今日 cs.AI方向共计43篇文章。

Artificial Intelligence(24篇)

[1]：Investment vs. reward in a competitive knapsack problem
标题：竞争背包问题中的投资与报酬
作者：Oren Neumann, Claudius Gros
链接：https://arxiv.org/abs/2101.10964
摘要：Natural selection drives species to develop brains, with sizes that increase with the complexity of the tasks to be tackled. Our goal is to investigate the balance between the metabolic costs of larger brains compared to the advantage they provide in solving general and combinatorial problems. Defining advantage as the performance relative to competitors, a two-player game based on the knapsack problem is used. Within this framework, two opponents compete over shared resources, with the goal of collecting more resources than the opponent. Neural nets of varying sizes are trained using a variant of the AlphaGo Zero algorithm. A surprisingly simple relation, $N_A/(N_A+N_B)$, is found for the relative win rate of a net with $N_A$ neurons against one with $N_B$. Success increases linearly with investments in additional resources when the networks sizes are very different, i.e. when $N_A \ll N_B$, with returns diminishing when both networks become comparable in size.[2]：Ordinal Monte Carlo Tree Search
标题：有序蒙特卡罗树搜索
作者：Tobias Joppen, Johannes Fürnkranz
备注：preprint. arXiv admin note: substantial text overlap witharXiv:1901.04274
链接：https://arxiv.org/abs/2101.10670
摘要：In many problem settings, most notably in game playing, an agent receives a possibly delayed reward for its actions. Often, those rewards are handcrafted and not naturally given. Even simple terminal-only rewards, like winning equals one and losing equals minus one, can not be seen as an unbiased statement, since these values are chosen arbitrarily, and the behavior of the learner may change with different encodings. It is hard to argue about good rewards and the performance of an agent often depends on the design of the reward signal. In particular, in domains where states by nature only have an ordinal ranking and where meaningful distance information between game state values is not available, a numerical reward signal is necessarily biased. In this paper we take a look at MCTS, a popular algorithm to solve MDPs, highlight a reoccurring problem concerning its use of rewards, and show that an ordinal treatment of the rewards overcomes this problem. Using the General Video Game Playing framework we show dominance of our newly proposed ordinal MCTS algorithm over other MCTS variants, based on a novel bandit algorithm that we also introduce and test versus UCB.[3]：How do some Bayesian Network machine learned graphs compare to causal  knowledge?
标题：一些贝叶斯网络机器学习图与因果知识相比如何？
作者：Anthony C. Constantinou, Norman Fenton, Martin Neil
链接：https://arxiv.org/abs/2101.10461
摘要：The graph of a BN can be machine learned, determined by causal knowledge, or a combination of both. In disciplines like bioinformatics, applying BN structure learning algorithms can reveal new insights that would otherwise remain unknown. However, these algorithms are less effective when the input data are limited in terms of sample size, which is often the case when working with real data. This paper focuses on purely machine learned and purely knowledge-based BNs and investigates their differences in terms of graphical structure and how well the implied statistical models explain the data. The tests are based on four previous case studies that had their BN structure determined by domain knowledge. Using various metrics, we compare the knowledge-based graphs to the machine learned graphs generated from various algorithms implemented in TETRAD spanning all three classes of learning. The results show that while the algorithms are much better at arriving at a graph with a high model selection score, the parameterised models obtained from those graphs tend to be poor predictors of variables of interest, relative to the corresponding inferences obtained from the knowledge-based graphs. Amongst our conclusions is that structure learning is ineffective in the presence of limited sample size relative to model dimensionality, which can be explained by model fitting becoming increasingly distorted under these conditions; essentially rendering ground truth graphs inaccurate by guiding algorithms towards graphical patterns that may share higher evaluation scores and yet deviate further from the ground truth graph. This highlights the value of causal knowledge in these cases, as well as the need for more appropriate model selection scores. Lastly, the experiments also provide new evidence that support the notion that results from simulated data tell us little about actual real-world performance.[4]：Predicting the future with a scale-invariant temporal memory for the  past
标题：用尺度不变的过去时间记忆预测未来
作者：Wei Zhong Goh, Varun Ursekar, Marc W. Howard
备注：28 pages, 9 figures
链接：https://arxiv.org/abs/2101.10953
摘要：In recent years it has become clear that the brain maintains a temporal memory of recent events stretching far into the past. This paper presents a neurally-inspired algorithm to use a scale-invariant temporal representation of the past to predict a scale-invariant future. The result is a scale-invariant estimate of future events as a function of the time at which they are expected to occur. The algorithm is time-local, with credit assigned to the present event by observing how it affects the prediction of the future. To illustrate the potential utility of this approach, we test the model on simultaneous renewal processes with different time scales. The algorithm scales well on these problems despite the fact that the number of states needed to describe them as a Markov process grows exponentially.[5]：Multimedia Respiratory Database (RespiratoryDatabase@TR): Auscultation  Sounds and Chest X-rays
标题：多媒体呼吸数据库(呼吸器数据库@TR)：听诊音和胸部X光片
作者：Gokhan Altan, Yakup Kutlu, Yusuf Garbi, Adnan Ozhan Pekmezci, Serkan Nural
备注：14 pages, 7 figures, Natural and Engineering Sciences
链接：https://arxiv.org/abs/2101.10946
摘要：Auscultation is a method for diagnosis of especially internal medicine diseases such as cardiac, pulmonary and cardio-pulmonary by listening the internal sounds from the body parts. It is the simplest and the most common physical examination in the assessment processes of the clinical skills. In this study, the lung and heart sounds are recorded synchronously from left and right sides of posterior and anterior chest wall and back using two digital stethoscopes in Antakya State Hospital. The chest X-rays and the pulmonary function test variables and spirometric curves, the St. George respiratory questionnaire (SGRQ-C) are collected as multimedia and clinical functional analysis variables of the patients. The 4 channels of heart sounds are focused on aortic, pulmonary, tricuspid and mitral areas. The 12 channels of lung sounds are focused on upper lung, middle lung, lower lung and costophrenic angle areas of posterior and anterior sides of the chest. The recordings are validated and labelled by two pulmonologists evaluating the collected chest x-ray, PFT and auscultation sounds of the subjects. The database consists of 30 healthy subjects and 45 subjects with pulmonary diseases such as asthma, chronic obstructive pulmonary disease, bronchitis. The novelties of the database are the combination ability between auscultation sound results, chest X-ray and PFT; synchronously assessment capability of the lungs sounds; image processing based computerized analysis of the respiratory using chest X-ray and providing opportunity for improving analysis of both lung sounds and heart sounds on pulmonary and cardiac diseases.[6]：Untargeted Poisoning Attack Detection in Federated Learning via Behavior  Attestation
标题：基于行为证明的联邦学习中非目标中毒攻击检测
作者：Ranwa Al Mallah, David Lopez, Bilal Farooq
链接：https://arxiv.org/abs/2101.10904
