Healthcare data continues to flourish yet a relatively small portion, mostly structured, is being utilized effectively for predicting clinical outcomes. The rich subjective information available in unstructured clinical notes can possibly facilitate higher discrimination but tends to be under-utilized in mortality prediction. This work attempts to assess the gain in performance when multiple notes that have been minimally preprocessed are used as an input for prediction. A hierarchical architecture consisting of both convolutional and recurrent layers is used to concurrently model the different notes compiled in an individual hospital stay. This approach is evaluated on predicting in-hospital mortality on the MIMIC-III dataset. On comparison to approaches utilizing structured data, it achieved higher metrics despite requiring less cleaning and preprocessing. This demonstrates the potential of unstructured data in enhancing mortality prediction and signifies the need to incorporate more raw unstructured data into current clinical prediction methods.

Applying reinforcement learning (RL) to physical systems presents notable challenges, given requirements regarding sample efficiency, safety, and physical constraints compared to simulated environments. To enable transfer of policies trained in simulation, randomising simulation parameters leads to more robust policies, but also significantly extends training time. In this paper, we exploit access to privileged information (such as environment states) often available in simulation, in order to improve and accelerate learning over randomised environments. We introduce Attention Privileged Reinforcement Learning (APRiL), which equips the agent with an attention mechanism and makes use of state information in simulation, learning to align attention between state- and image-based policies while additionally sharing generated data. During deployment we can apply the image-based policy to remove the requirement of access to additional information. We experimentally demonstrate accelerated and more robust learning on a number of diverse domains, leading to improved final performance for environments both within and outside the training distribution.

Hindsight Credit Assignment (HCA) refers to a recently proposed family of methods for producing more efficient credit assignment in reinforcement learning. These methods work by explicitly estimating the probability that certain actions were taken in the past given present information. Prior work has studied the properties of such methods and demonstrated their behaviour empirically. We extend this work by introducing a particular HCA algorithm which has provably lower variance than the conventional Monte-Carlo estimator when the necessary functions can be estimated exactly. This result provides a strong theoretical basis for how HCA could be broadly useful.

In this paper we introduce and study {\em all-pay bidding games}, a class of two player, zero-sum games on graphs. The game proceeds as follows. We place a token on some vertex in the graph and assign budgets to the two players. Each turn, each player submits a sealed legal bid (non-negative and below their remaining budget), which is deducted from their budget and the highest bidder moves the token onto an adjacent vertex. The game ends once a sink is reached, and \PO pays \PT the outcome that is associated with the sink. The players attempt to maximize their expected outcome. Our games model settings where effort (of no inherent value) needs to be invested in an ongoing and stateful manner. On the negative side, we show that even in simple games on DAGs, optimal strategies may require a distribution over bids with infinite support. A central quantity in bidding games is the {\em ratio} of the players budgets. On the positive side, we show a simple FPTAS for DAGs, that, for each budget ratio, outputs an approximation for the optimal strategy for that ratio. We also implement it, show that it performs well, and suggests interesting properties of these games. Then, given an outcome $c$, we show an algorithm for finding the necessary and sufficient initial ratio for guaranteeing outcome $c$ with probability~$1$ and a strategy ensuring such. Finally, while the general case has not previously been studied, solving the specific game in which \PO wins iff he wins the first two auctions, has been long stated as an open question, which we solve.

In this work, we focus on the problem of entity alignment in Knowledge Graphs (KG) and we report on our experiences when applying a Graph Convolutional Network (GCN) based model for this task. Variants of GCN are used in multiple state-of-the-art approaches and therefore it is important to understand the specifics and limitations of GCN-based models. Despite serious efforts, we were not able to fully reproduce the results from the original paper and after a thorough audit of the code provided by authors, we concluded, that their implementation is different from the architecture described in the paper. In addition, several tricks are required to make the model work and some of them are not very intuitive. We provide an extensive ablation study to quantify the effects these tricks and changes of architecture have on final performance. Furthermore, we examine current evaluation approaches and systematize available benchmark datasets. We believe that people interested in KG matching might profit from our work, as well as novices entering the field

The recent (2019-02) demonstration of the power of huge language models such as GPT-2 to memorise the answers to factoid questions raises questions about the extent to which knowledge is being embedded directly within these large models. This short paper describes an architecture through which much smaller models can also answer such questions - by making use of 'raw' external knowledge. The contribution of this work is that the methods presented here rely on unsupervised learning techniques, complementing the unsupervised training of the Language Model. The goal of this line of research is to be able to add knowledge explicitly, without extensive training.

