检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

14,413 篇 会议
650 篇 期刊文献
101 册 图书
40 篇 学位论文
1 篇 科技报告

馆藏范围

15,204 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

10,937 篇 工学
- 10,278 篇 计算机科学与技术...
- 5,404 篇 软件工程
- 1,460 篇 信息与通信工程
- 953 篇 电气工程
- 875 篇 控制科学与工程
- 446 篇 生物工程
- 221 篇 网络空间安全
- 220 篇 化学工程与技术
- 186 篇 机械工程
- 174 篇 生物医学工程（可授...
- 141 篇 电子科学与技术（可...
- 100 篇 仪器科学与技术
- 100 篇 安全科学与工程
2,473 篇 理学
- 1,150 篇 数学
- 649 篇 物理学
- 518 篇 生物学
- 391 篇 统计学（可授理学、...
- 241 篇 系统科学
- 232 篇 化学
2,413 篇 管理学
- 1,747 篇 图书情报与档案管...
- 754 篇 管理科学与工程(可...
- 239 篇 工商管理
- 104 篇 公共管理
1,761 篇 文学
- 1,709 篇 外国语言文学
- 184 篇 中国语言文学
510 篇 医学
- 299 篇 临床医学
- 282 篇 基础医学(可授医学...
- 112 篇 公共卫生与预防医...
277 篇 法学
- 249 篇 社会学
237 篇 教育学
- 224 篇 教育学
100 篇 农学
97 篇 经济学
9 篇 艺术学
7 篇 哲学
4 篇 军事学

主题

3,523 篇 natural language...
1,768 篇 natural language...
952 篇 computational li...
736 篇 semantics
680 篇 machine learning
606 篇 deep learning
520 篇 natural language...
345 篇 computational mo...
334 篇 training
331 篇 sentiment analys...
330 篇 accuracy
325 篇 large language m...
320 篇 feature extracti...
311 篇 data mining
290 篇 speech processin...
263 篇 speech recogniti...
250 篇 transformers
235 篇 neural networks
217 篇 iterative method...
211 篇 support vector m...

机构

85 篇 carnegie mellon ...
51 篇 university of ch...
45 篇 carnegie mellon ...
44 篇 tsinghua univers...
42 篇 zhejiang univers...
42 篇 national univers...
38 篇 nanyang technolo...
36 篇 university of wa...
35 篇 univ chinese aca...
34 篇 university of sc...
34 篇 carnegie mellon ...
33 篇 stanford univers...
32 篇 gaoling school o...
32 篇 school of artifi...
32 篇 alibaba grp peop...
29 篇 tsinghua univ de...
28 篇 harbin institute...
28 篇 peking universit...
27 篇 language technol...
26 篇 microsoft resear...

作者

55 篇 zhou guodong
50 篇 neubig graham
46 篇 liu yang
39 篇 sun maosong
36 篇 zhang min
34 篇 liu qun
33 篇 smith noah a.
28 篇 schütze hinrich
27 篇 liu zhiyuan
27 篇 lapata mirella
26 篇 wen ji-rong
24 篇 chang kai-wei
23 篇 zhou jie
23 篇 yang diyi
23 篇 zhao hai
23 篇 zhao wayne xin
21 篇 chua tat-seng
20 篇 dredze mark
18 篇 biemann chris
18 篇 fung pascale

语言

14,611 篇 英文
481 篇 其他
104 篇 中文
18 篇 法文
15 篇 土耳其文
2 篇 西班牙文
2 篇 俄文

检索条件"任意字段=Conference on empirical methods in natural language processing"

共 15205 条记录，以下是311-320 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Can LLMs Clarify? Investigation and Enhancement of Large language Models on Argument Claim Optimization 31

Can LLMs Clarify? Investigation and Enhancement of Large Lan...