摘要：Federated Learning (FL) is a paradigm in Machine Learning (ML) that addresses data privacy, security, access rights and access to heterogeneous information issues by training a global model using distributed nodes. Despite its advantages, there is an increased potential for cyberattacks on FL-based ML techniques that can undermine the benefits. Model-poisoning attacks on FL target the availability of the model. The adversarial objective is to disrupt the training. We propose attestedFL, a defense mechanism that monitors the training of individual nodes through state persistence in order to detect a malicious worker. A fine-grained assessment of the history of the worker permits the evaluation of its behavior in time and results in innovative detection strategies. We present three lines of defense that aim at assessing if the worker is reliable by observing if the node is really training, advancing towards a goal. Our defense exposes an attacker's malicious behavior and removes unreliable nodes from the aggregation process so that the FL process converge faster. Through extensive evaluations and against various adversarial settings, attestedFL increased the accuracy of the model between 12% to 58% under different scenarios such as attacks performed at different stages of convergence, attackers colluding and continuous attacks.[7]：Artificial Intelligence for Satellite Communication: A Review
标题：卫星通信人工智能综述
作者：Fares Fourati, Mohamed-Slim Alouini
链接：https://arxiv.org/abs/2101.10899
摘要：Satellite communication offers the prospect of service continuity over uncovered and under-covered areas, service ubiquity, and service scalability. However, several challenges must first be addressed to realize these benefits, as the resource management, network control, network security, spectrum management, and energy usage of satellite networks are more challenging than that of terrestrial networks. Meanwhile, artificial intelligence (AI), including machine learning, deep learning, and reinforcement learning, has been steadily growing as a research field and has shown successful results in diverse applications, including wireless communication. In particular, the application of AI to a wide variety of satellite communication aspects have demonstrated excellent potential, including beam-hopping, anti-jamming, network traffic forecasting, channel modeling, telemetry mining, ionospheric scintillation detecting, interference managing, remote sensing, behavior modeling, space-air-ground integrating, and energy managing. This work thus provides a general overview of AI, its diverse sub-fields, and its state-of-the-art algorithms. Several challenges facing diverse aspects of satellite communication systems are then discussed, and their proposed and potential AI-based solutions are presented. Finally, an outlook of field is drawn, and future steps are suggested.[8]：B-HAR: an open-source baseline framework for in depth study of human  activity recognition datasets and workflows
标题：B-HAR：一个用于深入研究人类活动识别数据集和工作流的开源基线框架
作者：Florenc Demrozi, Cristian Turetta, Graziano Pravadelli
备注：9 Pages, 3 Figures, 3 Tables, Link to B-HAR Library:this https URL
链接：https://arxiv.org/abs/2101.10870
摘要：Human Activity Recognition (HAR), based on machine and deep learning algorithms is considered one of the most promising technologies to monitor professional and daily life activities for different categories of people (e.g., athletes, elderly, kids, employers) in order to provide a variety of services related, for example to well-being, empowering of technical performances, prevention of risky situation, and educational purposes. However, the analysis of the effectiveness and the efficiency of HAR methodologies suffers from the lack of a standard workflow, which might represent the baseline for the estimation of the quality of the developed pattern recognition models. This makes the comparison among different approaches a challenging task. In addition, researchers can make mistakes that, when not detected, definitely affect the achieved results. To mitigate such issues, this paper proposes an open-source automatic and highly configurable framework, named B-HAR, for the definition, standardization, and development of a baseline framework in order to evaluate and compare HAR methodologies. It implements the most popular data processing methods for data preparation and the most commonly used machine and deep learning pattern recognition models.[9]：On managing vulnerabilities in AI/ML systems
标题：论AI/ML系统中的漏洞管理
作者：Jonathan M. Spring, April Galyardt, Allen D. Householder, Nathan VanHoudnos
备注：16 pages. New Security Paradigms Workshop
链接：https://arxiv.org/abs/2101.10865
摘要：This paper explores how the current paradigm of vulnerability management might adapt to include machine learning systems through a thought experiment: what if flaws in machine learning (ML) were assigned Common Vulnerabilities and Exposures (CVE) identifiers (CVE-IDs)? We consider both ML algorithms and model objects. The hypothetical scenario is structured around exploring the changes to the six areas of vulnerability management: discovery, report intake, analysis, coordination, disclosure, and response. While algorithm flaws are well-known in the academic research community, there is no apparent clear line of communication between this research community and the operational communities that deploy and manage systems that use ML. The thought experiments identify some ways in which CVE-IDs may establish some useful lines of communication between these two communities. In particular, it would start to introduce the research community to operational security concepts, which appears to be a gap left by existing efforts.[10]：Toxicity Detection in Drug Candidates using Simplified Molecular-Input  Line-Entry System
标题：用简化的分子输入线输入系统检测候选药物的毒性
作者：Mriganka Nath, Subhasish Goswami
备注：4 Pages, 4 Figures, Published with International Journal of Computer Applications (IJCA)
链接：https://arxiv.org/abs/2101.10831
摘要：The need for analysis of toxicity in new drug candidates and the requirement of doing it fast have asked the consideration of scientists towards the use of artificial intelligence tools to examine toxicity levels and to develop models to a degree where they can be used commercially to measure toxicity levels efficiently in upcoming drugs. Artificial Intelligence based models can be used to predict the toxic nature of a chemical using Quantitative Structure Activity Relationship techniques. Convolutional Neural Network models have demonstrated great outcomes in predicting the qualitative analysis of chemicals in order to determine the toxicity. This paper goes for the study of Simplified Molecular Input Line-Entry System (SMILES) as a parameter to develop Long short term memory (LSTM) based models in order to examine the toxicity of a molecule and the degree to which the need can be fulfilled for practical use alongside its future outlooks for the purpose of real world applications.[11]：Impact of Explanation on Trust of a Novel Mobile Robot
标题：解释对新型移动机器人信任的影响
作者：Stephanie Rosenthal, Elizabeth J. Carter
备注：9 pages, 3 figures
链接：https://arxiv.org/abs/2101.10813
摘要：One challenge with introducing robots into novel environments is misalignment between supervisor expectations and reality, which can greatly affect a user's trust and continued use of the robot. We performed an experiment to test whether the presence of an explanation of expected robot behavior affected a supervisor's trust in an autonomous robot. We measured trust both subjectively through surveys and objectively through a dual-task experiment design to capture supervisors' neglect tolerance (i.e., their willingness to perform their own task while the robot is acting autonomously). Our objective results show that explanations can help counteract the novelty effect of seeing a new robot perform in an unknown environment. Participants who received an explanation of the robot's behavior were more likely to focus on their own task at the risk of neglecting their robot supervision task during the first trials of the robot's behavior compared to those who did not receive an explanation. However, this effect diminished after seeing multiple trials, and participants who received explanations were equally trusting of the robot's behavior as those who did not receive explanations. Interestingly, participants were not able to identify their own changes in trust through their survey responses, demonstrating that the dual-task design measured subtler changes in a supervisor's trust.[12]：The Consequences of the Framing of Machine Learning Risk Prediction  Models: Evaluation of Sepsis in General Wards
标题：建立机器学习风险预测模型的后果：普通病房脓毒症的评估
作者：Simon Meyer Lauritsen, Bo Thiesson, Marianne Johansson Jørgensen, Anders Hammerich Riis, Ulrick Skipper Espelund, Jesper Bo Weile, Jeppe Lange
链接：https://arxiv.org/abs/2101.10790
摘要：Objectives: To evaluate the consequences of the framing of machine learning risk prediction models. We evaluate how framing affects model performance and model learning in four different approaches previously applied in published artificial-intelligence (AI) models.
