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

57,254 篇 会议
184 册 图书

馆藏范围

57,431 篇 电子文献
7 种 纸本馆藏

日期分布

学科分类号

57,042 篇 工学
- 56,774 篇 计算机科学与技术...
- 7,556 篇 控制科学与工程
- 2,463 篇 软件工程
- 2,057 篇 电气工程
- 483 篇 信息与通信工程
- 360 篇 生物医学工程（可授...
- 67 篇 机械工程
- 57 篇 土木工程
- 23 篇 石油与天然气工程
- 18 篇 生物工程
- 15 篇 仪器科学与技术
4,454 篇 理学
- 3,698 篇 数学
- 368 篇 物理学
- 274 篇 生物学
- 53 篇 科学技术史(分学科...
- 52 篇 统计学（可授理学、...
- 22 篇 系统科学
- 18 篇 化学
2,190 篇 医学
- 1,233 篇 基础医学(可授医学...
- 1,065 篇 临床医学
- 36 篇 特种医学
2,181 篇 文学
- 2,178 篇 外国语言文学
1,355 篇 管理学
- 1,256 篇 管理科学与工程(可...
- 84 篇 图书情报与档案管...
1,231 篇 教育学
- 709 篇 教育学
- 507 篇 心理学(可授教育学...
- 15 篇 体育学
57 篇 法学
- 56 篇 社会学
36 篇 艺术学
- 36 篇 音乐与舞蹈学
35 篇 哲学
- 35 篇 哲学
13 篇 经济学
1 篇 农学
1 篇 军事学

主题

1,258 篇 artificial intel...
1,112 篇 machine learning
978 篇 deep learning
919 篇 data mining
780 篇 multi agent syst...
725 篇 semantics
527 篇 classification
510 篇 reinforcement le...
474 篇 learning systems
463 篇 clustering
439 篇 neural networks
415 篇 ontology
353 篇 natural language...
257 篇 computers
249 篇 rough sets
236 篇 fuzzy sets
230 篇 feature selectio...
219 篇 computer circuit...
213 篇 knowledge repres...
205 篇 logic programmin...

机构

191 篇 univ chinese aca...
107 篇 chinese acad sci...
65 篇 harbin inst tech...
63 篇 polish acad sci ...
62 篇 wroclaw univ sci...
59 篇 soochow univ sch...
55 篇 delft univ techn...
53 篇 carnegie mellon ...
48 篇 beijing univ tec...
44 篇 chinese acad sci...
44 篇 shanghai jiao to...
43 篇 tu wien austria
42 篇 univ sci & techn...
41 篇 czech tech univ ...
40 篇 univ ulsan sch e...
39 篇 beijing jiaotong...
38 篇 tsinghua univ de...
38 篇 north carolina s...
37 篇 nanjing univ sta...
36 篇 tsinghua univ sc...

作者

47 篇 gelbukh alexande...
42 篇 wang lei
36 篇 reis luis paulo
35 篇 pelachaud cather...
35 篇 malerba donato
34 篇 liu yang
33 篇 novais paulo
33 篇 cpalka krzysztof
32 篇 li li
30 篇 ricci alessandro
27 篇 lau nuno
26 篇 wang hui
26 篇 napoli amedeo
25 篇 boryczka urszula
25 篇 rutkowski leszek
25 篇 wang jing
25 篇 pluhacek michal
25 篇 bickmore timothy
25 篇 calvo hiram
24 篇 villasenor-pined...

语言

57,321 篇 英文
116 篇 中文
1 篇 丹麦文

检索条件"丛书名=Lecture notes in artificial intelligence,"

共 57438 条记录，以下是81-90 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：

Improving Causal Inference of Large Language Models with SCM Tools 13th

Improving Causal Inference of Large Language Models with SCM...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Hua, Zhenyang Xing, Shuyue Jiang, Huixing Wei, Chen Wang, Xiaojie Beijing Univ Posts & Telecommun Ctr Intelligence Sci & Technol Beijing Peoples R China LI Auto Inc Beijing Peoples R China

ISBN: (纸本)9789819794362;9789819794379

Many previous studies have shown that Large Language Models (LLMs) are highly competent on many Natural Language Processing (NLP) tasks. However, a recent study showed the poor ability of LLMs to perform causal inference based on causal graphs and data. In this paper, we propose a method to enhance LLMs based on Structure Causal Model (SCM) tools. We constructed 10 causal inference tools based on SCM theory for solving 10 different types of causal questions. LLMs help to extract the information needed for causal inference tools in the causal questions, select the appropriate causal inference tools, and combine the inference results of the causal inference tools to generate the final causal question answers. The experimental results show that the method proposed in this paper outperforms the best existing methods.