引用

31st International conference on Computational Linguistics, COLING 2025

作者： Wang, Yiran He, Ben Chen, Xuanang Sun, Le School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Chinese Information Processing Laboratory Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761964

In argumentation, the claim is the foundational proposition that underpins the argument, serving as the central pillar upon which the argument is constructed. It guides the subsequent presentation of evidence, reasoning, and analysis, thereby facilitating the audience's understanding of the core issue. Therefore, ensuring that the claim is precise and unambiguous is crucial for constructing a coherent and persuasive argument. While Large language Models (LLMs) have demonstrated proficiency in text rewriting tasks such as style transfer and query rewriting, their application to claim optimization remains unexplored. Unlike other rewriting tasks, claim clarification requires the model to rewrite ambiguous or unclear segments of the claim, enhance the content by adding omitted key details, and eliminate redundant or verbose elements. Addressing this gap, this paper evaluates the performance of LLMs on the claim clarification task across various settings. While popular rewriting evaluation methods such as BLEU and ROUGE rely on exact word matching, this paper introduces a novel semantic evaluation approach based on a sliding window mechanism. Three distinct LLMs, including LLama2, Mistral, and Qwen2, are assessed for their ability to clarify arguments through zero-shot or few-shot prompting, and supervised fine-tuning (SFT). Additionally, we propose a reinforcement learning-based clarification approach that optimally balances content preservation with claim clarity, thereby augmenting the performance of LLMs on the claim clarification task. © 2025 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

Research on the Improvement of Human-Machine Collaborative Machine Translation Model Based on Internet 14th

Research on the Improvement of Human-Machine Collaborative M...

引用

14th International conference on Frontier Computing, FC 2024

作者： Sun, Wei Yao, Man Foreign Language School Anhui Xinhua University Anhui Hefei China

ISBN: (纸本)9789819627936

Machine translation is a key study subject in computer science that has drawn interest from a wide range of academic disciplines, including linguistics, philosophy, psychology, physics, and engineering. Its journey over the last seventy years has been from the limelight to the back burner to the vanguard, then back to the forefront, demonstrating the use of modern research techniques and its continued importance in commerce and academics. The two basic strategies in machine translation are rule-based and corpus-based methods, and hybrid models that combine the two have grown in popularity over the last decade. The development of corpus-based methods that take advantage of breakthroughs in computational linguistics and natural language processing has enabled the emergence of niche machine translation solutions that are well-suited to specific fields and market segments. In this paper, we introduce a new, collaborative human-machine translation model based on an Internet scenario that differs from traditional methods to MT. Unlike the traditional MT model, in which all learning is automatically machine-driven, the suggested technique mixes human review with C-value methods to improve translation quality. In other words, this innovative approach integrates human experience with all stages of the MT process to restore machine performance to levels comparable to those of human translators. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

15th International conference on Software Business, ICSOB 2024

15th International Conference on Software Business, ICSOB 20...

引用

15th International conference on Software Business, ICSOB 2024

ISBN: (纸本)9783031858482

The proceedings contain 36 papers. The special focus in this conference is on Software Business. The topics include: Digital Sovereignty: Affordances in Open Source Projects;The Ethical Landscape in Public Procurement of ICT Systems;Exploring Classification Consistency of natural language Requirements Using GPT-4o;unveiling the Skills and Responsibilities of Serverless Practitioners: An empirical Investigation;on the Way to the Best Information System of the Future – Reflections on Scenarios in Favor of Good Technology Development;what Affects Developer Experience in Software Platforms?;enabling Inter-organizational Data Sharing: Towards a Method for Assessing Data Assets;Fairness in AI Systems Development: Beyond EU AI Act Compliance;The EU AI Act is a Good Start But Falls Short;Professionals’ Opinions on the Use of AI Software for HRM;Emotion AI in Workplace Environments: A Case Study;exploring the Factors that Impact the Half-Life of Software;exploring Diversity-Driven Power Dynamics in Software Engineering Environments: Insights from a Qualitative Study;Towards Sustainable ICT Solutions: Analyzing Call for Tender Documents;exploring Perceptions of Blockchain in Cross-Border Workforce Mobility;Experience of Gender Among Professionals in Finnish IT Companies;secondary Use of Health Data: Centralized Structure and Information Security Frameworks in Finland;Sustainable ICT Procurement: Data-Driven Decision-Making in B2B Green ICT Adoption;integrating Sustainability into Scrum Agile Software Development: An Action Research Approach;optimizing for Sustainability: Product Ops and Software Waste Reduction;designing for Sustainability When Architecture Standards are Involved: An Industrial Case Study;challenges in Incorporating Sustainability Practices in the Software Lifecycle;pre-release Experimentation in Indie Game Development: An Interview Survey;marketplace for Multi-party Development of Artificial Intelligence Systems: Perceptions on Value Creation;Data-Limited Co