In this paper we consider a defending problem on a network. In the model, the defender holds a total defending resource of R, which can be distributed to the nodes of the network. The defending resource allocated to a node can be shared by its neighbors. There is a weight associated with every edge that represents the efficiency defending resources are shared between neighboring nodes. We consider the setting when each attack can affect not only the target node, but its neighbors as well. Assuming that nodes in the network have different treasures to defend and different defending requirements, the defender aims at allocating the defending resource to the nodes to minimize the loss due to attack. We give polynomial time exact algorithms for two important special cases of the network defending problem. For the case when an attack can only affect the target node, we present an LP-based exact algorithm. For the case when defending resources cannot be shared, we present a max-flow-based exact algorithm. We show that the general problem is NP-hard, and we give a 2-approximation algorithm based on LP-rounding. Moreover, by giving a matching lower bound of 2 on the integrality gap on the LP relaxation, we show that our rounding is tight.

Dialogue response generation (DRG) is a critical component of task-oriented dialogue systems (TDSs). Its purpose is to generate proper natural language responses given some context, e.g., historical utterances, system states, etc. State-of-the-art work focuses on how to better tackle DRG in an end-to-end way. Typically, such studies assume that each token is drawn from a single distribution over the output vocabulary, which may not always be optimal. Responses vary greatly with different intents, e.g., domains, system actions. We propose a novel mixture-of-generators network (MoGNet) for DRG, where we assume that each token of a response is drawn from a mixture of distributions. MoGNet consists of a chair generator and several expert generators. Each expert is specialized for DRG w.r.t. a particular intent. The chair coordinates multiple experts and combines the output they have generated to produce more appropriate responses. We propose two strategies to help the chair make better decisions, namely, a retrospective mixture-of-generators (RMoG) and prospective mixture-of-generators (PMoG). The former only considers the historical expert-generated responses until the current time step while the latter also considers possible expert-generated responses in the future by encouraging exploration. In order to differentiate experts, we also devise a global-and-local (GL) learning scheme that forces each expert to be specialized towards a particular intent using a local loss and trains the chair and all experts to coordinate using a global loss. We carry out extensive experiments on the MultiWOZ benchmark dataset. MoGNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, demonstrating its effectiveness for DRG.

In this paper, we study automatic question generation, the task of creating questions from corresponding text passages where some certain spans of the text can serve as the answers. We propose an Extended Answer-aware Network (EAN) which is trained with Word-based Coverage Mechanism (WCM) and decodes with Uncertainty-aware Beam Search (UBS). The EAN represents the target answer by its surrounding sentence with an encoder, and incorporates the information of the extended answer into paragraph representation with gated paragraph-to-answer attention to tackle the problem of the inadequate representation of the target answer. To reduce undesirable repetition, the WCM penalizes repeatedly attending to the same words at different time-steps in the training stage. The UBS aims to seek a better balance between the model confidence in copying words from an input text paragraph and the confidence in generating words from a vocabulary. We conduct experiments on the SQuAD dataset, and the results show our approach achieves significantly performance improvement. Introduction Question generation (QG) aims to automatically generate questions from corresponding natural language text passages.

Unmanned aerial vehicles (UAVs) can be utilized as aerial base stations (ABSs) to assist terrestrial infrastructure for keeping wireless connectivity in various emergency scenarios. To maximize the coverage rate of N ground users (GUs) by jointly placing multiple ABSs with limited coverage range is known to be a NP-hard problem with exponential complexity in N. The problem is further complicated when the coverage range becomes irregular due to site-specific blockage (e.g., buildings) on the air-ground channel in the 3-dimensional (3D) space. To tackle this challenging problem, this paper applies the Deep Reinforcement Learning (DRL) method by 1) representing the state by a coverage bitmap to capture the spatial correlation of GUs/ABSs, whose dimension and associated neural network complexity is invariant with arbitrarily large N; and 2) designing the action and reward for the DRL agent to effectively learn from the dynamic interactions with the complicated propagation environment represented by a 3D Terrain Map. Specifically, a novel two-level design approach is proposed, consisting of a preliminary design based on the dominant line-of-sight (LoS) channel model, and an advanced design to further refine the ABS positions based on site-specific LoS/non-LoS channel states. The double deep Q-network (DQN) with Prioritized Experience Replay (Prioritized Replay DDQN) algorithm is applied to train the policy of multi-ABS placement decision. Numerical results show that the proposed approach significantly improves the coverage rate in complex environment, compared to the benchmark DQN and K-means algorithms.