关注即可获取arXiv每日论文自动推送；
如果您有任何问题或建议，请公众号留言。
[如果您觉得本公众号对你有帮助，就是我们最大的荣幸]
今日 cs.AI方向共计28篇文章。
Artificial Intelligence(21篇)
[1]：AI and Wargaming
标题：战争和游戏
作者：James Goodman, Sebastian Risi, Simon Lucas
链接：https://arxiv.org/abs/2009.08922
摘要：Recent progress in Game AI has demonstrated that given enough data from human gameplay, or experience gained via simulations, machines can rival or surpass the most skilled human players in classic games such as Go, or commercial computer games such as Starcraft. We review the current state-of-the-art through the lens of wargaming, and ask firstly what features of wargames distinguish them from the usual AI testbeds, and secondly which recent AI advances are best suited to address these wargame-specific features.
[2]：Monte Carlo Tree Search Based Tactical Maneuvering
标题：基于蒙特卡罗树搜索的战术机动
作者：Kunal Srivastava, Amit Surana
链接：https://arxiv.org/abs/2009.08807
摘要：In this paper we explore the application of simultaneous move Monte Carlo Tree Search (MCTS) based online framework for tactical maneuvering between two unmanned aircrafts. Compared to other techniques, MCTS enables efficient search over long horizons and uses self-play to select best maneuver in the current state while accounting for the opponent aircraft tactics. We explore different algorithmic choices in MCTS and demonstrate the framework numerically in a simulated 2D tactical maneuvering application.
[3]：Dealing with Incompatibilities among Procedural Goals under Uncertainty
标题：不确定条件下程序目标不相容的处理
作者：Mariela Morveli-Espinoza, Juan Carlos Nieves, Ayslan Trevizan Possebom, Cesar Augusto Tacla
备注：14 pages, 4 figures, accepted in the Iberoamerican Journal of Artificial Intelligence. arXiv admin note: substantial text overlap witharXiv:2009.05186
链接：https://arxiv.org/abs/2009.08776
摘要：By considering rational agents, we focus on the problem of selecting goals out of a set of incompatible ones. We consider three forms of incompatibility introduced by Castelfranchi and Paglieri, namely the terminal, the instrumental (or based on resources), and the superfluity. We represent the agent's plans by means of structured arguments whose premises are pervaded with uncertainty. We measure the strength of these arguments in order to determine the set of compatible goals. We propose two novel ways for calculating the strength of these arguments, depending on the kind of incompatibility that exists between them. The first one is the logical strength value, it is denoted by a three-dimensional vector, which is calculated from a probabilistic interval associated with each argument. The vector represents the precision of the interval, the location of it, and the combination of precision and location. This type of representation and treatment of the strength of a structured argument has not been defined before by the state of the art. The second way for calculating the strength of the argument is based on the cost of the plans (regarding the necessary resources) and the preference of the goals associated with the plans. Considering our novel approach for measuring the strength of structured arguments, we propose a semantics for the selection of plans and goals that is based on Dung's abstract argumentation theory. Finally, we make a theoretical evaluation of our proposal.
[4]：Probably Approximately Correct Explanations of Machine Learning Models via Syntax-Guided Synthesis
标题：可能通过语法引导合成对机器学习模型进行近似正确的解释
作者：Daniel Neider, Bishwamittra Ghosh
链接：https://arxiv.org/abs/2009.08770
摘要：We propose a novel approach to understanding the decision making of complex machine learning models (e.g., deep neural networks) using a combination of probably approximately correct learning (PAC) and a logic inference methodology called syntax-guided synthesis (SyGuS). We prove that our framework produces explanations that with a high probability make only few errors and show empirically that it is effective in generating small, human-interpretable explanations.
