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

6,379 篇 会议
145 篇 期刊文献
2 册 图书

馆藏范围

6,526 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

5,103 篇 工学
- 4,993 篇 计算机科学与技术...
- 2,624 篇 软件工程
- 630 篇 信息与通信工程
- 397 篇 控制科学与工程
- 157 篇 电气工程
- 132 篇 网络空间安全
- 109 篇 生物工程
- 72 篇 化学工程与技术
- 60 篇 机械工程
- 53 篇 安全科学与工程
- 44 篇 农业工程
- 44 篇 生物医学工程（可授...
1,385 篇 文学
- 1,370 篇 外国语言文学
- 150 篇 中国语言文学
1,280 篇 管理学
- 981 篇 图书情报与档案管...
- 378 篇 管理科学与工程(可...
- 134 篇 工商管理
1,015 篇 理学
- 596 篇 数学
- 233 篇 物理学
- 152 篇 统计学（可授理学、...
- 141 篇 生物学
- 74 篇 化学
- 55 篇 系统科学
164 篇 法学
- 157 篇 社会学
128 篇 医学
- 96 篇 临床医学
- 60 篇 基础医学(可授医学...
- 53 篇 公共卫生与预防医...
85 篇 教育学
- 81 篇 教育学
56 篇 经济学
- 55 篇 应用经济学
48 篇 农学
- 48 篇 作物学
2 篇 艺术学
1 篇 哲学

主题

928 篇 natural language...
847 篇 computational li...
747 篇 natural language...
382 篇 semantics
313 篇 accuracy
238 篇 large language m...
211 篇 deep learning
193 篇 training
190 篇 machine learning
168 篇 computational mo...
165 篇 sentiment analys...
137 篇 transformers
132 篇 data models
131 篇 feature extracti...
108 篇 iterative method...
98 篇 analytical model...
93 篇 syntactics
90 篇 social networkin...
89 篇 predictive model...
80 篇 contrastive lear...

机构

66 篇 carnegie mellon ...
39 篇 carnegie mellon ...
35 篇 zhejiang univers...
33 篇 tsinghua univers...
32 篇 nanyang technolo...
32 篇 university of wa...
32 篇 school of comput...
31 篇 national univers...
31 篇 language technol...
30 篇 stanford univers...
30 篇 the chinese univ...
27 篇 gaoling school o...
25 篇 university of ch...
25 篇 harbin institute...
25 篇 alibaba group
24 篇 allen inst artif...
24 篇 peking universit...
23 篇 school of artifi...
23 篇 alibaba grp peop...
22 篇 university of il...

作者

40 篇 neubig graham
37 篇 smith noah a.
35 篇 lapata mirella
32 篇 liu yang
31 篇 sun maosong
29 篇 zhao jun
28 篇 liu qun
28 篇 liu zhiyuan
27 篇 hovy eduard
27 篇 huang xuanjing
26 篇 zhang min
25 篇 zhou guodong
25 篇 vulic ivan
24 篇 korhonen anna
23 篇 gurevych iryna
22 篇 schütze hinrich
20 篇 wen ji-rong
20 篇 ney hermann
20 篇 zhang qi
19 篇 zhou jie

语言

6,137 篇 英文
369 篇 其他
39 篇 中文
1 篇 土耳其文

检索条件"任意字段=2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024"

共 6526 条记录，以下是71-80 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：

Research on methods of Large language Models in the Field of Sensitive Data Governance 24

Research on Methods of Large Language Models in the Field of...

引用

2nd International conference on Artificial Intelligence, Systems and Network Security, AISNS 2024

作者： Zhang, Zhixian Bai, Yin Yu, Xiaoting Wang, Yu Yang, Siqi Yang, Shuo China Mobile Chengdu Institute of Research and Development Sichuan Chengdu China

ISBN: (纸本)9798400711237

With the rapid advancement of big data and artificial intelligence technologies, the governance of sensitive data has become a critical and pressing issue. Traditional data de-identification approaches exhibit inefficiencies and a lack of flexibility when processing unstructured data. This paper introduces a sensitive data governance method based on Large language Models, leveraging the natural language processing capabilities of LLMs to construct prompts that enable the identification of fields requiring de-identification and the selection of appropriate de-identification methods. Furthermore, it harnesses the LLMs to automatically generate Python processing code, thus circumventing the limitations of singular and inflexible built-in de-identification functionalities in big data platforms. The objective of this study is to reduce the technical barriers in sensitive data governance and to enhance the flexibility and efficiency of data processing. The paper provides a detailed exposition of the technical implementation of this method, encompassing multiple stages such as data identification, instruction processing, model invocation, result adjudication, and data caching, and discusses its advantages and potential value in practical applications. © 2024 Copyright held by the owner/author(s).

