检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Alhafni, Bashar Habash, Nizar Computational Approaches to Modeling Language Lab New York University Abu Dhabi United Arab Emirates

Text editing frames grammatical error correction (GEC) as a sequence tagging problem, where edit tags are assigned to input tokens, and applying these edits results in the corrected text. This approach has gained attention for its efficiency and interpretability. However, while extensively explored for English, text editing remains largely underexplored for morphologically rich languages like Arabic. In this paper, we introduce a text editing approach that derives edit tags directly from data, eliminating the need for language-specific edits. We demonstrate its effectiveness on Arabic, a diglossic and morphologically rich language, and investigate the impact of different edit representations on model performance. Our approach achieves SOTA results on two Arabic GEC benchmarks and performs on par with SOTA on two others. Additionally, our models are over six times faster than existing Arabic GEC systems, making our approach more practical for real-world applications. Finally, we explore ensemble models, demonstrating how combining different models leads to further performance improvements. We make our code, data, and pretrained models publicly available.1 Copyright © 2025, The Authors. All rights reserved.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment

arXiv

引用

arXiv 2025年

作者： Elmadani, Khalid N. Habash, Nizar Taha-Thomure, Hanada Computational Approaches to Modeling Language Lab New York University Abu Dhabi United Arab Emirates Zai Arabic Language Research Centre Zayed University United Arab Emirates

This paper introduces the Balanced Arabic Readability Evaluation Corpus (BAREC),1 a large-scale, fine-grained dataset for Arabic readability assessment. BAREC consists of 68,182 sentences spanning 1+ million words, carefully curated to cover 19 readability levels, from kindergarten to postgraduate comprehension. The corpus balances genre diversity, topical coverage, and target audiences, offering a comprehensive resource for evaluating Arabic text complexity. The corpus was fully manually annotated by a large team of annotators. The average pairwise inter-annotator agreement, measured by Quadratic Weighted Kappa, is 81.3%, reflecting a high level of substantial agreement. Beyond presenting the corpus, we benchmark automatic readability assessment across different granularity levels, comparing a range of techniques. Our results highlight the challenges and opportunities in Arabic readability modeling, demonstrating competitive performance across various methods. To support research and education, we will make BAREC openly available, along with detailed annotation guidelines and benchmark results. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Theoretical insight into stabilities and optoelectronic properties of RbZnX3 (X=Cl, Br) halide perovskites for energy conversion applications

引用

Optical and Quantum Electronics 2025年第1期57卷 1-21页

作者： Khan, Naimat Ullah Ghani, Usman khan, Arshad Khan, Asif Nawaz Ullah, Khadim Ali, Roshan Fadhali, Mohammed M. Department of Physics Materials Modeling and Simulation Lab University of Science & Technology Bannu Khyber Pakhtunkhwa Bannu28100 Pakistan Department of Physics University of Science & Technology Bannu Khyber Pakhtunkhwa Bannu28100 Pakistan Theoretical Condensed Matter Physics and Computational Materials Physics Laboratory College of Physical Sciences University of Chinese Academy of Sciences Beijing100049 China Department of Physical Sciences Physics Division College of Science Jazan University P.O. Box. 114 Jazan45142 Saudi Arabia

Owing to the interesting physical characteristics of perovskites, herein, we investigate RbZnX3 (X = Cl, Br) halide perovskites for sustainable green energy applications. All the given structures were made relaxed and minimum energy was attained by employing Birch-Muranghan equation of state. The electronic band structure of the under study materials were calculated through modified-Beck-Johnson potential. Our results showed that all the investigated RbZnX3 (X = Cl, Br) perovskites are semiconductors with band gaps of 1.34, and 0.12 eV, respectively. The calculated tolerance factors, formation energies, Born-Hung criteria, phonon spectra and ab initio molecular dynamic (AIMD) simulations demonstrated that the given compounds exhibit geometrical, thermodynamic, mechanical, dynamic and thermal stabilities. Findings of elastic investigation revealed an elastic, anisotropic, and ductile nature of our predicted compounds. Moreover, all the studied materials revealed strong absorption – 104 cm−1 in the visible and ultraviolet spectrum and the device absorption efficiency (%) was found comparable to other known reported materials. Overall, this study demonstrates that our simulated perovskites are suitable candidates for photovoltaic and optoelectronic applications. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Bromine compounds

来源：评论

学校读者我要写书评

暂无评论

Validation of merging techniques for cancer microarray data sets

Validation of merging techniques for cancer microarray data ...