Setting and participants: We analysed structured secondary healthcare data from 221,283 citizens from four Danish municipalities who were 18 years of age or older.
Results: The four models had similar population level performance (a mean area under the receiver operating characteristic curve of 0.73 to 0.82), in contrast to the mean average precision, which varied greatly from 0.007 to 0.385. Correspondingly, the percentage of missing values also varied between framing approaches. The on-clinical-demand framing, which involved samples for each time the clinicians made an early warning score assessment, showed the lowest percentage of missing values among the vital sign parameters, and this model was also able to learn more temporal dependencies than the others. The Shapley additive explanations demonstrated opposing interpretations of SpO2 in the prediction of sepsis as a consequence of differentially framed models.
Conclusions: The profound consequences of framing mandate attention from clinicians and AI developers, as the understanding and reporting of framing are pivotal to the successful development and clinical implementation of future AI technology. Model framing must reflect the expected clinical environment. The importance of proper problem framing is by no means exclusive to sepsis prediction and applies to most clinical risk prediction models.[13]：Dynamic prediction of time to event with survival curves
标题：用生存曲线动态预测事件发生时间
作者：Jie Zhu, Blanca Gallego
链接：https://arxiv.org/abs/2101.10739
摘要：With the ever-growing complexity of primary health care system, proactive patient failure management is an effective way to enhancing the availability of health care resource. One key enabler is the dynamic prediction of time-to-event outcomes. Conventional explanatory statistical approach lacks the capability of making precise individual level prediction, while the data adaptive binary predictors does not provide nominal survival curves for biologically plausible survival analysis. The purpose of this article is to elucidate that the knowledge of explanatory survival analysis can significantly enhance the current black-box data adaptive prediction models. We apply our recently developed counterfactual dynamic survival model (CDSM) to static and longitudinal observational data and testify that the inflection point of its estimated individual survival curves provides reliable prediction of the patient failure time.[14]：Advantages and Bottlenecks of Quantum Machine Learning for Remote  Sensing
标题：遥感量子机器学习的优势与瓶颈
作者：Daniela A. Zaidenberg, Alessandro Sebastianelli, Dario Spiller, Bertrand Le Saux, Silvia Liberata Ullo
备注：4 pages, 4 figures, submitted to IEEE IGARSS2021
链接：https://arxiv.org/abs/2101.10657
摘要：This concept paper aims to provide a brief outline of quantum computers, explore existing methods of quantum image classification techniques, so focusing on remote sensing applications, and discuss the bottlenecks of performing these algorithms on currently available open source platforms. Initial results demonstrate feasibility. Next steps include expanding the size of the quantum hidden layer and increasing the variety of output image options.[15]：CDSM -- Casual Inference using Deep Bayesian Dynamic Survival Models
标题：CDSM——基于深度贝叶斯动态生存模型的随机推理
作者：Jie Zhu, Blanca Gallego
链接：https://arxiv.org/abs/2101.10643
摘要：A smart healthcare system that supports clinicians for risk-calibrated treatment assessment typically requires the accurate modeling of time-to-event outcomes. To tackle this sequential treatment effect estimation problem, we developed causal dynamic survival model (CDSM) for causal inference with survival outcomes using longitudinal electronic health record (EHR). CDSM has impressive explanatory performance while maintaining the prediction capability of conventional binary neural network predictors. It borrows the strength from explanatory framework including the survival analysis and counterfactual framework and integrates them with the prediction power from a deep Bayesian recurrent neural network to extract implicit knowledge from EHR data. In two large clinical cohort studies, our model identified the conditional average treatment effect in accordance with previous literature yet detected individual effect heterogeneity over time and patient subgroups. The model provides individualized and clinically interpretable treatment effect estimations to improve patient outcomes.[16]：Symmetric Monoidal Categories with Attributes
标题：带属性的对称幺半群范畴
作者：Spencer Breiner, John S. Nolan
备注：In Proceedings ACT 2020,arXiv:2101.07888
链接：https://arxiv.org/abs/2101.10480
摘要：When designing plans in engineering, it is often necessary to consider attributes associated to objects, e.g. the location of a robot. Our aim in this paper is to incorporate attributes into existing categorical formalisms for planning, namely those based on symmetric monoidal categories and string diagrams. To accomplish this, we define a notion of a "symmetric monoidal category with attributes." This is a symmetric monoidal category in which objects are equipped with retrievable information and where the interactions between objects and information are governed by an "attribute structure." We discuss examples and semantics of such categories in the context of robotics to illustrate our definition.[17]：Appliance Operation Modes Identification Using Cycles Clustering
标题：基于循环聚类的家电运行模式识别
作者：Abdelkareem Jaradat, Hanan Lutfiyya, Anwar Haque
链接：https://arxiv.org/abs/2101.10472
摘要：The increasing cost, energy demand, and environmental issues has led many researchers to find approaches for energy monitoring, and hence energy conservation. The emerging technologies of Internet of Things (IoT) and Machine Learning (ML) deliver techniques that have the potential to efficiently conserve energy and improve the utilization of energy consumption. Smart Home Energy Management Systems (SHEMSs) have the potential to contribute in energy conservation through the application of Demand Response (DR) in the residential sector. In this paper, we propose appliances Operation Modes Identification using Cycles Clustering (OMICC) which is SHEMS fundamental approach that utilizes the sensed residential disaggregated power consumption in supporting DR by providing consumers the opportunity to select lighter appliance operation modes. The cycles of the Single Usage Profile (SUP) of an appliance are extracted and reformed into features in terms of clusters of cycles. These features are then used to identify the operation mode used in every occurrence using K-Nearest Neighbors (KNN). Operation modes identification is considered a basis for many potential smart DR applications within SHEMS towards the consumers or the suppliers[18]：RTGPU: Real-Time GPU Scheduling of Hard Deadline Parallel Tasks with  Fine-Grain Utilization
标题：RTGPU：具有细粒度利用的硬截止期并行任务的实时GPU调度
作者：An Zou, Jing Li, Christopher D. Gill, Xuan Zhang
链接：https://arxiv.org/abs/2101.10463