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

UHDF: Hallucination Detection Using Open Source Models Beyond Close Source Models methods 13th

UHDF: Hallucination Detection Using Open Source Models Beyon...

引用

13th International conference on natural language processing and Chinese Computing

作者： Liu, Dongxu Xu, Bufan Zhao, Zhilong Xu, Bing Yang, Muyun Harbin Inst Technol Harbin 150006 Peoples R China

ISBN: (纸本)9789819794423;9789819794430

With the emergence of multimodal large models, the problem of hallucination has been plaguing their development and deployment. How to reliably detect the presence of hallucinations inmLLMshas become an important issue. We propose UHDF, which replaces the closed-source models in it with open-source models by improving UniHD [15], and dramatically outperforms it. By optimizing the external information used in UniHD and achieving decoupling between different external information sources, we minimize the hallucinations introduced in pipeline, and thus improve the effectiveness of hallucinations detection. UHDF using the open-source model outperforms UniHD using the closed-source model (GPT-4v), achieving 86.6% (dev set)/85.3% (test set) on MacroF1 and achieved the first place in NLPCC2024 Shared Task 10 Track1 (Open Source). Our code and models are available at https://***/codetalker125/UHDF.

关键词： mLLM hallucination detection external information

来源：评论

学校读者我要写书评

暂无评论

The Benefits in Shallow: Merge Decoding Across Large language Model Layers 13th

The Benefits in Shallow: Merge Decoding Across Large Languag...

引用

13th International conference on natural language processing and Chinese Computing

作者： Zhou, Yuechi Zhou, Chuyue Xie, Wenjing Wang, Xinrui Chen, Jiuchang Ni, Zhenghua Li, Juntao Soochow Univ Inst Comp Sci & Technol Suzhou Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Large language models (LLMs) have become foundational to numerous natural language processing tasks;however, decoding coherent and contextually relevant text remains a complex challenge. In openended generation, maximizing probability is often not the appropriate objective, as with sampling methods, the continuation tends to be incoherent and repetitive in various degrees. We propose Merge Decoding, merging information in the shallow layer, such as sequential information, with the final task-specific layer, thereby generating coherent and rich text. MD works across three scales of the LLaMA family(7B, 13B, 30B), achieving higher quality text in open-ended text generation (Wiki-Text, WikiNews, BookCorpus) and enhancing reasoning capabilities in downstream tasks (Gsm8k, StrategyQA) https://***/YcChou/MergeDecoding.

关键词： Large language model Decoding strategy Text generation

来源：评论

学校读者我要写书评

暂无评论

CaFGD: Context Auto-Filling via Gradient Descent 24

CaFGD: Context Auto-Filling via Gradient Descent

引用

8th International conference on Computer Science and Artificial Intelligence, CSAI 2024

作者： Qin, Zhike Liu, Yanyan Wang, Shaopu Wang, Chunlei Shanghai University Shanghai China China Information Security Research Institute Co. Ltd. Beijing China

