检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Yixin Nath, Ankur Peng, Chunli Kuhnle, Alan Department of Computer Science & Engineering Texas A&M University College StationTX United States

For constrained, not necessarily monotone submodular maximization, all known approximation algorithms with ratio greater than 1/e require continuous ideas, such as queries to the multilinear extension of a submodular function and its gradient, which are typically expensive to simulate with the original set function. For combinatorial algorithms, the best known approximation ratios for both size and matroid constraint are obtained by a simple randomized greedy algorithm of Buchbinder et al. [9]: 1/e ≈ 0.367 for size constraint and 0.281 for the matroid constraint in O(kn) queries, where k is the rank of the matroid. In this work, we develop the first combinatorial algorithms to break the 1/e barrier: we obtain approximation ratio of 0.385 in O(kn) queries to the submodular set function for size constraint, and 0.305 for a general matroid constraint. These are achieved by guiding the randomized greedy algorithm with a fast local search algorithm. Further, we develop deterministic versions of these algorithms, maintaining the same ratio and asymptotic time complexity. Finally, we develop a deterministic, nearly linear time algorithm with ratio 0.377. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Are LLms Good Annotators for Discourse-level Event Relation Extraction?

Are LLMs Good Annotators for Discourse-level Event Relation ...

引用

2024 Conference on Empirical methods in Natural Language Processing, EmNLP 2024

作者： Wei, Kangda Gautam, Aayush Huang, Ruihong Department of Computer Science and Engineering Texas A&M University College StationTX United States

ISBN: (纸本)9798891761681

Large Language models (LLms) have demonstrated proficiency in a wide array of natural language processing tasks. However, its effectiveness over discourse-level event relation extraction (ERE) tasks remains unexplored. In this paper, we assess the effectiveness of LLms in addressing discourse-level ERE tasks characterized by lengthy documents and intricate relations encompassing coreference, temporal, causal, and subevent types. Evaluation is conducted using an commercial model, GPT-3.5, and an open-source model, LLamA-2. Our study reveals a notable underperformance of LLms compared to the baseline established through supervised learning. Although Supervised Fine-Tuning (SFT) can improve LLms performance, it does not scale well compared to the smaller supervised baseline model. Our quantitative and qualitative analysis shows that LLms have several weaknesses when applied for extracting event relations, including a tendency to fabricate event mentions, and failures to capture transitivity rules among relations, detect long distance relations, or comprehend contexts with dense event mentions. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Evaluating Gender Bias of LLms in making morality Judgements

Evaluating Gender Bias of LLMs in Making Morality Judgements

引用

2024 Findings of the Association for Computational Linguistics, EmNLP 2024

作者： Bajaj, Divij Lei, Yuanyuan Tong, Jonathan Huang, Ruihong Department of Computer Science and Engineering Texas A&M University College StationTX United States

ISBN: (纸本)9798891761681

Large Language models (LLms) have shown remarkable capabilities in a multitude of Natural Language Processing (NLP) tasks. However, these models are still not immune to limitations such as social biases, especially gender bias. This work investigates whether current closed and open-source LLms possess gender bias, especially when asked to give moral opinions. To evaluate these models, we curate and introduce a new dataset GenmO (Gender-bias in morality Opinions) comprising parallel short stories featuring male and female characters respectively. Specifically, we test models from the GPT family (GPT-3.5-turbo, GPT-3.5turbo-instruct, GPT-4-turbo), Llama 3 and 3.1 families (8B/70B), mistral-7B and Claude 3 families (Sonnet and Opus). Surprisingly, despite employing safety checks, all production-standard models we tested display significant gender bias with GPT-3.5-turbo giving biased opinions in 24% of the samples. Additionally, all models consistently favour female characters, with GPT showing bias in 68-85% of cases and Llama 3 in around 81-85% instances. Additionally, our study investigates the impact of model parameters on gender bias and explores real-world situations where LLms reveal biases in moral decision-making. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Sentence-level media Bias Analysis with Event Relation Graph

Sentence-level Media Bias Analysis with Event Relation Graph

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Lei, Yuanyuan Huang, Ruihong Department of Computer Science and Engineering Texas A&M University College StationTX United States

ISBN: (纸本)9798891761148

media outlets are becoming more partisan and polarized nowadays. In this paper, we identify media bias at the sentence level, and pinpoint bias sentences that intend to sway readers’ opinions. As bias sentences are often expressed in a neutral and factual way, considering broader context outside a sentence can help reveal the bias. In particular, we observe that events in a bias sentence need to be understood in associations with other events in the document. Therefore, we propose to construct an event relation graph to explicitly reason about event-event relations for sentence-level bias identification. The designed event relation graph consists of events as nodes and four common types of event relations: coreference, temporal, causal, and subevent relations. Then, we incorporate event relation graph for bias sentences identification in two steps: an event-aware language model is built to inject the events and event relations knowledge into the basic language model via soft labels;further, a relation-aware graph attention network is designed to update sentence embedding with events and event relations information based on hard labels. Experiments on two benchmark datasets demonstrate that our approach with the aid of event relation graph improves both precision and recall of bias sentence identification. ©2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

QORA: Zero-Shot Transfer via Interpretable Object-Relational model Learning 41

QORA: Zero-Shot Transfer via Interpretable Object-Relational...