摘要：Many emerging cyber-physical systems, such as autonomous vehicles and robots, rely heavily on artificial intelligence and machine learning algorithms to perform important system operations. Since these highly parallel applications are computationally intensive, they need to be accelerated by graphics processing units (GPUs) to meet stringent timing constraints. However, despite the wide adoption of GPUs, efficiently scheduling multiple GPU applications while providing rigorous real-time guarantees remains a challenge. In this paper, we propose RTGPU, which can schedule the execution of multiple GPU applications in real-time to meet hard deadlines. Each GPU application can have multiple CPU execution and memory copy segments, as well as GPU kernels. We start with a model to explicitly account for the CPU and memory copy segments of these applications. We then consider the GPU architecture in the development of a precise timing model for the GPU kernels and leverage a technique known as persistent threads to implement fine-grained kernel scheduling with improved performance through interleaved execution. Next, we propose a general method for scheduling parallel GPU applications in real time. Finally, to schedule multiple parallel GPU applications, we propose a practical real-time scheduling algorithm based on federated scheduling and grid search (for GPU kernel segments) with uniprocessor fixed priority scheduling (for multiple CPU and memory copy segments). Our approach provides superior schedulability compared with previous work, and gives real-time guarantees to meet hard deadlines for multiple GPU applications according to comprehensive validation and evaluation on a real NVIDIA GTX1080Ti GPU system.[19]：Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate  Time Series Forecasting
标题：时间潜在自动编码器：一种概率多元时间序列预测方法
作者：Nam Nguyen, Brian Quanz
备注：Accepted at AAAI 2021 (main conference)
链接：https://arxiv.org/abs/2101.10460
摘要：Probabilistic forecasting of high dimensional multivariate time series is a notoriously challenging task, both in terms of computational burden and distribution modeling. Most previous work either makes simple distribution assumptions or abandons modeling cross-series correlations. A promising line of work exploits scalable matrix factorization for latent-space forecasting, but is limited to linear embeddings, unable to model distributions, and not trainable end-to-end when using deep learning forecasting. We introduce a novel temporal latent auto-encoder method which enables nonlinear factorization of multivariate time series, learned end-to-end with a temporal deep learning latent space forecast model. By imposing a probabilistic latent space model, complex distributions of the input series are modeled via the decoder. Extensive experiments demonstrate that our model achieves state-of-the-art performance on many popular multivariate datasets, with gains sometimes as high as $50\%$ for several standard metrics.[20]：Test and Evaluation Framework for Multi-Agent Systems of Autonomous  Intelligent Agents
标题：自主智能体多智能体系统的测试与评价框架
作者：Erin Lanus, Ivan Hernandez, Adam Dachowicz, Laura Freeman, Melanie Grande, Andrew Lang, Jitesh H. Panchal, Anthony Patrick, Scott Welch
链接：https://arxiv.org/abs/2101.10430
摘要：Test and evaluation is a necessary process for ensuring that engineered systems perform as intended under a variety of conditions, both expected and unexpected. In this work, we consider the unique challenges of developing a unifying test and evaluation framework for complex ensembles of cyber-physical systems with embedded artificial intelligence. We propose a framework that incorporates test and evaluation throughout not only the development life cycle, but continues into operation as the system learns and adapts in a noisy, changing, and contended environment. The framework accounts for the challenges of testing the integration of diverse systems at various hierarchical scales of composition while respecting that testing time and resources are limited. A generic use case is provided for illustrative purposes and research directions emerging as a result of exploring the use case via the framework are suggested.[21]：Online and Scalable Model Selection with Multi-Armed Bandits
标题：多武装土匪在线可伸缩模型选择
作者：Jiayi Xie, Michael Tashman, John Hoffman, Lee Winikor, Rouzbeh Gerami
链接：https://arxiv.org/abs/2101.10385
摘要：Many online applications running on live traffic are powered by machine learning models, for which training, validation, and hyper-parameter tuning are conducted on historical data. However, it is common for models demonstrating strong performance in offline analysis to yield poorer performance when deployed online. This problem is a consequence of the difficulty of training on historical data in non-stationary environments. Moreover, the machine learning metrics used for model selection may not sufficiently correlate with real-world business metrics used to determine the success of the applications being tested. These problems are particularly prominent in the Real-Time Bidding (RTB) domain, in which ML models power bidding strategies, and a change in models will likely affect performance of the advertising campaigns. In this work, we present Automatic Model Selector (AMS), a system for scalable online selection of RTB bidding strategies based on real-world performance metrics. AMS employs Multi-Armed Bandits (MAB) to near-simultaneously run and evaluate multiple models against live traffic, allocating the most traffic to the best-performing models while decreasing traffic to those with poorer online performance, thereby minimizing the impact of inferior models on overall campaign performance. The reliance on offline data is avoided, instead making model selections on a case-by-case basis according to actionable business goals. AMS allows new models to be safely introduced into live campaigns as soon as they are developed, minimizing the risk to overall performance. In live-traffic tests on multiple ad campaigns, the AMS system proved highly effective at improving ad campaign performance.[22]：droidlet: modular, heterogenous, multi-modal agents
标题：droidlet：模块化的、异构的、多模式的代理
作者：Anurag Pratik, Soumith Chintala, Kavya Srinet, Dhiraj Gandhi, Rebecca Qian, Yuxuan Sun, Ryan Drew, Sara Elkafrawy, Anoushka Tiwari, Tucker Hart, Mary Williamson, Abhinav Gupta, Arthur Szlam
链接：https://arxiv.org/abs/2101.10384
摘要：In recent years, there have been significant advances in building end-to-end Machine Learning (ML) systems that learn at scale. But most of these systems are: (a) isolated (perception, speech, or language only); (b) trained on static datasets. On the other hand, in the field of robotics, large-scale learning has always been difficult. Supervision is hard to gather and real world physical interactions are expensive. In this work we introduce and open-source droidlet, a modular, heterogeneous agent architecture and platform. It allows us to exploit both large-scale static datasets in perception and language and sophisticated heuristics often used in robotics; and provides tools for interactive annotation. Furthermore, it brings together perception, language and action onto one platform, providing a path towards agents that learn from the richness of real world interactions.[23]：Learning to falsify automated driving vehicles with prior knowledge
标题：学习用事先的知识伪造自动驾驶车辆
作者：Andrea Favrin, Vladislav Nenchev, Angelo Cenedese
备注：Preprint accepted at IFAC World Congress 2020, Germany
链接：https://arxiv.org/abs/2101.10377
