人工智能学术速递[2021.5.13]

 访问arxivdaily.com

获取含摘要速递，更有收藏、搜索等功能，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域

同步公众号:arXiv每日学术速递，欢迎关注

cs.AI人工智能，共计26篇

【1】 The Greedy and Recursive Search for Morphological Productivity

标题：形态生产力的贪婪递归搜索

作者：Caleb Belth,Sarah Payne,Deniz Beser,Jordan Kodner,Charles Yang

机构：Department of Computer Science and Engineering, University of Michigan, Department of Linguistics and Department of Computer and Information Science, University of Pennsylvania, Information Sciences Institute, University of Southern California

备注：CogSci 2021

链接：https://arxiv.org/abs/2105.05790

【2】 Probabilistic Loss and its Online Characterization for Simplified Decision Making Under Uncertainty

标题：不确定条件下简化决策的概率损失及其在线表征

作者：Andrey Zhitnikov,Vadim Indelman

机构：∗Technion Autonomous Systems Program, †Department of Aerospace Engineering, Technion - Israel Institute of Technology, Haifa , Israel

链接：https://arxiv.org/abs/2105.05789

【3】 Exploring the Similarity of Representations in Model-Agnostic Meta-Learning

标题：模型不可知元学习中表征相似性的探索

作者：Thomas Goerttler,Klaus Obermayer

机构：Technische Universit¨at Berlin, Chair of Neural Information Processing, Germany, Bernstein Center for Computational Neuroscience Berlin, Germany

备注：Learning to Learn workshop at ICLR 2021

链接：https://arxiv.org/abs/2105.05757

【4】 Building a Question and Answer System for News Domain

标题：构建新闻领域的问答系统

作者：Sandipan Basu,Aravind Gaddala,Pooja Chetan,Garima Tiwari,Narayana Darapaneni,Sadwik Parvathaneni,Anwesh Reddy Paduri

机构：Director – AIML, Great LearningNorthwestern, University Illinois, USA, Student – AIML, Bangalore, India, Mentor– AIML, Anwesh Reddy Paduri, Data Scientist - AIML

链接：https://arxiv.org/abs/2105.05744

【5】 An Efficient Learning Framework For Federated XGBoost Using Secret Sharing And Distributed Optimization

标题：基于秘密共享和分布式优化的联邦XGBoost高效学习框架

作者：Lunchen Xie,Jiaqi Liu,Songtao Lu,Tsung-hui Chang,Qingjiang Shi

机构：Shenzhen, China

备注：24 pages, Special issue of ACM Transactions on Intelligent Systems and Technology

链接：https://arxiv.org/abs/2105.05717

【6】 Acting upon Imagination: when to trust imagined trajectories in model based reinforcement learning

标题：基于想象的行动：在基于模型的强化学习中，什么时候应该信任想象的轨迹

作者：Adrian Remonda,Eduardo Veas,Granit Luzhnica

机构：Know-Center, Graz, Styria, Austria, Graz University of Technology, Graz, Styria, Austria

链接：https://arxiv.org/abs/2105.05716

【7】 Representation in Dynamical Systems

标题：动力系统中的表示法

作者：Matthew Hutson

机构：Brown University, Providence, RI

备注：11 pages, 2 figures

链接：https://arxiv.org/abs/2105.05714

【8】 Segmenter: Transformer for Semantic Segmentation

标题：分词：语义分词的转换器

作者：Robin Strudel,Ricardo Garcia,Ivan Laptev,Cordelia Schmid

机构：Inria†

备注：Code available at this https URL

链接：https://arxiv.org/abs/2105.05633

【9】 NLP for Climate Policy: Creating a Knowledge Platform for Holistic and Effective Climate Action

标题：气候政策NLP：为全面和有效的气候行动创建知识平台

作者：Pradip Swarnakar,Ashutosh Modi

机构：Department of Humanities and Social Sciences, Department of Computer Science and Engineering, Indian Institute of Technology Kanpur, Kanpur , India