引用

41st International Conference on machine Learning, ICmL 2024

作者： Stella, Gabriel Loguinov, Dmitri Department of Computer Science & Engineering Texas A&M University College StationTX United States

Although neural networks have demonstrated significant success in various reinforcement-learning tasks, even the highest-performing deep models often fail to generalize. As an alternative, object-oriented approaches offer a promising path towards better efficiency and generalization;however, they typically address narrow problem classes and require extensive domain knowledge. To overcome these limitations, we introduce QORA, an algorithm that constructs models expressive enough to solve a variety of domains, including those with stochastic transition functions, directly from a domain-agnostic object-based state representation. We also provide a novel benchmark suite to evaluate learners' generalization capabilities. In our test domains, QORA achieves 100% predictive accuracy using almost four orders of magnitude fewer observations than a neural-network baseline, demonstrates zero-shot transfer to modified environments, and adapts rapidly when applied to tasks involving previously unseen object interactions. Finally, we give examples of QORA's learned rules, showing them to be easily interpretable. Copyright 2024 by the author(s)

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

machine Learning Applications for Online Partial Discharge Detection, Classification, and Localization in Power Transformers: A Review 4

Machine Learning Applications for Online Partial Discharge D...

引用

4th International Conference on Smart Grid and Renewable Energy, SGRE 2024

作者： Tag, Ameera Refaat, Shady S. Kameli, Sayed mohammad Saleh, mohammad Alshaikh Texas A&M University at Qatar Electrical and Computer Engineering Department Doha Qatar University of Hertfordshire School of Physics Engineering and Computer Science Department of Engineering United Kingdom Texas A&M University Department of Electrical and Computer Engineering College Station United States

ISBN: (纸本)9798350306262

The power transformer is a crucial asset and a fundamental component of the power grid. Assets undergo aging due to the stresses present in insulation materials. Partial discharges (PDs) are the most common fault source in power transformers and an excellent indicator of aging. The detection, classification, and localization of PD activities in power transformers are persisting challenges, while techniques utilizing machine learning (mL) are widely sought to deal with those challenges. Existing mL techniques show promising results with an elevated level of accuracy and precision. However, there is a lack of conventional mL-based real-time monitoring capability. Therefore, this paper presents a comprehensive review of the application of mL techniques for online PD activity detection, classification, and localization in power transformers, focusing on supervised, unsupervised, semi-supervised, and reinforcement learning techniques. In addition, this paper explores the challenges, future trends, perspectives, and outlook of machine learning for online transformer fault analysis. © 2024 IEEE.

关键词： Partial discharges

来源：评论

学校读者我要写书评

暂无评论

Boosting Logical Fallacy Reasoning in LLms via Logical Structure Tree

Boosting Logical Fallacy Reasoning in LLMs via Logical Struc...

引用

2024 Conference on Empirical methods in Natural Language Processing, EmNLP 2024

作者： Lei, Yuanyuan Huang, Ruihong Department of Computer Science and Engineering Texas A&M University College StationTX United States

ISBN: (纸本)9798891761643

Logical fallacy uses invalid or faulty reasoning in the construction of a statement. Despite the prevalence and harmfulness of logical fallacies, detecting and classifying logical fallacies still remains a challenging task. We observe that logical fallacies often use connective words to indicate an intended logical relation between two arguments, while the argument semantics does not actually support the logical relation. Inspired by this observation, we propose to build a logical structure tree to explicitly represent and track the hierarchical logic flow among relation connectives and their arguments in a statement. Specifically, this logical structure tree is constructed in an unsupervised manner guided by the constituency tree and a taxonomy of connectives for ten common logical relations, with relation connectives as non-terminal nodes and textual arguments as terminal nodes, and the latter are mostly elementary discourse units. We further develop two strategies to incorporate the logical structure tree into LLms for fallacy reasoning. Firstly, we transform the tree into natural language descriptions and feed the textualized tree into LLms as a part of the hard text prompt. Secondly, we derive a relation-aware tree embedding and insert the tree embedding into LLms as a soft prompt. Experiments on benchmark datasets demonstrate that our approach based on logical structure tree significantly improves precision and recall for both fallacy detection and fallacy classification. © 2024 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

AVTAR Cyber Shield: A Comprehensive Framework for machine Learning-Enhanced Cybersecurity in Cyber-Physical Environment

AVTAR Cyber Shield: A Comprehensive Framework for Machine Le...