摘要：While automated driving technology has achieved a tremendous progress, the scalable and rigorous testing and verification of safe automated and autonomous driving vehicles remain challenging. This paper proposes a learning-based falsification framework for testing the implementation of an automated or self-driving function in simulation. We assume that the function specification is associated with a violation metric on possible scenarios. Prior knowledge is incorporated to limit the scenario parameter variance and in a model-based falsifier to guide and improve the learning process. For an exemplary adaptive cruise controller, the presented framework yields non-trivial falsifying scenarios with higher reward, compared to scenarios obtained by purely learning-based or purely model-based falsification approaches.[24]：A Joint Learning and Communication Framework for Multi-Agent  Reinforcement Learning over Noisy Channels
标题：噪声信道下多智能体强化学习的联合学习与通信框架
作者：Tze-Yang Tung, Joan Roig Pujol, Szymon Kobus, Deniz Gunduz
链接：https://arxiv.org/abs/2101.10369
摘要：We propose a novel formulation of the "effectiveness problem" in communications, put forth by Shannon and Weaver in their seminal work [2], by considering multiple agents communicating over a noisy channel in order to achieve better coordination and cooperation in a multi-agent reinforcement learning (MARL) framework. Specifically, we consider a multi-agent partially observable Markov decision process (MA-POMDP), in which the agents, in addition to interacting with the environment can also communicate with each other over a noisy communication channel. The noisy communication channel is considered explicitly as part of the dynamics of the environment and the message each agent sends is part of the action that the agent can take. As a result, the agents learn not only to collaborate with each other but also to communicate "effectively" over a noisy channel. This framework generalizes both the traditional communication problem, where the main goal is to convey a message reliably over a noisy channel, and the "learning to communicate" framework that has received recent attention in the MARL literature, where the underlying communication channels are assumed to be error-free. We show via examples that the joint policy learned using the proposed framework is superior to that where the communication is considered separately from the underlying MA-POMDP. This is a very powerful framework, which has many real world applications, from autonomous vehicle planning to drone swarm control, and opens up the rich toolbox of deep reinforcement learning for the design of multi-user communication systems.

CV方向重复(9篇)

[1]：Online Body Schema Adaptation through Cost-Sensitive Active Learning
标题：基于成本敏感主动学习的在线身体图式适应
作者：Gonçalo Cunha, Pedro Vicente, Alexandre Bernardino, Ricardo Ribeiro, Plínio Moreno
备注：6 pages, 7 figures. Submitted to Humanoids 2020
链接：https://arxiv.org/abs/2101.10892
摘要：Humanoid robots have complex bodies and kinematic chains with several Degrees-of-Freedom (DoF) which are difficult to model. Learning the parameters of a kinematic model can be achieved by observing the position of the robot links during prospective motions and minimising the prediction errors. This work proposes a movement efficient approach for estimating online the body-schema of a humanoid robot arm in the form of Denavit-Hartenberg (DH) parameters. A cost-sensitive active learning approach based on the A-Optimality criterion is used to select optimal joint configurations. The chosen joint configurations simultaneously minimise the error in the estimation of the body schema and minimise the movement between samples. This reduces energy consumption, along with mechanical fatigue and wear, while not compromising the learning accuracy. The work was implemented in a simulation environment, using the 7DoF arm of the iCub robot simulator. The hand pose is measured with a single camera via markers placed in the palm and back of the robot's hand. A non-parametric occlusion model is proposed to avoid choosing joint configurations where the markers are not visible, thus preventing worthless attempts. The results show cost-sensitive active learning has similar accuracy to the standard active learning approach, while reducing in about half the executed movement.[2]：Indoor Group Activity Recognition using Multi-Layered HMMs
标题：基于多层HMMs的室内群体活动识别
作者：Vinayak Elangovan
备注：8 pages, 7 figures, 3 tables
链接：https://arxiv.org/abs/2101.10857
摘要：Discovery and recognition of Group Activities (GA) based on imagery data processing have significant applications in persistent surveillance systems, which play an important role in some Internet services. The process is involved with analysis of sequential imagery data with spatiotemporal associations. Discretion of video imagery requires a proper inference system capable of discriminating and differentiating cohesive observations and interlinking them to known ontologies. We propose an Ontology based GAR with a proper inference model that is capable of identifying and classifying a sequence of events in group activities. A multi-layered Hidden Markov Model (HMM) is proposed to recognize different levels of abstract GA. The multi-layered HMM consists of N layers of HMMs where each layer comprises of M number of HMMs running in parallel. The number of layers depends on the order of information to be extracted. At each layer, by matching and correlating attributes of detected group events, the model attempts to associate sensory observations to known ontology perceptions. This paper demonstrates and compares performance of three different implementation of HMM, namely, concatenated N-HMM, cascaded C-HMM and hybrid H-HMM for building effective multi-layered HMM.[3]：Analysis and evaluation of Deep Learning based Super-Resolution  algorithms to improve performance in Low-Resolution Face Recognition
标题：提高低分辨率人脸识别性能的深度学习超分辨率算法分析与评价
作者：Angelo G. Menezes
备注：MSc Thesis under supervision of Carlos A. E. Montesco presented at the Federal University of Sergipe, Brazil (2019)
链接：https://arxiv.org/abs/2101.10845
摘要：Surveillance scenarios are prone to several problems since they usually involve low-resolution footage, and there is no control of how far the subjects may be from the camera in the first place. This situation is suitable for the application of upsampling (super-resolution) algorithms since they may be able to recover the discriminant properties of the subjects involved. While general super-resolution approaches were proposed to enhance image quality for human-level perception, biometrics super-resolution methods seek the best "computer perception" version of the image since their focus is on improving automatic recognition performance. Convolutional neural networks and deep learning algorithms, in general, have been applied to computer vision tasks and are now state-of-the-art for several sub-domains, including image classification, restoration, and super-resolution. However, no work has evaluated the effects that the latest proposed super-resolution methods may have upon the accuracy and face verification performance in low-resolution "in-the-wild" data. This project aimed at evaluating and adapting different deep neural network architectures for the task of face super-resolution driven by face recognition performance in real-world low-resolution images. The experimental results in a real-world surveillance and attendance datasets showed that general super-resolution architectures might enhance face verification performance of deep neural networks trained on high-resolution faces. Also, since neural networks are function approximators and can be trained based on specific objective functions, the use of a customized loss function optimized for feature extraction showed promising results for recovering discriminant features in low-resolution face images.[4]：Generative Adversarial Network using Perturbed-Convolutions
