检索结果-内蒙古大学图书馆

41st Annual Meeting of the cognitive science Society: Creativity + Cognition + Computation, CogSci 2019

作者： Sun, Zhewei Zemel, Richard Xu, Yang Department of Computer Science University of Toronto Canada Department of Computer Science University of Toronto Vector Institute Canada Department of Computer Science Cognitive Science Program University of Toronto Canada

ISBN: (纸本)0991196775

Slang is a common device for expressivity in natural language. While slang has been studied extensively as a social phenomenon, its cognitive bases are not well understood. We formulate the processes of slang generation as a categorization problem. We explore a set of cognitive models of categorization that recommend slang words based on intended referents of the speaker beyond the existing senses of words. We test these models against a large repertoire of slang sense definitions from the Online Slang Dictionary and show that the categorization models predict slang word choices substantially better than chance, without explicit consideration of external social factors. We also show that words similar in existing senses tend to extend to similar novel slang senses, reflecting a process of parallel semantic change. Our work helps to ground theories of slang in cognitive models of categorization and provides the potential for machine processing of informal natural language. © cognitive science Society: Creativity + Cognition + Computation, CogSci *** rights reserved.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

Tracing Semantic Variation in Slang

Tracing Semantic Variation in Slang

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Sun, Zhewei Xu, Yang Department of Computer Science University of Toronto Toronto Canada Cognitive Science Program University of Toronto Toronto Canada

The meaning of a slang term can vary in different communities. However, slang semantic variation is not well understood and under-explored in the natural language processing of slang. One existing view argues that slang semantic variation is driven by culture-dependent communicative needs. An alternative view focuses on slang's social functions suggesting that the desire to foster semantic distinction may have led to the historical emergence of community-specific slang senses. We explore these theories using computational models and test them against historical slang dictionary entries, with a focus on characterizing regularity in the geographical variation of slang usages attested in the US and the UK over the past two centuries. We show that our models are able to predict the regional identity of emerging slang word meanings from historical slang records. We offer empirical evidence that both communicative need and semantic distinction play a role in the variation of slang meaning yet their relative importance fluctuates over the course of history. Our work offers an opportunity for incorporating historical cultural elements into the natural language processing of slang. © 2022 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Design and Performance Evaluation of Sequence Partition Algorithms

引用

Journal of computer science & Technology 2008年第5期23卷 711-718页

作者：杨兵陈菁吕恩月郑斯清 Cisco Systems 2200 East President George Bush Highway Telecom. Engineering Program University of Texas at Dallas Department of Mathematics and Computer Science Salisbury University Department of Computer Science University of Texas at Dallas

Tradeoffs between time complexities and solution optimalities are important when selecting algorithms for an NP-hard problem in different applications. Also, the distinction between theoretical upper bound and actual solution optimality for realistic instances of an NP-hard problem is a factor in selecting algorithms in practice. We consider the problem of partitioning a sequence of n distinct numbers into minimum number of monotone （increasing or decreasing） subsequences. This problem is NP-hard and the number of monotone subsequences can reach [√2n＋1/1-1/2]in the worst case. We introduce a new algorithm, the modified version of the Yehuda-Fogel algorithm, that computes a solution of no more than [√2n＋1/1-1/2]monotone subsequences in O（n^1.5） time. Then we perform a comparative experimental study on three algorithms, a known approximation algorithm of approximation ratio 1.71 and time complexity O（n^3）, a known greedy algorithm of time complexity O（n^1.5 log n）, and our new modified Yehuda-Fogel algorithm. Our results show that the solutions computed by the greedy algorithm and the modified Yehuda-Fogel algorithm are close to that computed by the approximation algorithm even though the theoretical worst-case error bounds of these two algorithms are not proved to be within a constant time of the optimal solution. Our study indicates that for practical use the greedy algorithm and the modified Yehuda-Fogel algorithm can be good choices if the running time is a major concern.