引用

22nd Benelux Conference on Artificial Intelligence, BNAIC 2010

作者： Taminau, Jonatan Meganck, Stijn Nowé, Ann Computational Modeling Lab Vrije Universiteit Brussel Belgium

There is a vast amount of gene expression data that has been gathered in microarray studies all over the world. Many of these studies use different experimentation plans, different platforms, different methodologies, etc. Merging information of different studies is an important part of current research in bioinformatics and several algorithms have been proposed recently. There is clearly a need to create large data sets which will allow more statistically relevant analysis in order to obtain more and better results in clinical and medical research. In this article we consistently describe several gene expression data merging techniques and apply them on several cancer microarray data sets.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning for energy efficient routing inwireless sensor networks

Reinforcement learning for energy efficient routing inwirele...

引用

23rd Benelux Conference on Artificial Intelligence, BNAIC 2011

作者： Devillé, Maarten Le Borgne, Yann-Aël Nowé, Ann Computational Modeling Lab Vrije Universiteit Brussel Belgium

In this paper we study the potential of using energy aware metrics in reinforcement learning based routing algorithms for wireless sensor networks. This paper contributes with an enhanced version of an existing energy aware algorithm and with a study that tests the influence of combining energy aware metrics with load balancing metrics from delay based Q-routing. We show that our enhanced algorithm can significantly improve the lifetime of a network without requiring any extra information or communication, by propagating energy information beyond direct neighbors throughout the network. Our study also shows that topologies composed from heterogenous nodes can have a significant impact on an algorithm's performance. Furthermore we show that load balancing in routing algorithms can help to improve the network lifetime while only requiring energy information about a node's direct neighbors.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Selection-Mutation Model for Q-learning in Multi-Agent Systems 03

A Selection-Mutation Model for Q-learning in Multi-Agent Sys...

引用

Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 03

作者： Tuyls, Karl Verbeeck, Katja Lenaerts, Tom Computational Modeling Lab Pleinlaan 2 1050 Brussels Belgium

ISBN: (纸本)9781581136838

Although well understood in the single-agent framework, the use of traditional reinforcement learning (RL) algorithms in multi-agent systems (MAS) is not always justified. The feed-back an agent experiences in a MAS, is usually influenced by the other agents present in the system. Multi agent environments are therefore non-stationary and convergence and optimality guarantees of RL algorithms are lost. To better understand the dynamics of traditional RL algorithms we analyze the learning process in terms of evolutionary dynamics. More specifically we show how the Replicator Dynamics (RD) can be used as a model for Q-learning in games. The dynamical equations of Q-learning are derived and illustrated by some well chosen experiments. Both reveal an interesting connection between the exploitation-exploration scheme from RL and the selection-mutation mechanisms from evolutionary game theory.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Social agents playing a periodical policy 12th

引用

12th European Conference on Machine Learning, ECML 2001

作者： Nowé, Ann Parent, Johan Verbeeck, Katja Vrije Universiteit Brussel Belgium Computational Modeling Lab Belgium

ISBN: (纸本)3540425365

Coordination is an important issue in multiagent systems. Within the stochastic game framework this problem translates to policy learning in a joint action space. This technique however suffers some im- portant drawbacks like the assumption of the existence of a unique Nash equilibrium and synchronicity, the need for central control, the cost of communication, etc. Moreover in general sum games it is not always clear which policies should be learned. Playing pure Nash equilibria is often unfair to at least one of the players, while playing a mixed strategy doesn't give any guarantee for coordination and usually results in a sub-optimal payoff for all agents. In this work we show the usefulness of periodical policies, which arise as a side effect of the fairness conditions used by the agents. We are interested in games which assume competition between the players, but where the overall performance can only be as good as the performance of the poorest player. Players are social distributed reinforcement learners, who have to learn to equalize their payoff. Our approach is illustrated on synchronous one-step games as well as on asynchronous job scheduling games. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Learning to take turns