标题：扰动卷积生成对抗网络
作者：Seung Park, Yoon-Jae Yeo, Yong-Goo Shin
备注：Preparation for submitting to the IEEE journal. arXiv admin note: text overlap witharXiv:1911.10979
链接：https://arxiv.org/abs/2101.10841
摘要：Despite growing insights into the GAN training, it still suffers from instability during the training procedure. To alleviate this problem, this paper presents a novel convolutional layer, called perturbed-convolution (PConv), which focuses on achieving two goals simultaneously: penalize the discriminator for training GAN stably and prevent the overfitting problem in the discriminator. PConv generates perturbed features by randomly disturbing an input tensor before performing the convolution operation. This approach is simple but surprisingly effective. First, to reliably classify real and generated samples using the disturbed input tensor, the intermediate layers in the discriminator should learn features having a small local Lipschitz value. Second, due to the perturbed features in PConv, the discriminator is difficult to memorize the real images; this makes the discriminator avoid the overfitting problem. To show the generalization ability of the proposed method, we conducted extensive experiments with various loss functions and datasets including CIFAR-10, CelebA-HQ, LSUN, and tiny-ImageNet. Quantitative evaluations demonstrate that WCL significantly improves the performance of GAN and conditional GAN in terms of Frechet inception distance (FID). For instance, the proposed method improves FID scores on the tiny-ImageNet dataset from 58.59 to 50.42.[5]：Developing emotion recognition for video conference software to support  people with autism
标题：开发支持自闭症患者的视频会议软件的情感识别
作者：Marc Franzen, Michael Stephan Gresser, Tobias Müller, Prof. Dr. Sebastian Mauser
链接：https://arxiv.org/abs/2101.10785
摘要：We develop an emotion recognition software for the use with a video conference software for autistic individuals which are unable to recognize emotions properly. It can get an image out of the video stream, detect the emotion in it with the help of a neural network and display the prediction to the user. The network is trained on facial landmark features. The software is fully modular to support adaption to different video conference software, programming languages and implementations.[6]：Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and  Video Denoising
标题：用于图像和视频去噪的空间和时空像素聚集学习算法
作者：Xiangyu Xu, Muchen Li, Wenxiu Sun, Ming-Hsuan Yang
备注：Project page:this https URL. arXiv admin note: substantial text overlap witharXiv:1904.06903
链接：https://arxiv.org/abs/2101.10760
摘要：Existing denoising methods typically restore clear results by aggregating pixels from the noisy input. Instead of relying on hand-crafted aggregation schemes, we propose to explicitly learn this process with deep neural networks. We present a spatial pixel aggregation network and learn the pixel sampling and averaging strategies for image denoising. The proposed model naturally adapts to image structures and can effectively improve the denoised results. Furthermore, we develop a spatio-temporal pixel aggregation network for video denoising to efficiently sample pixels across the spatio-temporal space. Our method is able to solve the misalignment issues caused by large motion in dynamic scenes. In addition, we introduce a new regularization term for effectively training the proposed video denoising model. We present extensive analysis of the proposed method and demonstrate that our model performs favorably against the state-of-the-art image and video denoising approaches on both synthetic and real-world data.[7]：Introducing and assessing the explainable AI (XAI)method: SIDU
标题：介绍和评估可解释人工智能（XAI）方法：SIDU
作者：Satya M. Muddamsetty, Mohammad N. S. Jahromi, Andreea E. Ciontos, Laura M. Fenoy, Thomas B. Moeslund
备注：Preprint-submitted to Journal of Pattern Recognition (Elsevier)
链接：https://arxiv.org/abs/2101.10710
摘要：Explainable Artificial Intelligence (XAI) has in recent years become a well-suited framework to generate human understandable explanations of black box models. In this paper, we present a novel XAI visual explanation algorithm denoted SIDU that can effectively localize entire object regions responsible for prediction in a full extend. We analyze its robustness and effectiveness through various computational and human subject experiments. In particular, we assess the SIDU algorithm using three different types of evaluations (Application, Human and Functionally-Grounded) to demonstrate its superior performance. The robustness of SIDU is further studied in presence of adversarial attack on black box models to better understand its performance.[8]：SkeletonVis: Interactive Visualization for Understanding Adversarial  Attacks on Human Action Recognition Models
标题：SkeletonVis：理解人类行为识别模型的对抗性攻击的交互式可视化
作者：Haekyu Park, Zijie J. Wang, Nilaksh Das, Anindya S. Paul, Pruthvi Perumalla, Zhiyan Zhou, Duen Horng Chau
备注：Accepted at AAAI'21 Demo
链接：https://arxiv.org/abs/2101.10586
摘要：Skeleton-based human action recognition technologies are increasingly used in video based applications, such as home robotics, healthcare on aging population, and surveillance. However, such models are vulnerable to adversarial attacks, raising serious concerns for their use in safety-critical applications. To develop an effective defense against attacks, it is essential to understand how such attacks mislead the pose detection models into making incorrect predictions. We present SkeletonVis, the first interactive system that visualizes how the attacks work on the models to enhance human understanding of attacks.[9]：RAMP-CNN: A Novel Neural Network for Enhanced Automotive Radar Object  Recognition
标题：RAMP-CNN：一种用于增强汽车雷达目标识别的新型神经网络
作者：Xiangyu Gao, Guanbin Xing, Sumit Roy, Hui Liu
备注：15 pages
链接：https://arxiv.org/abs/2011.08981
摘要：Millimeter-wave (mmW) radars are being increasingly integrated into commercial vehicles to support new advanced driver-assistance systems (ADAS) by enabling robust and high-performance object detection, localization, as well as recognition - a key component of new environmental perception. In this paper, we propose a novel radar multiple-perspectives convolutional neural network (RAMP-CNN) that extracts the location and class of objects based on further processing of the range-velocity-angle (RVA) heatmap sequences. To bypass the complexity of 4D convolutional neural networks (NN), we propose to combine several lower-dimension NN models within our RAMP-CNN model that nonetheless approaches the performance upper-bound with lower complexity. The extensive experiments show that the proposed RAMP-CNN model achieves better average recall (AR) and average precision (AP) than prior works in all testing scenarios (see Table. III). Besides, the RAMP-CNN model is validated to work robustly under the nighttime, which enables low-cost radars as a potential substitute for pure optical sensing under severe conditions.