备注：12 Pages (8 + 4 pages for references)

链接：https://arxiv.org/abs/2105.05621

【10】 Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding

标题：基于概率推理和语义嵌入的无监督知识图对齐

作者：Zhiyuan Qi,Ziheng Zhang,Jiaoyan Chen,Xi Chen,Yuejia Xiang,Ningyu Zhang,Yefeng Zheng

机构：Tencent Jarvis Lab, Shenzhen, China, Department of Computer Science, University of Oxford, UK, Platform and Content Group, Tencent, Shenzhen, China, Zhejiang University, Hangzhou, China

备注：Accepted by IJCAI 2021

链接：https://arxiv.org/abs/2105.05596

【11】 An Appraisal Transition System for Event-driven Emotions in Agent-based Player Experience Testing

标题：基于Agent的玩家体验测试中事件驱动情绪评价转换系统

作者：Saba Gholizadeh Ansari,I. S. W. B. Prasetya,Mehdi Dastani,Frank Dignum,Gabriele Keller

机构： Ume˚a University, Ume˚a, Sweden, NOTE: This is a preprint of the article , accepted in ,th International Workshop on Engineering Multi-Agent Systems, (EMAS,), held as a part of ,th International Conference on Autonomous Agents and Multiagent Systems (AAMAS).

备注：This is a preprint of an article with the same title, accepted in 9th International Workshop on Engineering Multi-Agent Systems (EMAS 2021) which was held as a part of 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021)

链接：https://arxiv.org/abs/2105.05589

【12】 "Alexa, what do you do for fun?" Characterizing playful requests with virtual assistants

作者：Chen Shani,Alexander Libov,Sofia Tolmach,Liane Lewin-Eytan,Yoelle Maarek,Dafna Shahaf

机构：The Hebrew University of Jerusalem, Amazon Alexa Shopping

链接：https://arxiv.org/abs/2105.05571

【13】 Looking at CTR Prediction Again: Is Attention All You Need?

标题：再看CTR预测：你只需要关注吗？

作者：Yuan Cheng,Yanbo Xue

机构：Career Science Lab, BOSS Zhipin, Beijing, China

备注：9 pages, 2 figures, 4 tables, SIGIR21

链接：https://arxiv.org/abs/2105.05563

【14】 Learning Uncertainty with Artificial Neural Networks for Improved Remaining Time Prediction of Business Processes

标题：改进业务流程剩余时间预测的人工神经网络学习不确定性

作者：Hans Weytjens,Jochen De Weerdt

机构：Research Centre for Information Systems Engineering (LIRIS), KU Leuven, Leuven, Belgium

备注：Accepted for the main conference at the Business Process Management Conferences 2021, 6-10 September 2021, Rome, Italy

链接：https://arxiv.org/abs/2105.05559

【15】 Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction

标题：源条件掩蔽跨度预测改进词汇约束神经机器翻译

作者：Gyubok Lee,Seongjun Yang,Edward Choi

机构：Graduate School of AI, KAIST

备注：To appear in ACL 2021

链接：https://arxiv.org/abs/2105.05498

【16】 Interpretable performance analysis towards offline reinforcement learning: A dataset perspective

标题：基于数据集的离线强化学习的可解释性性能分析

作者：Chenyang Xi,Bo Tang,Jiajun Shen,Xinfu Liu,Feiyu Xiong,Xueying Li

机构： China 2School of Aerospace Engi-neering, Beijing Institute of Technology, China 3School ofElectrical and Computer Engineering, Purdue University

链接：https://arxiv.org/abs/2105.05473

【17】 From Human-Computer Interaction to Human-AI Interaction: New Challenges and Opportunities for Enabling Human-Centered AI

标题：从人机交互到人机交互：实现以人为中心的人工智能的新挑战和新机遇

作者：Wei Xu,Marvin J. Dainoff,Liezhong Ge,Zaifeng Gao

机构：a Center for Psychological Sciences, Zhejiang University, Hangzhou, China; b Dept. of, Psychology, Miami University, Oxford, Ohio; c Zhejiang University, Department of Psychology