Learning to take turns

引用

3rd Adaptive and Learning Agents Workshop, ALA 2010 - In Conjunction with the 9th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2010

作者： Vrancx, Peter Verbeeck, Katja Nowé, Ann Computational Modeling Lab Vrije Universiteit Brussel Brussels Belgium Ghent Belgium

This paper provides a novel approach to multi-agent coordination in general-sum Markov games. Contrary to what is common in multi-agent learning, our approach does not focus on reaching a particular equilibrium between agent policies. Instead, it learns a basis set of special joint agent policies, over which it can randomize to build different solutions. The main idea is to tackle a Markov game by decomposing it into a set of multi-agent common interest problems, also called Multi-agent Markov Decision Processes (MMDPs). Each MMDP reflects one agent's preferences in the system. With only a minimum of coordination, simple reinforcement learning agents using Parameterised Learning Automata are able to solve this set of common interest problems in parallel. A third party then selects the MMDP to be played, without a need for the agents to know which problem or reward function they are confronted with. As a result, a team of simple learning agents is able to switch play between desired joint policies rather than mixing individual policies. One application of this principle, which we consider in this paper, is to let simple adaptive agents learn to take turns in generalsum Markov Games in order to satisfy their individual objectives. We experimentally demonstrate this principle in a grid-world setting.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Scalarized multi-objective reinforcement learning: Novel design techniques 25

Scalarized multi-objective reinforcement learning: Novel des...

引用

25th Benelux Conference on Artificial Intelligence, BNAIC 2013

作者： Van Moffaert, Kristof Drugan, Madalina M. Nowé, Ann Computational Modeling Lab VUB Pleinlaan 2 BrusselsB-1050 Belgium

In multi-objective problems, it is key to find compromising solutions that balance different objectives. The linear scalarization function is often utilized to translate the multi-objective nature of a problem into a standard, single-objective problem. Generally, it is noted that such as linear combination can only find solutions in convex areas of the Pareto front, therefore making the method inapplicable in situations where the shape of the front is not known beforehand. We propose a non-linear scalarization function, called the Chebyshev scalarization function in multi-objective reinforcement learning. We show that the Chebyshev scalarization method overcomes the flaws of the linear scalarization function and is able to discover all Pareto optimal solutions in non-convex environments. © 2013 University of Groningen. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Contextualizing predictive minds

引用

Neuroscience and Biobehavioral Reviews 2025年 168卷 105948页

作者： Butz, Martin V. Mittenbühler, Maximilian Schwöbel, Sarah Achimova, Asya Gumbsch, Christian Otte, Sebastian Kiebel, Stefan Cognitive Modeling Faculty of Science University of Tübingen Sand 14 Tübingen 72076 Germany Cognitive Computational Neuroscience Faculty of Psychology TU Dresden School of Science Dresden 01062 Germany Chair of Cognitive and Clinical Neuroscience Faculty of Psychology TU Dresden Dresden 01069 Germany Adaptive AI Lab Institute of Robotics and Cognitive Systems University of Lübeck Ratzeburger Allee 160 Lübeck 23562 Germany

The structure of human memory seems to be optimized for efficient prediction, planning, and behavior. We propose that these capacities rely on a tripartite structure of memory that includes concepts, events, and contexts—three layers that constitute the mental world model. We suggest that the mechanism that critically increases adaptivity and flexibility is the tendency to contextualize. This tendency promotes local, context-encoding abstractions, which focus event- and concept-based planning and inference processes on the task and situation at hand. As a result, cognitive contextualization offers a solution to the frame problem—the need to select relevant features of the environment from the rich stream of sensorimotor signals. We draw evidence for our proposal from developmental psychology and neuroscience. Adopting a computational stance, we present evidence from cognitive modeling research which suggests that context sensitivity is a feature that is critical for maximizing the efficiency of cognitive processes. Finally, we turn to recent deep-learning architectures which independently demonstrate how context-sensitive memory can emerge in a self-organized learning system constrained by cognitively-inspired inductive biases. © 2024 The Authors

关键词： Abstraction Active inference Behavior Cognitive modeling Context inference Deep learning Events Free energy Learning Prediction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：