关键词：

来源：评论

学校读者我要写书评

暂无评论

Universal Low-Resource Speech Synthesis Via Phoneme Fusion Coordinating Low-Rank Decomposition

Universal Low-Resource Speech Synthesis Via Phoneme Fusion C...

引用

2025 IEEE International conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Li, Yanliang Yu, Zhengtao Wang, Linqin Gao, Shengxiang Dong, Ling Wang, Wenjun Info. Engineering and Automation Yunnan Key Lab. of AI Kunming University of Tech. and Sci. Kunming China

ISBN: (纸本)9798350368741

Recent advancements in end-to-end text-to-speech models have made significant progress. However, these approaches based on high-resource languages, are inapplicable for low-resource languages, and existing low-resource speech synthesis methods are typically specific to single languages. Consequently, the pursuit of a universal methodology for low-resource speech synthesis emerges as a critical problem that requires immediate attention. Unlike previous works, we propose a novel and universal approach for multiple low-resource languages by leveraging phoneme fusion coordinating low-rank decomposition in a pre-trained multilingual model. Specifically, by establishing a multilingual phoneme dictionary through phoneme fusion and applying parameter freezing and matrix decomposition techniques for fine-tuning, the proposed method was extensively evaluated across four different languages, each utilizing approximately 3 hours of speech data. The experimental results demonstrate that the quality of the synthesized speech surpasses current mainstream methods for low-resource speech synthesis, achieving outcomes comparable to those trained with tens of hours of data. Audio samples are available at https://***/***. © 2025 IEEE.

关键词： low-resource language matrix decomposition phoneme fusion

来源：评论

学校读者我要写书评

暂无评论

InVideo Search: Scene Description Clustering and Integrating Image and Audio Captioning for Enhanced Video Search 21st

InVideo Search: Scene Description Clustering and Integrating...

引用

21st International conference on Distributed Computing and Intelligent Technology

作者： Khan, Almira Asif Muhammed Shaji, Asher Mathews Sujith, Devika Nath, Aneesh G. Udmale, Sandeep S. TKM Coll Engn Dept Comp Sci & Engn Kollam Kerala India Veermata Jijabai Technol Inst VJTI Dept Comp Engn & Informat Technol Mumbai 400019 Maharashtra India

ISBN: (纸本)9783031814037;9783031814044

In the digital era, the vast amount of long videos highlights the need for an advanced system to efficiently find specific segments based on text descriptions. The proposed solution aims to develop a video content retrieval system by utilizing established tools in video analysis, image/video captioning, and information retrieval. The work is organized into three modules: Keyframe extraction, Captioning, and Query-based searching. Our primary focus is on effectively identifying key elements within these videos, achieving a semantic understanding of these videos in the form of captions, and establishing precise matches of user queries. In short, users input descriptive text prompts, and the application, equipped with pre-trained models, promptly and accurately identifies and retrieves the video segments. This application carries significant potential across various domains, from enabling efficient scene location in movies to helping extract knowledge from educational lectures. Furthermore, this research fundamentally departs from conventional video search methods that heavily rely on metadata or manually assigned tags, which often fall short of capturing the nuances of video content. This work also focuses on a multimodal captioning strategy to integrate more semantic content. Clustering of captions was also incorporated to improve search performance in the case of long videos. This approach allows us to deliver a robust and efficient solution, taking advantage of the extensive knowledge and research underlying these established technologies. Beyond the immediate applications, this research has broader applications in fields like natural language understanding, multimedia analysis, and information retrieval.