ISBN: (纸本)9798400718182

Recently, large language models (LLMs) achieve remarkable success in domains beyond the traditional natural language processing, and there is a growing interest in applying LLMs to more general domains like code generation, travel planning, and robot controls, but these models still need improvement in targeted performance and generalization capabilities in specific fields or tasks. To enable models to more specifically understand various tasks, prompt learning has been proposed to convert downstream prediction tasks into language model tasks. Among prompt learning methods, most utilize gradient-based trigger token search methods for automatic context filling to complete tasks. However, these methods don’t always enhance the accuracy of LLMs in completing tasks, especially when meeting multiple task types and uncertain input sentences. The choice of trigger tokens often lacks specificity, leading to suboptimal model performance. To enhance model stability and generate more targeted trigger tokens, we propose a context auto-filling method via average gradient descent. Unlike other methods, our approach comprehensively considers the relationship between all trigger tokens and context. Proposed method modifies a template by replacing one trigger token with another token, using the model’s average gradient across all trigger tokens to select one token that maximize the likelihood function of the template. We conducted experiments on the SST-2 and SICK-E datasets for sentiment analysis (SA) and natural language Inference (NLI) tasks respectively. The experimental results demonstrate that the context auto-filling method with an average gradient of trigger token yields better performance. © 2024 Copyright held by the owner/author(s).

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

An Automated Grading System for Competition Theses Assisted by NLP Models 24

An Automated Grading System for Competition Theses Assisted ...

引用

8th International conference on Electronic Information Technology and Computer Engineering, EITCE 2024

作者： Xue, Sijuan Duan, Xu Yang, Manqi College of Information Engineering Hainan Vocational University of Science and Technology Hainan Haikou China

ISBN: (纸本)9798400710094

As the digital transformation of education continues to advance, the inefficiency and subjectivity of traditional manual scoring methods have become increasingly prominent. To address this issue, this study developed an automated scoring process. The process includes several key steps: reading text files, training latent Dirichlet allocation (LDA) topic models, matching texts with conditional sentence libraries, and performing natural language processing (NLP) analysis. The scoring method used in this study follows the standards proposed by advocates of text scoring conditions to comprehensively evaluate the completeness and accuracy of the text. The entire paper is comprehensively evaluated from four dimensions: completeness, content, summary quality, and writing ability. © 2024 Copyright held by the owner/author(s).

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Prompting methods in Low-Resource Speech Recognition with Whisper 13th

Exploring the Potential of Prompting Methods in Low-Resource...

引用

13th International conference on natural language processing and Chinese Computing

作者： Chen, Yaqi Zhang, Wenlin Zhang, Hao Yang, Xukui Qu, Dan Informat Engn Univ Sch Informat Syst Engn Zhengzhou Peoples R China Lab Adv Comp & Intelligence Engn Wuxi Jiangsu Peoples R China

ISBN: (纸本)9789819794362;9789819794379

Recent advancements in large-scale pre-trained automatic speech recognition (ASR) foundation models (e.g., Whisper) have exhibited remarkable performance in speech processing tasks. But fine-tuning such models for low-resource languages can be computationally expensive and prone to overfitting. Prompting methods offer a solution by designing specific prompts in the inputs that guide the model's behavior for targeted tasks, facilitating parameter-efficient adaptation. This paper presents the first exploration of various prompt tuning methods and optimized strategies for low-resource ASR based on Whisper. Moreover, we propose a shallow integration method to utilize the advantage of deep prompt tuning and reparametrization. Extensive experiments on the Common Voice and FLEURS datasets show the competitive performance of prompt tuning compared to full fine-tuning and Lora with fewer trainable parameters. Notably, the shallow integration strategy yields impressive results, especially for small models.

关键词： low-resource automatic speech recognition Whisper prompt tuning

来源：评论

学校读者我要写书评

暂无评论

Resolving Unseen Rumors with Retrieval-Augmented Large language Models 13th

Resolving Unseen Rumors with Retrieval-Augmented Large Langu...

引用

13th International conference on natural language processing and Chinese Computing

作者： Chen, Lei Wei, Zhongyu Fudan Univ Sch Data Sci Shanghai Peoples R China Fudan Univ Res Inst Intelligent & Complex Syst Shanghai Peoples R China

ISBN: (纸本)9789819794393;9789819794409

Social media has become the primary source of information for individuals, yet much of this information remains unverified. The rise of generative artificial intelligence has further accelerated the creation of unverified content. Adaptive rumor resolution systems are imperative for maintaining information integrity and public trust. Traditional methods have relied on encoder-based frameworks to enhance rumor representation and propagation characteristics. However, these models are often small in scale and lack generalizability for unforeseen events. Recent advances in Large language Models show promise but are unreliable in discerning truth from falsehood. Our work leverages LLMs by creating a testbed for predicting unprecedented rumors and designing a retrieval-augmented framework that integrates historical knowledge and collective intelligence. Experiments on two real-world datasets demonstrate the effectiveness of our proposed framework.