[5]：TotalBotWar: A New Pseudo Real-time Multi-action Game Challenge and Competition for AI
标题：TotalBotWar：一种新的人工智能虚拟实时多动作游戏挑战与竞争
作者：Alejandro Estaben, César Díaz, Raul Montoliu, Diego Pérez-Liebana
备注：6 pages, 5 figures
链接：https://arxiv.org/abs/2009.08696
摘要：This paper presents TotalBotWar, a new pseudo real-time multi-action challenge for game AI, as well as some initial experiments that benchmark the framework with different agents. The game is based on the real-time battles of the popular TotalWar games series where players manage an army to defeat the opponent's one. In the proposed game, a turn consists of a set of orders to control the units. The number and specific orders that can be performed in a turn vary during the progression of the game. One interesting feature of the game is that if a particular unit does not receive an order in a turn, it will continue performing the action specified in a previous turn. The turn-wise branching factor becomes overwhelming for traditional algorithms and the partial observability of the game state makes the proposed game an interesting platform to test modern AI algorithms.
[6]：EM-RBR: a reinforced framework for knowledge graph completion from reasoning perspective
标题：EM-RBR：一个从推理角度增强知识图完成的框架
作者：Zhaochong An, Bozhou Chen, Houde Quan, Qihui Lin, Hongzhi Wang
链接：https://arxiv.org/abs/2009.08656
摘要：Knowledge graph completion aims to predict the new links in given entities among the knowledge graph (KG). Most mainstream embedding methods focus on fact triplets contained in the given KG, however, ignoring the rich background information provided by logic rules driven from knowledge base implicitly. To solve this problem, in this paper, we propose a general framework, named EM-RBR(embedding and rule-based reasoning), capable of combining the advantages of reasoning based on rules and the state-of-the-art models of embedding. EM-RBR aims to utilize relational background knowledge contained in rules to conduct multi-relation reasoning link prediction rather than superficial vector triangle linkage in embedding models. By this way, we can explore relation between two entities in deeper context to achieve higher accuracy. In experiments, we demonstrate that EM-RBR achieves better performance compared with previous models on FB15k, WN18 and our new dataset FB15k-R. We make the implementation of EM-RBR available atthis https URL.
[7]：RLzoo: A Comprehensive and Adaptive Reinforcement Learning Library
标题：RLzoo：一个综合性和适应性的强化学习库
作者：Zihan Ding, Tianyang Yu, Yanhua Huang, Hongming Zhang, Luo Mai, Hao Dong
备注：Paper under submission at Journal of Machine Learning Research-Open Source Software
链接：https://arxiv.org/abs/2009.08644
摘要：Recently, we have seen a rapidly growing adoption of Deep Reinforcement Learning (DRL) technologies. Fully achieving the promise of these technologies in practice is, however, extremely difficult. Users have to invest tremendous efforts in building DRL agents, incorporating the agents into various external training environments, and tuning agent implementation/hyper-parameters so that they can reproduce state-of-the-art (SOTA) performance. In this paper, we propose RLzoo, a new DRL library that aims to make it easy to develop and reproduce DRL algorithms. RLzoo has both high-level APIs and low-level APIs, useful for constructing and customising DRL agents, respectively. It has an adaptive agent construction algorithm that can automatically integrate custom RLzoo agents into various external training environments. To help reproduce the results of SOTA algorithms, RLzoo provides rich reference DRL algorithm implementations and effective hyper-parameter settings. Extensive evaluation results show that RLzoo not only outperforms existing DRL libraries in its simplicity of API design; but also provides the largest number of reference DRL algorithm implementations.
[8]：On the Tractability of SHAP Explanations
标题：论形解释的可操作性
作者：Guy Van den Broeck, Anton Lykov, Maximilian Schleich, Dan Suciu
链接：https://arxiv.org/abs/2009.08634
摘要：SHAP explanations are a popular feature-attribution mechanism for explainable AI. They use game-theoretic notions to measure the influence of individual features on the prediction of a machine learning model. Despite a lot of recent interest from both academia and industry, it is not known whether SHAP explanations of common machine learning models can be computed efficiently. In this paper, we establish the complexity of computing the SHAP explanation in three important settings. First, we consider fully-factorized data distributions, and show that the complexity of computing the SHAP explanation is the same as the complexity of computing the expected value of the model. This fully-factorized setting is often used to simplify the SHAP computation, yet our results show that the computation can be intractable for commonly used models such as logistic regression. Going beyond fully-factorized distributions, we show that computing SHAP explanations is already intractable for a very simple setting: computing SHAP explanations of trivial classifiers over naive Bayes distributions. Finally, we show that even computing SHAP over the empirical distribution is #P-hard.