关键词： Large Language Models Causal Inference Structure Causal Model

来源：评论

学校读者我要写书评

暂无评论

Overcoming Rigid and Monotonous: Enhancing Knowledge-Grounded Conversation Generation via Multi-granularity Knowledge 13th

Overcoming Rigid and Monotonous: Enhancing Knowledge-Grounde...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Zhang, Xingsheng Deng, YiFan Hu, Yue Li, Yunpeng Guo, Ping Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Knowledge-grounded conversation (KGC) shows great potential in building an engaging and reliable chatbot, in which knowledge-aware generation is a key ingredient in it. Traditional methods, which usually generate responses based on sentence-level knowledge, are unable to locate the suitable knowledge pieces exactly, leading to insufficient utilization of knowledge and monotonous and rigid responses. In this paper, we propose a Multi-granularity Knowledge-aware Adaptive Generation (MKAG) model, which can adaptively select knowledge units from coarse to fine-grained based on various semantic segments in the response, as well as generating knowledgeable and informative responses. Specifically, an expandable knowledge supporter is devised to split knowledge units of various granularities according to semantics for positioning knowledge precisely. Besides, we design a segmentation-based decoding method, which is capable of generating multiple semantic segments sequentially, and each semantic segment can adaptively select the corresponding granularity of knowledge units for the generation. Experimental results show that MKAG significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, indicating that it can alleviate the issue of monotonous and rigid replies effectively.

关键词： Knowledge-grounded conversation Multi-granularity Knowledge Segmentation-based decoding

来源：评论

学校读者我要写书评

暂无评论

Joint Graph Augmentation and Adaptive Synthetic Sampling for Imbalanced Node Classification 13th

Joint Graph Augmentation and Adaptive Synthetic Sampling for...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Lu, Guangquan Chen, Wanxin Han, Yadan Tang, Jiamin Huang, Faliang Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Guangxi Key Lab Multisource Informat Min & Secur Guilin 541004 Peoples R China Nanning Normal Univ Guangxi Key Lab Human Machine Interact & Intellig Nanning Peoples R China

ISBN: (纸本)9789819794393;9789819794409

Graph representation learning is a very important part of the field of machine learning. It focuses on learning and extracting representations of nodes and edges in graph data to better analyze features and relationships within the graph structure. Graph neural networks (GNNs) are widely used to deal with node classification problems and has achieved state-of-the-art performance. However, most of the existing methods are performed under the condition that the number of node classes is balanced. In fact, in real-life scenarios, the number of samples of some classes will be significantly less than that of other classes. This leads to insufficient information representation of the minority class graph, thereby affecting the classification performance of GNNs. This paper proposes a new framework GraphAdasyn for imbalanced node classification to address this problem. The model inputs a hybrid view to utilize global and local topology information, expends an over-sampling method that is generalized to multiple-class imbalanced problems in the graph. This method enables adaptively synthesize the number of minority class samples based on the density distribution and is flexibly applicable to various datasets. Through numerous experiments results indicate that proposed framework demonstrates superior performance compared to all baseline methods in imbalanced node classification tasks.

关键词： Graph representation learning Imbalanced node classification Graph neural network

来源：评论

学校读者我要写书评

暂无评论

S2D: Enhancing Zero-Shot Cross-Lingual Event Argument Extraction with Semantic Knowledge 13th

S2D: Enhancing Zero-Shot Cross-Lingual Event Argument Extrac...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Zhao, Zongkai Li, Xiuhua Wei, Kaiwen Chongqing Univ Sch Big Data & Software Engn Chongqing Peoples R China Chongqing Univ Coll Comp Sci Chongqing Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Zero-shot Cross-lingual EAE has garnered significant interests from the community because it could minimize the need for extensive data annotation to identify the roles of the arguments within a specific event. Some prior works point out that syntactic structures could be regarded as the language-independent features and those methods have achieved promising performance. However, sometimes even the sentences in different languages express the same meaning, the syntactic parsing results are quite different. To alleviate this problem, we find the semantic information is rarely considered, which could be considered as another language-independent features and provides more consistent parsing results across languages. To this end, in this paper, we propose the Semantic-Syntactic Driven framework (S2D) for incorporating the semantic and syntactic information simultaneously. Specifically, we design a language-independent dual-prefix constructor module to handle the semantic and syntactic discrepancies between source and target languages. Besides, we introduce a semantic role labeling source generator module to expand the source language dataset with semantic features. The experimental results illustrate that S2D surpasses the state-of-the-art methods by 3.4% and 5.3% in terms of average F1-score on the ACE-2005 and ERE datasets, respectively.