关键词： monotone subsequence permutation algorithm NP-complete approximation complexity

来源：评论

学校读者我要写书评

暂无评论

Gumbel-Softmax Flow Matching with Straight-Through Guidance for Controllable Biological Sequence Generation

arXiv

引用

arXiv 2025年

作者： Tang, Sophia Zhang, Yinuo Tong, Alexander Chatterjee, Pranam Department of Biomedical Engineering Duke University United States Management and Technology Program University of Pennsylvania United States Center of Computational Biology Duke-NUS Medical School Singapore Mila Quebec AI Institute Canada Université de Montréal Canada Department of Computer Science Duke University United States Department of Biostatistics and Bioinformatics Duke University United States

Flow matching in the continuous simplex has emerged as a promising strategy for DNA sequence design, but struggles to scale to higher simplex dimensions required for peptide and protein generation. We introduce Gumbel-Softmax Flow and Score Matching, a generative framework on the simplex based on a novel Gumbel-Softmax interpolant with a time-dependent temperature. Using this interpolant, we introduce Gumbel-Softmax Flow Matching by deriving a parameterized velocity field that transports from smooth categorical distributions to distributions concentrated at a single vertex of the simplex. We alternatively present Gumbel-Softmax Score Matching which learns to regress the gradient of the probability density. Our framework enables high-quality, diverse generation and scales efficiently to higher-dimensional simplices. To enable training-free guidance, we propose Straight-Through Guided Flows (STGFlow), a classifier-based guidance method that leverages straight-through estimators to steer the unconditional velocity field toward optimal vertices of the simplex. STGFlow enables efficient inference-time guidance using classifiers pre-trained on clean sequences, and can be used with any discrete flow method. Together, these components form a robust framework for controllable de novo sequence generation. We demonstrate state-of-the-art performance in conditional DNA promoter design, sequence-only protein generation, and target-binding peptide design for rare disease treatment. © 2025, CC BY-NC-ND.

关键词： Velocity distribution

来源：评论

学校读者我要写书评

暂无评论

Towards decoupling frontend enhancement and backend recognition in monaural robust ASR

引用

computer Speech & Language 2026年 95卷

作者： Yufeng Yang Ashutosh Pandey DeLiang Wang Department of Computer Science and Engineering The Ohio State University 2015 Neil Avenue Columbus 43210 OH United States Center for Cognitive and Brain Science The Ohio State University 1835 Neil Ave Columbus 43210 OH United States

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement (SE) algorithms. However, monaural SE has not been established as an effective frontend for automatic speech recognition (ASR) in noisy conditions compared to an ASR model trained on noisy speech directly. The divide between SE and ASR impedes the progress of robust ASR systems, especially as SE has made major advances in recent years. This paper focuses on eliminating this divide with an ARN (attentive recurrent network) time-domain, a TF-CrossNet time–frequency domain, and an MP-SENet magnitude-phase based enhancement model. The proposed systems decouple frontend enhancement and backend ASR, with the latter trained only on clean speech. Results on the WSJ, CHiME-2, LibriSpeech, and CHiME-4 corpora demonstrate that ARN, TF-CrossNet, and MP-SENet enhanced speech all translate to improved ASR results in noisy and reverberant environments, and generalize well to real acoustic scenarios. The proposed system outperforms the baselines trained on corrupted speech directly. Furthermore, it cuts the previous best word error rate (WER) on CHiME-2 by 28.4% relatively with a 5.6% WER, and achieves 3 . 3 / 4 . 4 % WER on single-channel CHiME-4 simulated/real test data without training on CHiME-4. We also observe consistent improvements using noise-robust Whisper as the backend ASR model.

关键词： CHiME-2 CHiME-4 Robust ASR Speech distortion Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

CHARACTERISTICS OF JUNCTIONS MADE BETWEEN PB AND BI2SR2CACU2O8+X

引用

IEEE TRANSACTIONS ON MAGNETICS 1991年第2期27卷 935-938页

作者： YANG, YF NORDMAN, JE Materials Science Program Department of Electrical and Computer Engineering University of Wisconsin Madison Madison WI USA

Investigations on the junctions made between Pb and polycrystalline Bi2Sr2CaCu2O8+x (BSCCO) are reported. The BSCCO surfaces were treated with number of methods including mechanically scraping, plasma sputtering, plasma oxidation, and Br etch before junctions were fabricated. The current-voltage characteristics and dynamic resistance (dV/dI) vs voltage have been measured at both 77K and 4.2K. We observed, among other features, a Pb gap structure similar to that seen in Pb/YBa2Cu3O7-delta junctions, a magnetic dependent supercurrent, an asymmetric I-V curve, and narrow resistance peaks. Properties of junctions prepared in different manners are compared. Both XPS and electrical studies indicated that Br etch is not suitable for the BiSrCaCuO system in spite of its successful application in YBa2Cu3O7-delta.