[9]：Conditional Hybrid GAN for Sequence Generation
标题：用于序列产生的条件混合GAN
作者：Yi Yu, Abhishek Srivastava, Rajiv Ratn Shah
链接：https://arxiv.org/abs/2009.08616
摘要：Conditional sequence generation aims to instruct the generation procedure by conditioning the model with additional context information, which is a self-supervised learning issue (a form of unsupervised learning with supervision information from data itself). Unfortunately, the current state-of-the-art generative models have limitations in sequence generation with multiple attributes. In this paper, we propose a novel conditional hybrid GAN (C-Hybrid-GAN) to solve this issue. Discrete sequence with triplet attributes are separately generated when conditioned on the same context. Most importantly, relational reasoning technique is exploited to model not only the dependency inside each sequence of the attribute during the training of the generator but also the consistency among the sequences of attributes during the training of the discriminator. To avoid the non-differentiability problem in GANs encountered during discrete data generation, we exploit the Gumbel-Softmax technique to approximate the distribution of discrete-valued sequences.Through evaluating the task of generating melody (associated with note, duration, and rest) from lyrics, we demonstrate that the proposed C-Hybrid-GAN outperforms the existing methods in context-conditioned discrete-valued sequence generation.
[10]：Towards Behavior-Level Explanation for Deep Reinforcement Learning
标题：深层强化学习的行为层面解释
作者：Xuan Chen, Zifan Wang, Yucai Fan, Bonan Jin, Piotr Mardziel, Carlee Joe-Wong, Anupam Datta
链接：https://arxiv.org/abs/2009.08507
摘要：While Deep Neural Networks (DNNs) are becoming the state-of-the-art for many tasks including reinforcement learning (RL), they are especially resistant to human scrutiny and understanding. Input attributions have been a foundational building block for DNN expalainabilty but face new challenges when applied to deep RL. We address the challenges with two novel techniques. We define a class of \emph{behaviour-level attributions} for explaining agent behaviour beyond input importance and interpret existing attribution methods on the behaviour level. We then introduce \emph{$\lambda$-alignment}, a metric for evaluating the performance of behaviour-level attributions methods in terms of whether they are indicative of the agent actions they are meant to explain. Our experiments on Atari games suggest that perturbation-based attribution methods are significantly more suitable to deep RL than alternatives from the perspective of this metric. We argue that our methods demonstrate the minimal set of considerations for adopting general DNN explanation technology to the unique aspects of reinforcement learning and hope the outlined direction can serve as a basis for future research on understanding Deep RL using attribution.
[11]：GRAC: Self-Guided and Self-Regularized Actor-Critic
标题：自我引导和自我规范的演员评论家
作者：Lin Shao, Yifan You, Mengyuan Yan, Qingyun Sun, Jeannette Bohg
链接：https://arxiv.org/abs/2009.08973
摘要：Deep reinforcement learning (DRL) algorithms have successfully been demonstrated on a range of challenging decision making and control tasks. One dominant component of recent deep reinforcement learning algorithms is the target network which mitigates the divergence when learning the Q function. However, target networks can slow down the learning process due to delayed function updates. Another dominant component especially in continuous domains is the policy gradient method which models and optimizes the policy directly. However, when Q functions are approximated with neural networks, their landscapes can be complex and therefore mislead the local gradient. In this work, we propose a self-regularized and self-guided actor-critic method. We introduce a self-regularization term within the TD-error minimization and remove the need for the target network. In addition, we propose a self-guided policy improvement method by combining policy-gradient with zero-order optimization such as the Cross Entropy Method. It helps to search for actions associated with higher Q-values in a broad neighborhood and is robust to local noise in the Q function approximation. These actions help to guide the updates of our actor network. We evaluate our method on the suite of OpenAI gym tasks, achieving or outperforming state of the art in every environment tested.
