检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Chenxu Jian, Ping Huang, Mu School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Institute of Technology Beijing China

Implicit Discourse Relation Recognition (IDRR), which infers discourse relations without the help of explicit connectives, is still a crucial and challenging task for discourse parsing. Recent works tend to exploit the hierarchical structure information from the annotated senses, which demonstrate enhanced discourse relation representations can be obtained by integrating sense hierarchy. Nevertheless, the performance and robustness for IDRR are significantly constrained by the availability of annotated data. Fortunately, there is a wealth of unannotated utterances with explicit connectives, that can be utilized to acquire enriched discourse relation features. In light of such motivation, we propose a Prompt-based Logical Semantics Enhancement (PLSE) method for IDRR. Essentially, our method seamlessly injects knowledge relevant to discourse relation into pre-trained language models through prompt-based connective prediction. Furthermore, considering the prompt-based connective prediction exhibits local dependencies due to the deficiency of masked language model (MLM) in capturing global semantics, we design a novel self-supervised learning objective based on mutual information maximization to derive enhanced representations of logical semantics for IDRR. Experimental results on PDTB 2.0 and CoNLL16 datasets demonstrate that our method achieves outstanding and consistent performance against the current state-of-the-art models. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

DESIGN AND DEVELOPMENT OF MORPHOLOGICAL ANALYZER FOR TIGRIGNA VERBS USING HYBRID APPROACH

Research Square

引用

research Square 2023年

作者： Gebremeskel, Hagos Gebremedhin Chong, Feng Heyan, Huang Beijing Engineering Research Center of High Volume Language Information Processing Cloud Computing Applications Laboratory School of Computer Science and Technology Beijing Institute of Technology China Department of Computer Science Mekelle University Tigray Mekelle231 Ethiopia

Morphological analyzer is the base for various high-level NLP applications such as information retrieval, spell checking, grammar checking, machine translation, speech recognition, POS tagging and automatic sentence construction. This paper is carefully designed for design and analysis of morphological analyzer Tigrigna verbs using hybrid of memory learning and rules based approaches. The experiment have conducted using Python 3 where TiMBL algorithms IB2 and TRIBL2, and Finite State Transducer rules are used. The performance of the system has been evaluated using 10 fold cross validation technique. Testing was conducted using optimized parameter settings for regular verbs and linguistic rules of the Tigrigna language allomorph and phonology for the irregular verbs. The accuracy of the memory based approach with optimized parameters of TiMBL algorithm IB2 and TRIBL2 was 93.24% and 92.31%, respectively. Finally, the hybrid approach had an actual performance of 95.6% using linguistic rules for handling irregular and copula verbs. © 2023, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

MindLLM: Pre-training Lightweight Large Language Model from Scratch, Evaluations and Domain applications

arXiv

引用

arXiv 2023年

作者： Yang, Yizhe Sun, Huashan Li, Jiawei Liu, Runheng Li, Yinghao Liu, Yuhang Gao, Yang Huang, Heyan School of Computer Science Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Institute of Technology Southeast Academy of Information Technology China

Large Language Models (LLMs) have demonstrated remarkable performance across various natural language tasks, marking significant strides towards general artificial intelligence. While general artificial intelligence is leveraged by developing increasingly large-scale models, there could be another branch to develop lightweight custom models that better serve certain domains, taking into account the high cost of training and deploying LLMs and the scarcity of resources. In this paper, we present MindLLM, a novel series of bilingual lightweight large language models, trained from scratch, alleviating such burdens by offering models with 1.3 billion and 3 billion parameters. A thorough account of experiences accrued during large model development is given, covering every step of the process, including data construction, model architecture, evaluation, and applications. Such insights are hopefully valuable for fellow academics and developers. MindLLM consistently matches or surpasses the performance of other open-source larger models on some public benchmarks. We also introduce an innovative instruction tuning framework tailored for smaller models to enhance their capabilities efficiently. Moreover, we explore the application of MindLLM in specific vertical domains such as law and finance, underscoring the agility and adaptability of our lightweight models. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Privacy-preserving Surface Defect Detection Scheme for Strip Steel

A Privacy-preserving Surface Defect Detection Scheme for Str...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Xuan Tang Xiao Zheng Xiujun Wang Jun Huang School of Computer Science and Technology Anhui University of Technology Maanshan China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Maanshan China