关键词： Clustering Keyframe extraction natural language processing Video content retrieval system

来源：评论

学校读者我要写书评

暂无评论

Automatic Extraction and Formalization of Temporal Requirements from Text: A Survey 28th

Automatic Extraction and Formalization of Temporal Require...

引用

28th International conference on Enterprise Design, Operations, and Computing, EDOC 2024

作者： Barrientos, Marisol Winter, Karolin Rinderle-Ma, Stefanie Technical University of Munich Garching Germany Eindhoven University of Technology Eindhoven Netherlands

ISBN: (纸本)9783031783371

natural language processing has opened new paths for business process management and requirements engineering, particularly in automating the extraction and formalization of temporal requirements from diverse documents such as system specifications, legal texts, and business process descriptions. Recently, approaches have been introduced to automate this task, employing various document formats as input and targeting different formal specifications. However, a key challenge persists: effectively comparing these approaches and choosing the most suitable one for a specific task. This paper aims to bridge this research gap by conducting a systematic literature review, including a detailed analysis and comparing existing approaches. This comparison is crucial to determine if the latest Large language Model-based solutions could surpass existing methods in effectiveness and ease of use. The systematic literature review enables users to select the most suitable method based on their data and end goals. Moreover, this work proposes the NL2MTL (https://***/marisol-barrientos/nl2mtl, DLA: 22.04.2024) method to bridge some of the gaps identified in the literature analysis, i.e., establishing a comparable assessment method, under-representation of legal texts, poor output context management, and the necessity to automate the formalization of requirements, considering both quantitative and qualitative aspects of time. Addressing the latter aspect, we select Metric Temporal Logic (MTL) as formalization and provide the associated prompts and an evaluation of the NL2MTL output. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Administrative data processing

来源：评论

学校读者我要写书评

暂无评论

CEEMDAN–WTD Denoising Method for Enhanced Magnetic Memory Detection Signal of Defects 16

CEEMDAN–WTD Denoising Method for Enhanced Magnetic Memory D...

引用

16th International conference on Signal processing Systems, ICSPS 2024

作者： Ji, Shouhong Yan, Jie Liu, Yang He, Guojun National Pipeline Network Group Zhejiang Natural Gas Pipeline Network Co. Ltd Hangzhou310000 China

ISBN: (纸本)9781510689251

During the enhanced magnetic memory detection of defects, many interference signals appear in the detection signal, which makes it difficult to accurately extract the characteristics of the defect signals and significantly affects the detection effectiveness. When the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is employed independently for signal denoising, the noise and feature signals of the transition components will be retained or removed. When wavelet threshold denoising (WTD) is employed independently for signal denoising, the denoising effect is restricted because of the difficulty in determining the number of decomposition layers m and wavelet basis function. To solve these problems, a denoising method for enhanced magnetic memory detection signals based on CEEMDAN and WTD, called CEEMDAN–WTD, is proposed in the paper. Firstly, the correlation coefficient R of the signal components obtained by performing decomposition with the CEEMDAN method is calculated, and the signal components are divided into noise-dominant components, transition components, and useful signal components based on the R. Subsequently, WTD is employed to perform denoising on the two order signal components before and after transition components IMF(k − 2) ~ IMF(k + 2) obtained from the CEEMDAN method. Ultimately, the denoising components IMF(k − 2) ~ IMF(k + 2) and high-order useful signal components obtained by the CEEMDAN method are selected for signal reconstruction to obtain a denoised signal. To validate the effectiveness of the proposed method, the denoising effects of the CEEMDAN–WTD, CEEMDAN, and WTD methods were compared based on the signal-to-noise ratio (SNR). The comparison indicated that the CEEMDAN–WTD denoising method significantly enhanced the denoising effect, and the SNRs of the components of the magnetic field signal could be increased by up to 8.24% and 45.88%, respectively, indicating that the CEEMDAN-WTD denoising method is relativel

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Caskow: Context-Aware Stance Detection Using External Knowledge-Augmented LLM

Caskow: Context-Aware Stance Detection Using External Knowle...

