this, we propose an extended form of 2-OPT in order to change the picking plan in coordination with modifying the tour. Items deemed as less profitable and picked in cities earlier in the reversed segment are replaced by items that tend to be equally or more profitable and not picked in cities later in the reversed segment. The picking plan is further changed through a modified form of the bit-flip search, where changes in the picking state are only permitted for boundary items, which are defined as lowest profitable picked items or highest profitable unpicked items. This restriction reduces the amount of time spent on the KP component, allowing more tours to be evaluated by the TSP component within a given time budget. The two modified heuristics form the basis of a new cooperative coordination solver, which is shown to outperform several state-of-the-art TTP solvers on a broad range of benchmark TTP instances.

And while we don't always know the full impact of such technological advancement, with Artificial Intelligence (AI) it's becoming increasingly clear that AI will disrupt nearly every industry in one way or another. While many people fear a future in which robots have eliminated human employees from the workforce, AI technology is not nearly that sophisticated yet. Sure, an autonomous train is already helping a company automate its mining operations in Australia, Google is making music with AI and a robot named Flippy has a job flipping burgers in Southern California, but the technology has quite a ways to go before it'll free us from all mundane and repetitive tasks. While experts argue whether AI will ultimately create more jobs than it destroys, we know it is already being used to help humans do their jobs better and augment the number of tasks they can handle concurrently. The technology has been around longer than most people realize.