As the Industrial Internet becomes an integral part of the steel industry, the next question is naturally how to combine powerful computing power as well as data sharing capabilities for effective detection of surface defects in strip steel. However, existing classification algorithms focus on the accuracy of the classification without considering how to protect the privacy of the manufacturer or the company, as the data is uploaded to the cloud and easily discovered by attackers. To address this problem, in this paper, we propose a privacy-preserving classification scheme that provides both privacy protection and improved classification accuracy in the industrial Internet. Specifically, our approach first adaptively encrypts the original steel image using a homomorphic encryption scheme. The homomorphic encryption scheme is followed by designing a convolutional neural network which can handle the encrypted images well and provide better classification accuracy. In addition, the execution efficiency of our method can be further improved under the edge computing architecture by using distributed computing with cloud-edge architecture. Experiments conducted on real image datasets of strip steel surface show that the encryption scheme not only protects the privacy of manufacturers or companies contained in the steel images and guarantees classification accuracy, but also outperforms existing methods in terms of efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MindLLM: Lightweight Large Language Model Pre-Training, Evaluation and Domain Application

SSRN

引用

SSRN 2024年

作者： Yang, Yizhe Sun, Huashan Li, Jiawei Liu, Runheng Li, Yinghao Liu, Yuhang Gao, Yang Huang, Heyan School of Computer Science Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China Beijing Institute of Technology Southeast Academy of Information Technology Fujian Putian China

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Boosting legal case retrieval by query content selection with large language models

arXiv

引用

arXiv 2023年

作者： Zhou, Youchao Huang, Heyan Wu, Zhijing School of Computer Science and Technology Beijing Institute of Technology Southeast Academy of Information Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China

Legal case retrieval, which aims to retrieve relevant cases to a given query case, benefits judgment justice and attracts increasing attention. Unlike generic retrieval queries, legal case queries are typically long and the definition of relevance is closely related to legal-specific elements. Therefore, legal case queries may suffer from noise and sparsity of salient content, which hinders retrieval models from perceiving correct information in a query. While previous studies have paid attention to improving retrieval models and understanding relevance judgments, we focus on enhancing legal case retrieval by utilizing the salient content in legal case queries. We first annotate the salient content in queries manually and investigate how sparse and dense retrieval models attend to those content. Then we experiment with various query content selection methods utilizing large language models (LLMs) to extract or summarize salient content and incorporate it into the retrieval models. Experimental results show that reformulating long queries using LLMs improves the performance of both sparse and dense models in legal case retrieval. © 2023, CC BY-NC-SA.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Focused Laser Differential Interferometry: Recent Developments and applications for Flow Measurements

Focused Laser Differential Interferometry: Recent Developmen...

引用

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

作者： Benitez, Elizabeth K. Ceruzzi, Andrew P. Gragston, Mark Parziale, Nicholaus J. Schmidt, Bryan E. Weisberger, Joshua M. High-Speed Aerodynamics Branch U.S. Air Force Research Laboratory Wright-Patterson AFB OH45433 United States Department of Engineering Science Oxford Thermofluids Institute University of Oxford OxfordOX2 0ES United Kingdom The University of Tennessee-Knoxville KnoxvilleTN37996 United States Stevens Institute of Technology HobokenNJ07030 United States Case Western Reserve University ClevelandOH44106 United States Advanced Measurements and Data Systems Branch NASA Langley Research Center HamptonVA23681 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Focused laser differential interferometry (FLDI), first introduced in the 1970s, has developed into a powerful tool for the analysis of turbulent dynamics and fluctuations in fluid flows ranging from subsonic to hypersonic. This paper provides a review of recent FLDI developments and applications, including discussions on the basic theory of the instrument, various forms of FLDI, multi-point techniques, utilization in fluid flow measurements, quantitative measurement capabilities, and more. © 2025, American institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Laser interferometry

来源：评论

学校读者我要写书评

暂无评论

Incorporating Option and Out-of-domain Knowledge for Multi-choice Machine Reading Comprehension 7

Incorporating Option and Out-of-domain Knowledge for Multi-c...