关键词： Rumor Detection Retrieval-Augmented LLMs

来源：评论

学校读者我要写书评

暂无评论

Automated Implementation Scheme for Low-Code Development Based on Large language Models 24

Automated Implementation Scheme for Low-Code Development Bas...

引用

4th International conference on Signal processing and Communication Technology, SPCT 2024

作者： Sun, Tao Lan, Xingfei Jing, Guoshuai Zhang, Judong Jin, Yuchao Xu, Lexi Yang, Lei JDCloud *** Inc. Beijing China Research Institute China United Network Communications Corporation Beijing China

ISBN: (纸本)9798400710636

This paper presents an implementation scheme that integrates low-code platforms with artificial intelligence (AI) technology to enhance the development process. By leveraging AI for automatic code generation, intelligent component recommendations, and error detection/repair, the efficiency of low-code development is significantly improved. The combination of natural language requirements and visual drag-and-drop operations lowers the technical barrier. A new model for evaluating efficiency improvement is introduced and validated using actual business data, demonstrating the feasibility and effectiveness of this integration. © 2024 Copyright held by the owner/author(s).

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

Local or Global Optimization for Dialogue Discourse Parsing 13th

Local or Global Optimization for Dialogue Discourse Parsing

引用

13th International conference on natural language processing and Chinese Computing

作者： Wang, Chengrui Ji, Shaoming Kong, Fang Soochow Univ Lab Nat Language Proc Suzhou Peoples R China Soochow Univ Sch Comp Sci & Technol Suzhou Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Dialogue Discourse Parsing aims to identify the discourse links and relations between utterances, which has attracted more interest in recent years. Previous studies either adopt local optimization to independently select one parent for each utterance or use global optimization to directly get the tree representing the dialogue structure. However, the influence of these two optimization methods remains less explored. In this paper, we aim to systematically inspect their performance. Specifically, for local optimization, we use local loss during the training stage and a greedy strategy during the inference stage. For global optimization, We implement optimization of unlabeled and labeled trees by structured losses including Max-Margin and TreeCRF, and exploit Chu-Liu-Edmonds algorithm during the inference stage. Experiments shows that the performance of these two optimization methods is closely related to the characteristics of the dataset, and global optimization can reduce the burden of identifying long-range dependency relations.

关键词： Dialogue discourse parsing Local optimization Global optimization

来源：评论

学校读者我要写书评

暂无评论

ASRLM: ASR-Robust language Model Pre-training via Generative and Discriminative Learning 13th

ASRLM: ASR-Robust Language Model Pre-training via Generative...

引用

13th International conference on natural language processing and Chinese Computing

作者： Hu, Qian Han, Xue Wang, Yiting Wang, Yitong Deng, Chao Feng, Junlan China Mobile Res Inst JiuTian Team Beijing Peoples R China

ISBN: (纸本)9789819794362;9789819794379

The rise of voice interface applications has renewed interest in improving the robustness of spoken language understanding(SLU). Many advances have come from end-to-end speech-language joint training, such as inferring semantics directly from speech signals and post-editing automatic speech recognition (ASR) output. Despite their performance achievements, these methods either suffer from the unavailability of a large number of paired error-prone ASR transcriptions and ground-truth annotations or are computationally costly. To mitigate these issues, we propose an ASR-robust pre-trained language model (ASRLM), which involves a generator generating simulated ASR transcriptions from ground-truth annotations and a sample-efficient discriminator distinguishing reasonable ASR errors from unrealistic ones. Experimental results demonstrate that ASRLM improves performance on a wide range of SLU tasks in the presence of ASR errors while saving 27% of the computation cost compared to baselines. Analysis also shows that our proposed generator is better than other simulation methods, including both BERT and GPT4-based, at simulating real-world ASR error situations.

关键词： Spoken language understanding Automatic speech recognition Pre-trained language model

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 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：