关键词： Event Extraction Cross Lingual Semantic Knowledge

来源：评论

学校读者我要写书评

暂无评论

What is the Best Model? Application-Driven Evaluation for Large Language Models 13th

What is the Best Model? Application-Driven Evaluation for La...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Lian, Shiguo Zhao, Kaikai Liu, Xinhui Lei, Xuejiao Yang, Bikun Zhang, Wenjing Wang, Kai Liu, Zhaoxiang China Unicom AI Innovat Ctr Beijing 100013 Peoples R China China Unicom Unicom Digital Technol Beijing 100013 Peoples R China

ISBN: (纸本)9789819794362;9789819794379

General large language models enhanced with supervised fine-tuning and reinforcement learning from human feedback are increasingly popular in academia and industry as they generalize foundation models to various practical tasks in a prompt manner. To assist users in selecting the best model in practical application scenarios, i.e., choosing the model that meets the application requirements while minimizing cost, we introduce A-Eval, an application-driven LLMs evaluation benchmark for general large language models. First, we categorize evaluation tasks into five main categories and 27 sub-categories from a practical application perspective. Next, we construct a dataset comprising 678 question-and-answer pairs through a process of collecting, annotating, and reviewing. Then, we design an objective and effective evaluation method and evaluate a series of LLMs of different scales on A-Eval. Finally, we reveal interesting laws regarding model scale and task difficulty level and propose a feasible method for selecting the best model. Through A-Eval, we provide clear empirical and engineer guidance for selecting the best model, reducing barriers to selecting and using LLMs and promoting their application and development. Our benchmark is publicly available at https://***/UnicomAI/UnicomBenchmark/tree/main/A-Eval.

关键词： Large Language Models application-driven evaluation benchmark selecting the best model

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fake News Detection with Large Language Models Through Multi-agent Debates 13th

Enhancing Fake News Detection with Large Language Models Thr...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Jeptoo, Korir Nancy Su, Chengjie Harbin Inst Technol Fac Comp Harbin Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Large language models (LLMs) are showing dramatic progress in terms of language generation and in reasoning tasks. Existing works on fake news detection mostly focus on fine-tuning small language models such as BERT. One downside of fine-tuning is that it requires a lot of data which might not always be available. With the prevalent spread of fake news and misinformation, alternative ways are needed especially in cases where there is lack of enough training data. In this paper, we propose using multi-agent debate strategies to enhance fake news detection by leveraging the capabilities of LLMs. We introduce two approaches: a uniform prompt multi-agent debate and a diverse prompt multi-agent debate where each LLM agent adopts distinct roles such as fact-checker, journalist, or data scientist. These methods are bench-marked against single LLM evaluations to assess the impact of collaborative reasoning. Our experiments on the PolitiFact and GossipCop datasets reveal that the multi-agent debate methods outperform single LLM assessments. Notably, the diverse persona debate approach achieves the highest performance, demonstrating the value of incorporating different perspectives in reasoning. These results suggest that multi-agent debates can effectively harness the strengths of single LLMs to improve the reliability of fake news detection systems.

关键词： Fake News Detection Large Language Models Multi-Agent Debate

来源：评论

学校读者我要写书评

暂无评论

Integration of Short-Term and Long-Term Harmonic Peaks in a Two-Level Discriminative Weight Training Framework for Voice Activity Detection 26th

Integration of Short-Term and Long-Term Harmonic Peaks in a ...

引用

26th International Conference on Speech and Computer

作者： Tan, YingWei Volkswagen Mobvoi Beijing Informat Technol Co Ltd Beijing Peoples R China

ISBN: (纸本)9783031780134;9783031780141

Short-term harmonic peaks (STHPs) have been used in a harmonic frequency-based multiple observation likelihood ratio test (Hmfreq-MOLRT) VAD successfully. Through the characteristics of spectral harmonicity, the method boosts the likelihood ratio (LR) scores for voiced frames under low signal-to-noise ratio (SNR) conditions so that the total score of its decision function is high enough to promote the detection of weaker speech frames. However, when the STHPs are seriously disturbed by various noises, the total score is not improved by the method sufficiently and the VAD's performance starts to fall. In this paper, we present a novel VAD algorithm to solve the problem. In the algorithm, we design a new geometric mean (GM) of likelihood ratios (LRs) located at long-term harmonic peaks (LTHPs) and realize an integration of STHPs and LTHPs using a two-level discriminative weight training framework. Experimental results show the performance of the proposed method has significant improvement on speech/non-speech detection accuracy in comparison with the Hmfreq-MOLRT algorithm. Especially in extremely adverse noisy conditions, such as -10 dB and -5 dB, the improvement is more obvious.

关键词： Voice activity detection Likelihood ratio test Long-term harmonic peaks a Two-level discriminative weight training framework Segment-level voiced/unvoiced decision

来源：评论

学校读者我要写书评

暂无评论

Bias Unveiled: Enhancing Fairness in German Word Embeddings with Large Language Models 26th

Bias Unveiled: Enhancing Fairness in German Word Embeddings ...