引用

7th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2021

作者： Xu, Yuan Shi, Shumin Huang, Heyan Beijing Institute of Technology School of Computer Science and Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China

ISBN: (纸本)9781665441490

Multi-choice Machine Reading Comprehension (MRC) requires the model to select the correct answer from a set of answer candidates given the corresponding passage and question. Previous studies mainly focus on complex matching networks to model the relationship among options, passage and question. However, these models obtain little improvement over the powerful Pre-trained Language Models (PLMs). In this paper, we propose a simple method to incorporate option knowledge from PLMs and introduce out-of-domain knowledge by multi-task learning skillfully. Our approach obtains state-of-the-art results on Chinese multi-choice MRC dataset ReCO and also effectively improves the performance on C3. © 2021 IEEE.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

CTourLLM: enhancing LLMs with Chinese tourism knowledge

引用

Cluster Computing 2025年第6期28卷 1-13页

作者： Wei, Qikai Yang, Mingzhi Wang, Jinqiang Mao, Wenwei Xu, Jiabo Ning, Huansheng School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Key Laboratory of Xinjiang Coal Resources Green Mining Ministry of Education Xinjiang Institute of Engineering Urumqi China Guangxi Tourism Development One-Click Tour Digital Cultural Tourism Industry Co. Ltd Guangxi China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing China

Recently, large language models (LLMs) have demonstrated their effectiveness in various natural language processing (NLP) tasks. However, the lack of tourism knowledge limits the performance of LLMs in tourist attraction presentations and travel planning. To address this challenge, we constructed a supervised fine-tuning dataset for the Chinese culture and tourism domain, named Cultour. This dataset consists of three parts: tourism knowledge base data, travelogues data, and tourism QA data. Additionally, we propose CTourLLM, a Qwen-based model supervised fine-tuned with Cultour, to improve the quality of information about attractions and travel planning. To evaluate the performance of CTourLLM, we proposed a human evaluation criterion named RRA (Relevance, Readability, Availability), and employed both automatic and human evaluation. The experimental results demonstrate that CTourLLM outperforms ChatGPT, achieving an improvement of 1.21 in BLEU-1 and 1.54 in Rouge-L, thereby validating the effectiveness of the response outcomes. Our proposed Cultour is accessible at https://***/mrweiqk/Cultour .

关键词：

来源：评论

学校读者我要写书评

暂无评论

ANTARCTICA AND THE SOUTHERN OCEAN

引用

BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY 2024年第8期105卷 S331-S370页

作者： Clem, K. R. Raphael, M. N. School of Geography Environment and Earth Sciences Victoria University of Wellington Wellington New Zealand Department of Geography University of California Los Angeles Los Angeles California Scripps Institution of Oceanography University of California San Diego La Jolla California Université Grenoble Alpes Institut des Géosciences de l’Environnement IRD CNRS Grenoble INP Grenoble France Department of Atmospheric and Oceanic Sciences University of Colorado Boulder Boulder Colorado Earth Science and Observation Center Cooperative Institute for Research in Environmental Sciences (ESOC/CIRES) University of Colorado Boulder Boulder Colorado Argentine Naval Hydrographic Service Buenos Aires Argentina Department of Earth and Environmental Science Temple University Philadelphia Pennsylvania Department of Meteorology University of Valparaíso Valparaíso Chile Center for Climate and Resilience Research (CR)2 Santiago Chile British Antarctic Survey Cambridge United Kingdom Science Systems and Applications Inc. Lanham Maryland NASA Goddard Space Flight Center Greenbelt Maryland Centre for Ocean River Atmosphere and Land Sciences (CORAL) Indian Institute of Technology Kharagpur Kharagpur India Royal Netherlands Meteorological Institute (KNMI) DeBilt The Netherlands Department of Marine Sciences University of Gothenburg Gothenburg Sweden National Institute of Water and Atmospheric Research Ltd. (NIWA) Auckland New Zealand Department of Geography Ohio University Athens Ohio NOAA/OAR Earth System Research Laboratory Global Monitoring Laboratory Boulder Colorado University of Colorado Boulder Boulder Colorado Marine Systems Modelling National Oceanography Center Southampton United Kingdom Department of Atmospheric and Oceanic Sciences University of Wisconsin-Madison Madison Wisconsin Antarctic Meteorological Research and Data Center Space Science and Engineering Center University of Wisconsin-Madison Madison Wisconsin Department of Geography Pennsylvania Sta

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：