[12]：Boosting Retailer Revenue by Generated Optimized Combined Multiple Digital Marketing Campaigns
标题：通过优化组合多个数字营销活动提高零售商收入
作者：Yafei Xu, Tian Xie, Yu Zhang
链接：https://arxiv.org/abs/2009.08949
摘要：Campaign is a frequently employed instrument in lifting up the GMV (Gross Merchandise Volume) of retailer in traditional marketing. As its counterpart in online context, digital-marketing-campaign (DMC) has being trending in recent years with the rapid development of the e-commerce. However, how to empower massive sellers on the online retailing platform the capacity of applying combined multiple digital marketing campaigns to boost their shops' revenue, is still a novel topic. In this work, a comprehensive solution of generating optimized combined multiple DMCs is presented. Firstly, a potential personalized DMC pool is generated for every retailer by a newly proposed neural network model, i.e. the DMCNet (Digital-Marketing-Campaign Net). Secondly, based on the sub-modular optimization theory and the DMC pool by DMCNet, the generated combined multiple DMCs are ranked with respect to their revenue generation strength then the top three ranked campaigns are returned to the sellers' back-end management system, so that retailers can set combined multiple DMCs for their online shops just in one-shot. Real online A/B-test shows that with the integrated solution, sellers of the online retailing platform increase their shops' GMVs with approximately 6$\%$.
[13]：Spatio-Temporal Activation Function To Map Complex Dynamical Systems
标题：映射复杂动力系统的时空激活函数
作者：Parth Mahendra
备注：6 pages, 11 figures
链接：https://arxiv.org/abs/2009.08931
摘要：Most of the real world is governed by complex and chaotic dynamical systems. All of these dynamical systems pose a challenge in modelling them using neural networks. Currently, reservoir computing, which is a subset of recurrent neural networks, is actively used to simulate complex dynamical systems. In this work, a two dimensional activation function is proposed which includes an additional temporal term to impart dynamic behaviour on its output. The inclusion of a temporal term alters the fundamental nature of an activation function, it provides capability to capture the complex dynamics of time series data without relying on recurrent neural networks.
[14]：HTMRL: Biologically Plausible Reinforcement Learning with Hierarchical Temporal Memory
标题：HTMRL：具有层次时间记忆的生物学似然强化学习
作者：Jakob Struye, Kevin Mets, Steven Latré
链接：https://arxiv.org/abs/2009.08880
摘要：Building Reinforcement Learning (RL) algorithms which are able to adapt to continuously evolving tasks is an open research challenge. One technology that is known to inherently handle such non-stationary input patterns well is Hierarchical Temporal Memory (HTM), a general and biologically plausible computational model for the human neocortex. As the RL paradigm is inspired by human learning, HTM is a natural framework for an RL algorithm supporting non-stationary environments. In this paper, we present HTMRL, the first strictly HTM-based RL algorithm. We empirically and statistically show that HTMRL scales to many states and actions, and demonstrate that HTM's ability for adapting to changing patterns extends to RL. Specifically, HTMRL performs well on a 10-armed bandit after 750 steps, but only needs a third of that to adapt to the bandit suddenly shuffling its arms. HTMRL is the first iteration of a novel RL approach, with the potential of extending to a capable algorithm for Meta-RL.