引用

26th International Conference on Speech and Computer

作者： Saeid, Yasser Kopinski, Thomas South Westphalia Univ Appl Sci Meschede Germany

ISBN: (纸本)9783031780134;9783031780141

Gender bias in word embedding algorithms has garnered significant attention due to its integration into machine learning systems and its potential to reinforce stereotypes. Despite ongoing efforts, the root causes of biases in training word embeddings, specifically for the German language, remain unclear. This research presents a novel approach to tackling this problem, paving the way for new avenues of investigation. Our methodology involves a comprehensive analysis of word embeddings, focusing on how training data manipulations impact resulting biases. By examining how biases originate within specific training documents, we identify subsets that can be removed to effectively mitigate these effects. Additionally, we explore both conventional methods and new approaches using large language models (LLMs) to ensure the generated text adheres to concepts of fairness. Using few-shot prompting, we generate gender bias-free text, employing GPT-4 as a benchmark to evaluate the fairness of this process for the German language. Our method explains the intricate origins of biases within word embeddings, validated through rigorous application to German Wikipedia corpora. Our findings robustly demonstrate the efficacy of our method, showing that removing certain document subsets significantly diminishes bias in word embeddings. This is further detailed in our analysis, "Unlocking the Limits: Document Removal with an Upper Bound," in the experimental results section. Ultimately, this research presents a practical framework to uncover and mitigate biases in word embedding algorithms during training. Our goal is to advance machine learning systems that prioritize fairness and impartiality by revealing and addressing latent sources of bias.

关键词： Stereotypical biases Gender bias Machine learning systems Word embedding algorithms Bias amplification Embedding bias Origins of bias Specific training documents Efficacy Abating bias Methodology Insights Matrix German Wikipedia corpora Empirical endeavor Precision Sources of bias Equanimity Impartiality LLM

来源：评论

学校读者我要写书评

暂无评论

Margin Discrepancy-Based Adversarial Training for Multi-Domain Text Classification 13th

Margin Discrepancy-Based Adversarial Training for Multi-Doma...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Wu, Yuan Jilin Univ Sch Artificial Intelligence Changchun Peoples R China

ISBN: (纸本)9789819794362;9789819794379

Multi-domain text classification (MDTC) endeavors to harness available resources from correlated domains to enhance the classification accuracy of the target domain. Presently, most MDTC approaches that embrace adversarial training and the shared-private paradigm exhibit cutting-edge performance. Unfortunately, these methods face a non-negligible challenge: the absence of theoretical guarantees in the design of MDTC algorithms. The dearth of theoretical underpinning poses a substantial impediment to the advancement of MDTC algorithms. To tackle this problem, we first provide a theoretical analysis of MDTC by decomposing the MDTC task into multiple domain adaptation tasks. We incorporate the margin discrepancy as the measure of domain divergence and establish a new generalization bound based on Rademacher complexity. Subsequently, we propose a margin discrepancy-based adversarial training (MDAT) approach for MDTC, in accordance with our theoretical analysis. To validate the efficacy of the proposed MDAT method, we conduct empirical studies on two MDTC benchmarks. The experimental results demonstrate that our MDAT approach surpasses state-of-the-art baselines on both datasets.

关键词： Multi-domain text classification Adversarial training Margin discrepancy

来源：评论

学校读者我要写书评

暂无评论

Mathematical Reasoning via Multi-step Self Questioning and Answering for Small Language Models 13th

Mathematical Reasoning via Multi-step Self Questioning and A...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Chen, Kaiyuan Wang, Jin Zhang, Xuejie Yunnan Univ Sch Informat Sci & Engn Kunming Yunnan Peoples R China

ISBN: (纸本)9789819794393;9789819794409

Mathematical reasoning is challenging for large language models (LLMs), while the scaling relationship concerning LLM capacity is under-explored. Existing works have tried to leverage the rationales of LLMs to train small language models (SLMs) for enhanced reasoning abilities, referred to as distillation. However, most existing distillation methods have not considered guiding the small models to solve problems progressively from simple to complex, which can be a more effective way. This study proposes a multi-step self questioning and answering (M-SQA) method that guides SLMs to solve complex problems by starting from simple ones. Initially, multi-step self-questioning and answering rationales are extracted from LLMs based on complexity-based prompting. Subsequently, these rationales are employed for distilling SLMs in a multi-task learning framework, during which the model learns to multi-step reason in a self questioning and answering way and answer each sub-question in a single step iteratively. Experiments on current mathematical reasoning tasks demonstrate the effectiveness of the proposed approach.

关键词： Mathematical Reasoning Knowledge Distillation Small Language Models

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 << < 5 6 7 8 9 10 11 12 13 14 > >>

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：