关键词： Plasma measurements Bismuth compounds Plasma applications Plasma properties Strontium Surface resistance Surface treatment Sputtering Oxidation Sputter etching

来源：评论

学校读者我要写书评

暂无评论

Neural Circuits for Any-Time Phrase Recognition with Applications in cognitive Models and Human-Robot Interaction 34

Neural Circuits for Any-Time Phrase Recognition with Applica...

引用

34th Annual Meeting of the cognitive science Society: Building Bridges Across cognitive sciences Around the World, CogSci 2012

作者： Veale, Richard Scheutz, Matthias Cognitive Science Program Indiana University United States Department of Computer Science Tufts University United States

ISBN: (纸本)9780976831884

Humans are remarkably good at recognizing spoken language, even in very noisy environments. Yet, artificial speech recognizers do not reach human level performance, nor do they typically even attempt to model human speech processing. In this paper, we introduce a biologically plausible neural model of real-time spoken phrase recognition which shows how the time-varying spiking activity of neurons can be integrated into word tokens. We present a proof-of-concept implementation of the model, which shows promise both in terms of recognition accuracy as well as recognition speed. The model is also pragmatically useful to cognitive modelers who require robust any-time speech recognition for their models such as real-time models of human-robot interaction. We thus also present such an example of embedding our model in a larger cognitive model, along with offline analysis of its performance on a speech corpus. © CogSci *** rights reserved.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Embodied enumeration: Appealing to activities for mathematical explanation

Embodied enumeration: Appealing to activities for mathematic...

引用

2006 AAAI Workshop

作者： Goldfain, Albert Department of Computer Science and Engineering Center for Cognitive Science University at Buffalo Buffalo NY 14260

ISBN: (纸本)1577352858

A computational cognitive agent capable of mathematical reasoning should be able to: (1) perform mental operations over abstract internal representations (e.g., counting numbers) and (2) perform physical operations over concrete external objects (e.g., counting apples). In a context of justification, both of these types of activity can contribute to mathematical explanations. In this paper, we focus on an agent's ability to enumerate external objects, the knowledge-level representational requirements (and side-effects) for such an ability, and the applicability of the enumeration result during an explanation. The SNePS knowledge-representation, reasoning, and acting system is used for a preliminary implementation of Cassie, our enumeration agent. The GLAIR architecture, which is used to model Cassie's embodiment, is also discussed. Copyright © 2006, American Association for Artificial Intelligence (***). All rights reserved.

关键词： cognitive systems

来源：评论

学校读者我要写书评

暂无评论

A Conceptual Exploration of Generative AI-Induced cognitive Dissonance and its Emergence in University-Level Academic Writing

arXiv

引用

arXiv 2025年

作者： Seran, Carl Errol Tan, Myles Joshua Toledo Karim, Hezerul Abdul AlDahoul, Nouar Biology Program College of Arts and Sciences University of St. La Salle Bacolod Philippines Department of Natural Sciences College of Arts and Sciences University of St. La Salle Bacolod Philippines Faculty of Education University of the Philippines Open University Los Baños Philippines Department of Electrical and Computer Engineering Herbert Wertheim College of Engineering University of Florida GainesvilleFL United States Department of Epidemiology College of Public Health and Health Professions College of Medicine University of Florida GainesvilleFL United States Department of Chemical Engineering College of Engineering and Technology University of St. La Salle Bacolod Philippines Department of Electronics Engineering College of Engineering and Technology University of St. La Salle Bacolod Philippines Yo-Vivo Corporation Bacolod Philippines Faculty of Engineering Multimedia University Persiaran Multimedia Cyberjaya Malaysia Department of Computer Science Division of Science New York University Abu Dhabi Abu Dhabi United Arab Emirates