[15]：PANDA: Predicting the change in proteins binding affinity upon mutations using sequence information
标题：PANDA：利用序列信息预测突变后蛋白质结合亲和力的变化
作者：Wajid Arshad Abbasi, Syed Ali Abbas, Saiqa Andleeb
链接：https://arxiv.org/abs/2009.08869
摘要：Accurately determining a change in protein binding affinity upon mutations is important for the discovery and design of novel therapeutics and to assist mutagenesis studies. Determination of change in binding affinity upon mutations requires sophisticated, expensive, and time-consuming wet-lab experiments that can be aided with computational methods. Most of the computational prediction techniques require protein structures that limit their applicability to protein complexes with known structures. In this work, we explore the sequence-based prediction of change in protein binding affinity upon mutation. We have used protein sequence information instead of protein structures along with machine learning techniques to accurately predict the change in protein binding affinity upon mutation. Our proposed sequence-based novel change in protein binding affinity predictor called PANDA gives better accuracy than existing methods over the same validation set as well as on an external independent test dataset. On an external test dataset, our proposed method gives a maximum Pearson correlation coefficient of 0.52 in comparison to the state-of-the-art existing protein structure-based method called MutaBind which gives a maximum Pearson correlation coefficient of 0.59. Our proposed protein sequence-based method, to predict a change in binding affinity upon mutations, has wide applicability and comparable performance in comparison to existing protein structure-based methods. A cloud-based webserver implementation of PANDA and its python code is available atthis https URLandthis https URL.
[16]：Counterfactual Explanation and Causal Inference in Service of Robustness in Robot Control
标题：机器人控制鲁棒性的反事实解释和因果推理
作者：Simón C. Smith, Subramanian Ramamoorthy
备注：8 pages, 11 figures. To be published in the 10th IEEE International Conference on Development and Learning (ICDL), Valparaiso, Chile
链接：https://arxiv.org/abs/2009.08856
摘要：We propose an architecture for training generative models of counterfactual conditionals of the form, 'can we modify event A to cause B instead of C?', motivated by applications in robot control. Using an 'adversarial training' paradigm, an image-based deep neural network model is trained to produce small and realistic modifications to an original image in order to cause user-defined effects. These modifications can be used in the design process of image-based robust control - to determine the ability of the controller to return to a working regime by modifications in the input space, rather than by adaptation. In contrast to conventional control design approaches, where robustness is quantified in terms of the ability to reject noise, we explore the space of counterfactuals that might cause a certain requirement to be violated, thus proposing an alternative model that might be more expressive in certain robotics applications. So, we propose the generation of counterfactuals as an approach to explanation of black-box models and the envisioning of potential movement paths in autonomous robotic control. Firstly, we demonstrate this approach in a set of classification tasks, using the well known MNIST and CelebFaces Attributes datasets. Then, addressing multi-dimensional regression, we demonstrate our approach in a reaching task with a physical robot, and in a navigation task with a robot in a digital twin simulation.
[17]：Multi-source Data Mining for e-Learning
标题：面向e-Learning的多源数据挖掘
作者：Julie Bu Daher, Armelle Brun, Anne Boyer
链接：https://arxiv.org/abs/2009.08791
摘要：Data mining is the task of discovering interesting, unexpected or valuable structures in large datasets and transforming them into an understandable structure for further use . Different approaches in the domain of data mining have been proposed, among which pattern mining is the most important one. Pattern mining mining involves extracting interesting frequent patterns from data. Pattern mining has grown to be a topic of high interest where it is used for different purposes, for example, recommendations. Some of the most common challenges in this domain include reducing the complexity of the process and avoiding the redundancy within the patterns. So far, pattern mining has mainly focused on the mining of a single data source. However, with the increase in the amount of data, in terms of volume, diversity of sources and nature of data, mining multi-source and heterogeneous data has become an emerging challenge in this domain. This challenge is the main focus of our work where we propose to mine multi-source data in order to extract interesting frequent patterns.
[18]：A Visual Language for Composable Inductive Programming
标题：可组合归纳程序设计的可视化语言
作者：Edward McDaid, Sarah McDaid
备注：10 pages, 4 figures
链接：https://arxiv.org/abs/2009.08700
摘要：We present Zoea Visual which is a visual programming language based on the Zoea composable inductive programming language. Zoea Visual allows users to create software directly from a specification that resembles a set of functional test cases. Programming with Zoea Visual involves the definition of a data flow model of test case inputs, optional intermediate values, and outputs. Data elements are represented visually and can be combined to create structures of any complexity. Data flows between elements provide additional information that allows the Zoea compiler to generate larger programs in less time. This paper includes an overview of the language. The benefits of the approach and some possible future enhancements are also discussed.