备注：76 pages

链接：https://arxiv.org/abs/2105.05424

【18】 Could you give me a hint? Generating inference graphs for defeasible reasoning

标题：你能给我一个提示吗？生成用于可废止推理的推理图

作者：Aman Madaan,Dheeraj Rajagopal,Niket Tandon,Yiming Yang,Eduard Hovy

机构：Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA, † Allen Institute for Artificial Intelligence, Seattle, WA, USA

备注：Findings of the Association for Computational Linguistics: ACL 2021

链接：https://arxiv.org/abs/2105.05418

【19】 Bayesian Model Averaging for Data Driven Decision Making when Causality is Partially Known

标题：因果关系部分已知时数据驱动决策的贝叶斯模型平均

作者：Marios Papamichalis,Abhishek Ray,Ilias Bilionis,Karthik Kannan,Rajiv Krishnamurthy

链接：https://arxiv.org/abs/2105.05395

【20】 Accuracy-Privacy Trade-off in Deep Ensemble

标题：深度集成中的精度-隐私权衡

作者：Shahbaz Rezaei,Zubair Shafiq,Xin Liu

机构：University of California, Davis, CA, USA

链接：https://arxiv.org/abs/2105.05381

【21】 Return-based Scaling: Yet Another Normalisation Trick for Deep RL

标题：基于回报的缩放：Deep RL的另一个归一化技巧

作者：Tom Schaul,Georg Ostrovski,Iurii Kemaev,Diana Borsa

链接：https://arxiv.org/abs/2105.05347

【22】 Neuro-Symbolic Artificial Intelligence Current Trends

标题：神经符号人工智能的发展趋势

作者：Md Kamruzzaman Sarker,Lu Zhou,Aaron Eberhart,Pascal Hitzler

机构：Department of Computer Science, Kansas State University, KS, USA

备注：under review

链接：https://arxiv.org/abs/2105.05330

【23】 Seeing All From a Few: Nodes Selection Using Graph Pooling for Graph Clustering

标题：从几个方面看全部：使用图池进行图聚类的节点选择

作者：Yiming Wang,Dongxia Chang,Zhiqian Fu,Yao Zhao

机构：Beijing Jiaotong University

链接：https://arxiv.org/abs/2105.05320

【24】 Intelligent interactive technologies for mental health and well-being

标题：心理健康和福祉的智能互动技术

作者：Mladjan Jovanovic,Aleksandar Jevremovic,Milica Pejovic-Milovancevic

机构：rsMilica Pejovic-MilovancevicInstitute of Mental Health and Faculty of Medicine

链接：https://arxiv.org/abs/2105.05306

【25】 Online POMDP Planning via Simplification

标题：基于简化的在线POMDP规划

作者：Ori Sztyglic,Vadim Indelman

机构：Department of Computer Science, Department of Aerospace Engineering, Technion - Israel Institute of Technology, Haifa , Israel

链接：https://arxiv.org/abs/2105.05296

【26】 CCN GAC Workshop: Issues with learning in biological recurrent neural networks

标题：CCN GAC研讨会：生物递归神经网络中的学习问题

作者：Luke Y. Prince,Ellen Boven,Roy Henha Eyono,Arna Ghosh,Joe Pemberton,Franz Scherr,Claudia Clopath,Rui Ponte Costa,Wolfgang Maass,Blake A. Richards,Cristina Savin,Katharina Anna Wilmes

机构：School of Computer Science, McGill University, Montreal, Canada, Mila, Montreal, Canada, Bristol Computational Neuroscience Unit, University of Bristol, United Kingdom, Institute of Theoretical Computer Science, Graz University of Technology, Graz, Austria

链接：https://arxiv.org/abs/2105.05382

机器翻译，仅供参考

访问arxivdaily.com

获取含摘要速递，更有收藏、搜索等功能，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域

同步公众号:arXiv每日学术速递，欢迎关注