The integration of Generative Artificial Intelligence (GenAI) intouniversity-level academic writing presents both opportunities and challenges,particularly in relation to cognitive dissonance (CD). This work explores howGenAI serves as both a trigger and amplifier of CD, as students navigateethical concerns, academic integrity, and self-efficacy in their writingpractices. By synthesizing empirical evidence and theoretical insights, weintroduce a hypothetical construct of GenAI-induced CD, illustrating thepsychological tension between AI-driven efficiency and the principles oforiginality, effort, and intellectual ownership. We further discuss strategiesto mitigate this dissonance, including reflective pedagogy, AI literacyprograms, transparency in GenAI use, and discipline-specific task *** approaches reinforce critical engagement with AI, fostering a balancedperspective that integrates technological advancements while safeguarding humancreativity and learning. Our findings contribute to ongoing discussions on AIin education, self-regulated learning, and ethical AI use, offering aconceptual framework for institutions to develop guidelines that align AIadoption with academic values. © 2025, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Distributed Multidisciplinary Design Optimization of the NASA Lift-Plus-Cruise Air Taxi Concept

Large-Scale Distributed Multidisciplinary Design Optimizatio...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： van Schie, Sebastiaan P. C. Ruh, Marius L. Fletcher, Andrew Warner, Michael Sperry, Mark Scotzniovsky, Luca Orndorff, Nicholas C. Xiang, Ru Yan, Jiayao Zhao, Han Krokowski, Joshua J. Chen, J.S. Sarojini, Darshan Gill, Hyunjune Lee, Seongkyu Tagg, Andrew Anderson, Ryan Green, Eric Joseph, Cibin Ning, Andrew Cheng, Zeyu Cao, Zhi Mi, Chunting Guibert, Alexandre T. R. Cronk, Ashley Kim, H. Alicia Meng, Y. Shirley Silva, Christopher Hwang, John T. University of California San Diego 9500 Gilman Dr La Jolla CA92093 United States Department of Mechanical and Aerospace Engineering University of California San Diego 9500 Gilman Dr La Jolla CA92093 United States Department of Structural Engineering University of California San Diego 9500 Gilman Dr La Jolla CA92093 United States Aerospace and Ocean Engineering Department Virginia Tech 1600 Innovation Dr BlacksburgVA24060 United States Department of Mechanical and Aerospace Engineering University of California Davis 1 Shields Avenue DavisCA95616 United States Mechanical Engineering Brigham Young University ProvoUT84602 United States Department of Electrical & Computer Engineering San Diego State University 5500 Campanile Dr San Diego92182 United States Structural Engineering Department University of California San Diego 9500 Gilman Dr La Jolla CA92093 United States Materials Science & Engineering Program University of California San Diego 9500 Gilman Dr La Jolla CA92093 United States Pritzker School of Molecular Engineering The University of Chicago ChicagoIL60607 United States NASA Ames Research Center Moffett FieldCA94035 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Large-scale gradient-based Multidisciplinary Design Optimization (MDO) can aid in the exploration of high-dimensional design spaces for novel air vehicle concepts, thereby leading to more efficient and economic designs. This paper builds on past works where we demonstrated large-scale physics-based MDO capabilities and applied these to NASA’s lift-plus-cruise electric air taxi concept. We extend this comprehensive mid-fidelity system-level optimization problem with high(er)-fidelity subsystem-level optimizations of various aircraft systems and mission phases, with the aim of further enhancing the accuracy and scope of the aforementioned system-level optimization problem: 1) Power minimization during the transition mission phase;2) Electrical powertrain topology optimization;3) Cell chemistry modeling and thermomechanical battery pack topology optimization;4) Shell-based coupled aero-elastic wing structure optimization. An Analytical Target Cascading-like distributed MDO architecture allows us to couple the system- and subsystem-level optimizations in order to arrive at a consistent and feasible design. We find that the system-level design is most heavily impacted by the reduced battery pack-level energy densities that stem from power peaks in the mission profile. These power peaks seem to result from the inefficient lift rotor blade designs that are needed to satisfy noise constraints. We draw conclusions based on trends in our results and give recommendations for future MDO studies of electrical air taxi vehicle concepts. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Shape optimization

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：