[19]：A Contraction Approach to Model-based Reinforcement Learning
标题：基于模型的强化学习的收缩方法
作者：Ting-Han Fan, Peter J. Ramadge
链接：https://arxiv.org/abs/2009.08586
摘要：Model-based Reinforcement Learning has shown considerable experimental success. However, a theoretical understanding of it is still lacking. To this end, we analyze the error in cumulative reward for both stochastic and deterministic transitions using a contraction approach. We show that this approach doesn't require strong assumptions and can recover the typical quadratic error to the horizon. We prove that branched rollouts can reduce this error and are essential for deterministic transitions to have a Bellman contraction. Our results also apply to Imitation Learning, where we prove that GAN-type learning is better than Behavioral Cloning in continuous state and action spaces.
[20]：Deep Learning & Software Engineering: State of Research and Future Directions
标题：深度学习与软件工程：研究现状与发展方向
作者：Prem Devanbu, Matthew Dwyer, Sebastian Elbaum, Michael Lowry, Kevin Moran, Denys Poshyvanyk, Baishakhi Ray, Rishabh Singh, Xiangyu Zhang
备注：Community Report from the 2019 NSF Workshop on Deep Learning & Software Engineering, 37 pages
链接：https://arxiv.org/abs/2009.08525
摘要：Given the current transformative potential of research that sits at the intersection of Deep Learning (DL) and Software Engineering (SE), an NSF-sponsored community workshop was conducted in co-location with the 34th IEEE/ACM International Conference on Automated Software Engineering (ASE'19) in San Diego, California. The goal of this workshop was to outline high priority areas for cross-cutting research. While a multitude of exciting directions for future work were identified, this report provides a general summary of the research areas representing the areas of highest priority which were discussed at the workshop. The intent of this report is to serve as a potential roadmap to guide future work that sits at the intersection of SE & DL.
[21]：Online Semi-Supervised Learning in Contextual Bandits with Episodic Reward
标题：基于情景奖励的情境土匪在线半监督学习
作者：Baihan Lin
备注：AJCAI 2020. This article supersedes our workarXiv:1802.00981on contextual bandits in nonstationary setting, introduces a new problem setting with episodically revealed reward, and provides a novel solution by propagating pseudo-feedbacks to un-rewarded cases from self-supervision
链接：https://arxiv.org/abs/2009.08457
摘要：We considered a novel practical problem of online learning with episodically revealed rewards, motivated by several real-world applications, where the contexts are nonstationary over different episodes and the reward feedbacks are not always available to the decision making agents. For this online semi-supervised learning setting, we introduced Background Episodic Reward LinUCB (BerlinUCB), a solution that easily incorporates clustering as a self-supervision module to provide useful side information when rewards are not observed. Our experiments on a variety of datasets, both in stationary and nonstationary environments of six different scenarios, demonstrated clear advantages of the proposed approach over the standard contextual bandit. Lastly, we introduced a relevant real-life example where this problem setting is especially useful.CV方向重复(3篇)
[1]：Commands 4 Autonomous Vehicles (C4AV) Workshop Summary
标题：指挥部4辆自动驾驶车辆（C4AV）车间总结
作者：Thierry Deruyttere, Simon Vandenhende, Dusan Grujicic, Yu Liu, Luc Van Gool, Matthew Blaschko, Tinne Tuytelaars, Marie-Francine Moens
链接：https://arxiv.org/abs/2009.08792
摘要：The task of visual grounding requires locating the most relevant region or object in an image, given a natural language query. So far, progress on this task was mostly measured on curated datasets, which are not always representative of human spoken language. In this work, we deviate from recent, popular task settings and consider the problem under an autonomous vehicle scenario. In particular, we consider a situation where passengers can give free-form natural language commands to a vehicle which can be associated with an object in the street scene. To stimulate research on this topic, we have organized the \emph{Commands for Autonomous Vehicles} (C4AV) challenge based on the recent \emph{Talk2Car} dataset (URL:this https URL). This paper presents the results of the challenge. First, we compare the used benchmark against existing datasets for visual grounding. Second, we identify the aspects that render top-performing models successful, and relate them to existing state-of-the-art models for visual grounding, in addition to detecting potential failure cases by evaluating on carefully selected subsets. Finally, we discuss several possibilities for future work.