NLP方向重复(10篇)

[1]：Towards Entity Alignment in the Open World: An Unsupervised Approach
标题：开放世界中的实体对齐：一种无监督的方法
作者：Weixin Zeng, Xiang Zhao, Jiuyang Tang, Xinyi Li, Minnan Luo, Qinghua Zheng
备注：Accepted by DASFAA 2021
链接：https://arxiv.org/abs/2101.10535
摘要：Entity alignment (EA) aims to discover the equivalent entities in different knowledge graphs (KGs). It is a pivotal step for integrating KGs to increase knowledge coverage and quality. Recent years have witnessed a rapid increase of EA frameworks. However, state-of-the-art solutions tend to rely on labeled data for model training. Additionally, they work under the closed-domain setting and cannot deal with entities that are unmatchable. To address these deficiencies, we offer an unsupervised framework that performs entity alignment in the open world. Specifically, we first mine useful features from the side information of KGs. Then, we devise an unmatchable entity prediction module to filter out unmatchable entities and produce preliminary alignment results. These preliminary results are regarded as the pseudo-labeled data and forwarded to the progressive learning framework to generate structural representations, which are integrated with the side information to provide a more comprehensive view for alignment. Finally, the progressive learning framework gradually improves the quality of structural embeddings and enhances the alignment performance by enriching the pseudo-labeled data with alignment results from the previous round. Our solution does not require labeled data and can effectively filter out unmatchable entities. Comprehensive experimental evaluations validate its superiority.[2]：On the Evaluation of Vision-and-Language Navigation Instructions
标题：视觉评价与语言导航教学
作者：Ming Zhao, Peter Anderson, Vihan Jain, Su Wang, Alexander Ku, Jason Baldridge, Eugene Ie
备注：Accepted to EACL 2021
链接：https://arxiv.org/abs/2101.10504
摘要：Vision-and-Language Navigation wayfinding agents can be enhanced by exploiting automatically generated navigation instructions. However, existing instruction generators have not been comprehensively evaluated, and the automatic evaluation metrics used to develop them have not been validated. Using human wayfinders, we show that these generators perform on par with or only slightly better than a template-based generator and far worse than human instructors. Furthermore, we discover that BLEU, ROUGE, METEOR and CIDEr are ineffective for evaluating grounded navigation instructions. To improve instruction evaluation, we propose an instruction-trajectory compatibility model that operates without reference instructions. Our model shows the highest correlation with human wayfinding outcomes when scoring individual instructions. For ranking instruction generation systems, if reference instructions are available we recommend using SPICE.[3]：I Beg to Differ: A study of constructive disagreement in online  conversations
标题：我不敢苟同：网络会话中的建设性分歧研究
作者：Christine de Kock, Andreas Vlachos
备注：Accepted to appear in EACL 2021
链接：https://arxiv.org/abs/2101.10917
摘要：Disagreements are pervasive in human communication. In this paper we investigate what makes disagreement constructive. To this end, we construct WikiDisputes, a corpus of 7 425 Wikipedia Talk page conversations that contain content disputes, and define the task of predicting whether disagreements will be escalated to mediation by a moderator. We evaluate feature-based models with linguistic markers from previous work, and demonstrate that their performance is improved by using features that capture changes in linguistic markers throughout the conversations, as opposed to averaged values. We develop a variety of neural models and show that taking into account the structure of the conversation improves predictive accuracy, exceeding that of feature-based models. We assess our best neural model in terms of both predictive accuracy and uncertainty by evaluating its behaviour when it is only exposed to the beginning of the conversation, finding that model accuracy improves and uncertainty reduces as models are exposed to more information.[4]：Summarising Historical Text in Modern Languages
标题：用现代语言总结历史文本
作者：Xutan Peng, Yi Zheng, Chenghua Lin, Advaith Siddharthan
备注：To appear at EACL 2021
链接：https://arxiv.org/abs/2101.10759
摘要：We introduce the task of historical text summarisation, where documents in historical forms of a language are summarised in the corresponding modern language. This is a fundamentally important routine to historians and digital humanities researchers but has never been automated. We compile a high-quality gold-standard text summarisation dataset, which consists of historical German and Chinese news from hundreds of year ago summarised in modern German or Chinese. Based on cross-lingual transfer learning techniques, we propose a summarisation model which can be trained even with no cross-lingual (historical to modern) parallel data, and further benchmark it against state-of-the-art algorithms. We report automatic and human evaluations that distinguish the historic to modern language summarisation task from standard cross-lingual summarisation (i.e., modern to modern language), highlight the distinctness and value of our dataset, and demonstrate that our transfer learning approach outperforms standard cross-lingual benchmarks on this task.[5]：Few-Shot Semantic Parsing for New Predicates
标题：新谓词的少量语义分析
作者：Zhuang Li, Lizhen Qu, Shuo Huang, Gholamreza Haffari
备注：Accepted to EACL 2021
链接：https://arxiv.org/abs/2101.10708
摘要：In this work, we investigate the problems of semantic parsing in a few-shot learning setting. In this setting, we are provided with utterance-logical form pairs per new predicate. The state-of-the-art neural semantic parsers achieve less than 25% accuracy on benchmark datasets when k= 1. To tackle this problem, we proposed to i) apply a designated meta-learning method to train the model; ii) regularize attention scores with alignment statistics; iii) apply a smoothing technique in pre-training. As a result, our method consistently outperforms all the baselines in both one and two-shot settings.[6]：Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks
标题：监督自然语言处理任务中零镜头跨语言迁移分析
作者：Hyunjin Choi, Judong Kim, Seongho Joe, Seungjai Min, Youngjune Gwon
备注：6 pages, 4 figures, to be published in 25th International Conference on Pattern Recognition, ICPR 2020
链接：https://arxiv.org/abs/2101.10649