引用

2024 International Conference on Circuit, Systems and Communication, ICCSC 2024

作者： Sykam, Venkata Narendra Kumar Goyal, Ayush Nijim, mais mishra, Avdesh Hicks, David Texas A&m University Kingsville Department of Electrical Engineering and Computer Science Kingsville United States

ISBN: (纸本)9798350365306

In the rapidly advancing era of self-driving cars, the imperative of ensuring robust cybersecurity measures to safeguard against evolving threats becomes paramount. This paper investigates the intricate cyber-physical systems within autonomous vehicles, emphasizing the critical role of 'AVTAR Cyber Shield' as a comprehensive cybersecurity framework for fortifying against potential vulnerabilities. The paper provides a basic understanding on how autonomous car manufacturers and/or technology providers like ***, Waymo, WeRide and Zoox implement safety measures which prompted us to introduce a new driver's self-preparation safety module before riding to qualitatively evaluate the preride risk(s) associated with self-driving cars. An exploration of current cybersecurity threats, and compliance with industry standards, is complemented by the identification of challenges such as technical complexities and human factors. The paper concludes with analyzing the existing statistical result focus on recent risk calculation, contributing to the future trends and innovations, proposing recommendations that advocate for continuous monitoring, best practices, and adaptive strategies to address evolving cybersecurity threats and traditional human un/known mistakes. This comprehensive examination contributes valuable insights to the discourse on securing the future of self-driving vehicles, offering guidance for researchers, practitioners, and policymakers navigating the complex landscape of autonomous transportation. © 2024 IEEE.

关键词： Shielding

来源：评论

学校读者我要写书评

暂无评论

Automated Vulnerability Detection in Source Code Using Deep Representation Learning 14

Automated Vulnerability Detection in Source Code Using Deep ...

引用

2024 IEEE 14th Annual Computing and Communication Workshop and Conference, CCWC 2024

作者： Seas, Christoforos Fitzpatrick, Glenn Hamilton, John A. Carlisle, martin C. University of Cyprus Computer Science Nicosia Cyprus Texas A&m University Computer Science and Engineering College StationTX United States

ISBN: (纸本)9798350360134

Each year, software vulnerabilities are discovered, which pose significant risks of exploitation and system compromise. We present a convolutional neural network model that can successfully identify bugs in C code. We trained our model using two complementary datasets: a machine-labeled dataset created by Draper Labs using three static analyzers and the NIST SATE Juliet human-labeled dataset designed for testing static analyzers. In contrast with the work of Russell et al. on these datasets, we focus on C programs, enabling us to specialize and optimize our detection techniques for this language. After removing duplicates from the dataset, we tokenize the input into 91 token categories. The category values are converted to a binary vector to save memory. Our first convolution layer is chosen so that the entire encoding of the token is presented to the filter. We use two convolution and pooling layers followed by two fully connected layers to classify programs into either a common weakness enumeration category or as "clean."We obtain higher recall than prior work by Russell et al. on this dataset when requiring high precision. We also demonstrate on a custom Linux kernel dataset that we are able to find real vulnerabilities in complex code with a low false-positive rate. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Using the interactive software FossilSketch to teach micropaleontology to undergraduate students

引用

Journal of Geoscience Education 2025年第2期73卷 133-153页

作者： Stepanova, Anna Belanger, Christina Anwar, Saira Stanley, Christine Nath, Ankur Cherian, Josh Hammond, Tracy Department of Computer Science and Engineering Texas A&M University College Station TX United States Department of Geology and Geophysics Texas A&M University College Station TX United States Department of Multidisciplinary Engineering Texas A&M University College Station TX United States Department of Educational Administration and Human Resource Development Texas A&M University College Station TX United States Institute for Engineering Education and Innovation Texas A&M University College Station TX United States

micropaleontology is a critical tool for determining the ages of geologic records, reconstructing ancient environments, and monitoring modern ecosystem health. However, most students are not exposed to micropaleontology in their college coursework. To enable non-expert instructors to integrate microfossil identification training in their undergraduate courses, we developed FossilSketch, an interactive web-based educational tool that introduces students to the basics of micropaleontology and guides students through a scaffolded learning experience that develops microfossil identification skills. Here we test the impact of FossilSketch on students’ ability to learn micropaleontology skills, such as identification of microfossils to genus level and basics of fossil data analysis, using data on students’ performance and survey responses collected in an undergraduate paleontology course for geology majors at a large public university. A total of 112 students took part in this study. Analysis of classroom assessments showed that junior and senior geology majors who used FossilSketch were better able to understand the process of microfossil identification, recognize morphological characteristics, and achieve a correct identification than those who did not use FossilSketch. Students who used FossilSketch needed to ask the teaching assistant fewer questions and felt better prepared for specimen-based work than students who did not use FossilSketch. These results suggest that FossilSketch improves students’ understanding of the microfossil identification process. © 2024 National Association of Geoscience Teachers.

关键词： micropaleontology Taxonomy undergraduate education

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：