[2]：Contextual Semantic Interpretability
标题：语境语义可解释性
作者：Diego Marcos, Ruth Fong, Sylvain Lobry, Remi Flamary, Nicolas Courty, Devis Tuia
链接：https://arxiv.org/abs/2009.08720
摘要：Convolutional neural networks (CNN) are known to learn an image representation that captures concepts relevant to the task, but do so in an implicit way that hampers model interpretability. However, one could argue that such a representation is hidden in the neurons and can be made explicit by teaching the model to recognize semantically interpretable attributes that are present in the scene. We call such an intermediate layer a \emph{semantic bottleneck}. Once the attributes are learned, they can be re-combined to reach the final decision and provide both an accurate prediction and an explicit reasoning behind the CNN decision. In this paper, we look into semantic bottlenecks that capture context: we want attributes to be in groups of a few meaningful elements and participate jointly to the final decision. We use a two-layer semantic bottleneck that gathers attributes into interpretable, sparse groups, allowing them contribute differently to the final output depending on the context. We test our contextual semantic interpretable bottleneck (CSIB) on the task of landscape scenicness estimation and train the semantic interpretable bottleneck using an auxiliary database (SUN Attributes). Our model yields in predictions as accurate as a non-interpretable baseline when applied to a real-world test set of Flickr images, all while providing clear and interpretable explanations for each prediction.
[3]：The Next Big Thing(s) in Unsupervised Machine Learning: Five Lessons from Infant Learning
标题：无监督机器学习的下一件大事：婴儿学习的五个教训
作者：Lorijn Zaadnoordijk, Tarek R. Besold, Rhodri Cusack
链接：https://arxiv.org/abs/2009.08497
摘要：After a surge in popularity of supervised Deep Learning, the desire to reduce the dependence on curated, labelled data sets and to leverage the vast quantities of unlabelled data available recently triggered renewed interest in unsupervised learning algorithms. Despite a significantly improved performance due to approaches such as the identification of disentangled latent representations, contrastive learning, and clustering optimisations, the performance of unsupervised machine learning still falls short of its hypothesised potential. Machine learning has previously taken inspiration from neuroscience and cognitive science with great success. However, this has mostly been based on adult learners with access to labels and a vast amount of prior knowledge. In order to push unsupervised machine learning forward, we argue that developmental science of infant cognition might hold the key to unlocking the next generation of unsupervised learning approaches. Conceptually, human infant learning is the closest biological parallel to artificial unsupervised learning, as infants too must learn useful representations from unlabelled data. In contrast to machine learning, these new representations are learned rapidly and from relatively few examples. Moreover, infants learn robust representations that can be used flexibly and efficiently in a number of different tasks and contexts. We identify five crucial factors enabling infants' quality and speed of learning, assess the extent to which these have already been exploited in machine learning, and propose how further adoption of these factors can give rise to previously unseen performance levels in unsupervised learning.NLP方向重复(4篇)
[1]：SciBERT-based Semantification of Bioassays in the Open Research Knowledge Graph
标题：开放式研究知识图中基于SciBERT的生物测试语义化
作者：Marco Anteghini, Jennifer D'Souza, Vitor A. P. Martins dos Santos, Sören Auer
备注：In proceedings of the '22nd International Conference on Knowledge Engineering and Knowledge Management' 'Demo and Poster section'
链接：https://arxiv.org/abs/2009.08801
摘要：As a novel contribution to the problem of semantifying biological assays, in this paper, we propose a neural-network-based approach to automatically semantify, thereby structure, unstructured bioassay text descriptions. Experimental evaluations, to this end, show promise as the neural-based semantification significantly outperforms a naive frequency-based baseline approach. Specifically, the neural method attains 72% F1 versus 47% F1 from the frequency-based method.