引用

International conference on Web Research (ICWR)

作者： Maryam Shafiei Hossein Rahmani Amirhossein Derakhshan Milad Allahgholi School of Computer Engineering Iran University of Science and Technology Tehran Iran

ISBN: (数字)9798331508913

ISBN: (纸本)9798331508920

Stance detection in texts is an important task in natural language processing with diverse applications in political, economic and marketing. The research conducted in this area is categorized into traditional methods, deep learning methods and language model-based methods. However, to the best of our knowledge, none of these methods have effectively addressed context-aware stance detection. In this paper, we propose a method called CASKOW, which first collects context for a given text from Wikipedia as an external resource using information retrieval techniques and then employs the context alongside a large language model (LLM) to detect the stance. Experimental results show that CASKOW achieves a 7% improvement in F1-measure when the label “none” is included and a 10 % improvement when the label “none” is excluded, compared to models that do not utilize contextual information. Additionally, non-numerical interpretation of results reveals key insights, allowing for the identification of errors and challenges in stance detection datasets.

关键词： Economics Deep learning Large language models Biological system modeling Encyclopedias Context awareness natural language processing Internet Online services Context modeling

来源：评论

学校读者我要写书评

暂无评论

IDE: A Multi-Agent-Driven Iterative Framework for Dynamic Evaluation of LLMs

IDE: A Multi-Agent-Driven Iterative Framework for Dynamic Ev...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Xin Tong Bo Jin Jingya Wang Wenpeng Xing Tian Xia Meng Han People’s Public Security University of China Beijing China The Third Research Institute of the Ministry of Public Security of China China Zhejiang University Hangzhou China Renmin University of China Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

With the widespread use of large language models (LLMs) in natural language processing, traditional evaluation methods based on static datasets have become inadequate to fully capture their performance and generalization capabilities. To address this challenge, we propose an Iterative Dynamic Evaluation (IDE) framework, which utilizes a multi-agent system to systematically evaluate LLMs. The innovation of IDE lies in its iterative enhancement and comparative selection mechanisms. Through successive rounds of data augmentation, the framework emulates evolutionary processes by progressively increasing sample complexity, while competitive selection ensures only the optimal samples are retained. This iterative optimization and filtering produce increasingly challenging and diverse datasets. Experimental results demonstrate that IDE more effectively exposes the limitations of models in complex tasks compared to traditional methods, providing a more comprehensive foundation for the evaluation, optimization, and application of LLMs.

关键词： Technological innovation System performance Scalability Refining Signal processing natural language processing Iterative methods Speech processing Optimization Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

BertTab: Table Learning with Feature Descriptions and Context 7th

BertTab: Table Learning with Feature Descriptions and Contex...

引用

7th Chinese conference on Pattern Recognition and Computer Vision

作者： Xie, Meng An, Haibing Han, Songjun Mao, Jiangtao Jiang, Ying Wang, Jiajia Xinjiang Univ Urumqi Peoples R China

ISBN: (纸本)9789819787944;9789819787951

Tabular data is widely used as a common form of relational data in many industries where machine learning is applied, especially in finance, healthcare, and industry. However, traditional methods often do not fully consider the information embedded in the samples in the tables, including the meaning of the features themselves (column descriptions) as well as the contextual information. In this paper, we propose the BertTab model, which transforms a table sample into a sentence describing that sample by using an utterance template into which the category features of the table sample are populated. The sentences describing the sample are then converted into powerful contextual embeddings using the pre-trained Bert model. Finally, the context-embedded features are fused with the original features to obtain richer and more complete features of the sample, thus achieving higher performance. We evaluated the model on three datasets. Compared to the benchmark model, BertTab improves the AUC-ROC, AUC-PR, and accuracy by an average of 2.10, 4.43, and 0.48% on the three datasets, respectively. The ablation experiments demonstrate the positive effect of introducing category feature column descriptions and considering sample category feature contexts with the fusion of raw features on model effectiveness improvement.

关键词： Tabular data Contextual information Feature extraction Feature fusion natural language processing

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 28 29 30 31 32 33 34 35 36 37 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：