摘要：In zero-shot cross-lingual transfer, a supervised NLP task trained on a corpus in one language is directly applicable to another language without any additional training. A source of cross-lingual transfer can be as straightforward as lexical overlap between languages (e.g., use of the same scripts, shared subwords) that naturally forces text embeddings to occupy a similar representation space. Recently introduced cross-lingual language model (XLM) pretraining brings out neural parameter sharing in Transformer-style networks as the most important factor for the transfer. In this paper, we aim to validate the hypothetically strong cross-lingual transfer properties induced by XLM pretraining. Particularly, we take XLM-RoBERTa (XLMR) in our experiments that extend semantic textual similarity (STS), SQuAD and KorQuAD for machine reading comprehension, sentiment analysis, and alignment of sentence embeddings under various cross-lingual settings. Our results indicate that the presence of cross-lingual transfer is most pronounced in STS, sentiment analysis the next, and MRC the last. That is, the complexity of a downstream task softens the degree of crosslingual transfer. All of our results are empirically observed and measured, and we make our code and data publicly available.[7]：Evaluation of BERT and ALBERT Sentence Embedding Performance on  Downstream NLP Tasks
标题：下游自然语言处理任务中BERT和ALBERT语句嵌入性能的评价
作者：Hyunjin Choi, Judong Kim, Seongho Joe, Youngjune Gwon
备注：6 pages, 2 figures, to be published in 25th International Conference on Pattern Recognition, ICPR2020
链接：https://arxiv.org/abs/2101.10642
摘要：Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in sentence-pair regressions such as semantic textual similarity (STS) and natural language inference (NLI). Although BERT-based models yield the [CLS] token vector as a reasonable sentence embedding, the search for an optimal sentence embedding scheme remains an active research area in computational linguistics. This paper explores on sentence embedding models for BERT and ALBERT. In particular, we take a modified BERT network with siamese and triplet network structures called Sentence-BERT (SBERT) and replace BERT with ALBERT to create Sentence-ALBERT (SALBERT). We also experiment with an outer CNN sentence-embedding network for SBERT and SALBERT. We evaluate performances of all sentence-embedding models considered using the STS and NLI datasets. The empirical results indicate that our CNN architecture improves ALBERT models substantially more than BERT models for STS benchmark. Despite significantly fewer model parameters, ALBERT sentence embedding is highly competitive to BERT in downstream NLP evaluations.[8]：RESPER: Computationally Modelling Resisting Strategies in Persuasive  Conversations
标题：RESPER：说服性会话中的抵制策略的计算模型
作者：Ritam Dutt, Sayan Sinha, Rishabh Joshi, Surya Shekhar Chakraborty, Meredith Riggs, Xinru Yan, Haogang Bao, Carolyn Penstein Rosé
备注：Accepted as a long paper at the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021)
链接：https://arxiv.org/abs/2101.10545
摘要：Modelling persuasion strategies as predictors of task outcome has several real-world applications and has received considerable attention from the computational linguistics community. However, previous research has failed to account for the resisting strategies employed by an individual to foil such persuasion attempts. Grounded in prior literature in cognitive and social psychology, we propose a generalised framework for identifying resisting strategies in persuasive conversations. We instantiate our framework on two distinct datasets comprising persuasion and negotiation conversations. We also leverage a hierarchical sequence-labelling neural architecture to infer the aforementioned resisting strategies automatically. Our experiments reveal the asymmetry of power roles in non-collaborative goal-directed conversations and the benefits accrued from incorporating resisting strategies on the final conversation outcome. We also investigate the role of different resisting strategies on the conversation outcome and glean insights that corroborate with past findings. We also make the code and the dataset of this work publicly available atthis https URL.[9]：El Volumen Louder Por Favor: Code-switching in Task-oriented  SemanticParsing
标题：El Volumen Louder Por Favor：面向任务的语义分析中的代码转换
作者：Arash Einolghozati, Abhinav Arora, Lorena Sainz-Maza Lecanda, Anuj Kumar, Sonal Gupta
链接：https://arxiv.org/abs/2101.10524
摘要：Being able to parse code-switched (CS) utterances, such as Spanish+English or Hindi+English, is essential to democratize task-oriented semantic parsing systems for certain locales. In this work, we focus on Spanglish (Spanish+English) and release a dataset, CSTOP, containing 5800 CS utterances alongside their semantic parses. We examine the CS generalizability of various Cross-lingual (XL) models and exhibit the advantage of pre-trained XL language models when data for only one language is present. As such, we focus on improving the pre-trained models for the case when only English corpus alongside either zero or a few CS training instances are available. We propose two data augmentation methods for the zero-shot and the few-shot settings: fine-tune using translate-and-align and augment using a generation model followed by match-and-filter. Combining the few-shot setting with the above improvements decreases the initial 30-point accuracy gap between the zero-shot and the full-data settings by two thirds.[10]：Randomized Deep Structured Prediction for Discourse-Level Processing
标题：语篇层次处理中的随机深层结构预测
作者：Manuel Widmoser, Maria Leonor Pacheco, Jean Honorio, Dan Goldwasser
备注：Accepted to EACL 2021
链接：https://arxiv.org/abs/2101.10435
摘要：Expressive text encoders such as RNNs and Transformer Networks have been at the center of NLP models in recent work. Most of the effort has focused on sentence-level tasks, capturing the dependencies between words in a single sentence, or pairs of sentences. However, certain tasks, such as argumentation mining, require accounting for longer texts and complicated structural dependencies between them. Deep structured prediction is a general framework to combine the complementary strengths of expressive neural encoders and structured inference for highly structured domains. Nevertheless, when the need arises to go beyond sentences, most work relies on combining the output scores of independently trained classifiers. One of the main reasons for this is that constrained inference comes at a high computational cost. In this paper, we explore the use of randomized inference to alleviate this concern and show that we can efficiently leverage deep structured prediction and expressive neural encoders for a set of tasks involving complicated argumentative structures.中文来自机器翻译，仅供参考。