[2]：RECON: Relation Extraction using Knowledge Graph Context in a Graph Neural Network
标题：RECON：图神经网络中基于知识图上下文的关系抽取
作者：Anson Bastos, Abhishek Nadgeri, Kuldeep Singh, Isaiah Onando Mulang', Saeedeh Shekarpour, Johannes Hoffart
备注：under review
链接：https://arxiv.org/abs/2009.08694
摘要：In this paper, we present a novel method named RECON, that automatically identifies relations in a sentence (sentential relation extraction) and aligns to a knowledge graph (KG). RECON uses a graph neural network to learn representations of both the sentence as well as facts stored in a KG, improving the overall extraction quality. These facts, including entity attributes (label, alias, description, instance-of) and factual triples, have not been collectively used in the state of the art methods. We evaluate the effect of various forms of representing the KG context on the performance of RECON. The empirical evaluation on two standard relation extraction datasets shows that RECON significantly outperforms all state of the art methods on NYT Freebase and Wikidata datasets. RECON reports 87.23 F1 score (Vs 82.29 baseline) on Wikidata dataset whereas on NYT Freebase, reported values are 87.5(P@10) and 74.1(P@30) compared to the previous baseline scores of 81.3(P@10) and 63.1(P@30).
[3]：Dr. Summarize: Global Summarization of Medical Dialogue by Exploiting Local Structures
标题：医生总结：利用局部结构对医学对话进行全球总结
作者：Anirudh Joshi, Namit Katariya, Xavier Amatriain, Anitha Kannan
备注：Accepted for publication in Findings of EMNLP at EMNLP 2020
链接：https://arxiv.org/abs/2009.08666
摘要：Understanding a medical conversation between a patient and a physician poses a unique natural language understanding challenge since it combines elements of standard open ended conversation with very domain specific elements that require expertise and medical knowledge. Summarization of medical conversations is a particularly important aspect of medical conversation understanding since it addresses a very real need in medical practice: capturing the most important aspects of a medical encounter so that they can be used for medical decision making and subsequent follow ups.
In this paper we present a novel approach to medical conversation summarization that leverages the unique and independent local structures created when gathering a patient's medical history. Our approach is a variation of the pointer generator network where we introduce a penalty on the generator distribution, and we explicitly model negations. The model also captures important properties of medical conversations such as medical knowledge coming from standardized medical ontologies better than when those concepts are introduced explicitly. Through evaluation by doctors, we show that our approach is preferred on twice the number of summaries to the baseline pointer generator model and captures most or all of the information in 80% of the conversations making it a realistic alternative to costly manual summarization by medical experts.
[4]：Structured Attention for Unsupervised Dialogue Structure Induction
标题：无监督对话结构归纳的结构注意
作者：Liang Qiu, Yizhou Zhao, Weiyan Shi, Yuan Liang, Feng Shi, Tao Yuan, Zhou Yu, Song-Chun Zhu
备注：Long paper accepted by EMNLP 2020
链接：https://arxiv.org/abs/2009.08552
摘要：Inducing a meaningful structural representation from one or a set of dialogues is a crucial but challenging task in computational linguistics. Advancement made in this area is critical for dialogue system design and discourse analysis. It can also be extended to solve grammatical inference. In this work, we propose to incorporate structured attention layers into a Variational Recurrent Neural Network (VRNN) model with discrete latent states to learn dialogue structure in an unsupervised fashion. Compared to a vanilla VRNN, structured attention enables a model to focus on different parts of the source sentence embeddings while enforcing a structural inductive bias. Experiments show that on two-party dialogue datasets, VRNN with structured attention learns semantic structures that are similar to templates used to generate this dialogue corpus. While on multi-party dialogue datasets, our model learns an interactive structure demonstrating its capability of distinguishing speakers or addresses, automatically disentangling dialogues without explicit human annotation.中文来自机器翻译，仅供参考。
