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

57,035 篇 工学
- 56,756 篇 计算机科学与技术...
- 7,563 篇 控制科学与工程
- 2,548 篇 软件工程
- 2,065 篇 电气工程
- 514 篇 信息与通信工程
- 373 篇 生物医学工程（可授...
- 69 篇 机械工程
- 60 篇 土木工程
- 47 篇 生物工程
- 23 篇 石油与天然气工程
- 16 篇 仪器科学与技术
4,529 篇 理学
- 3,741 篇 数学
- 378 篇 物理学
- 305 篇 生物学
- 67 篇 统计学（可授理学、...
- 53 篇 科学技术史(分学科...
- 28 篇 系统科学
- 26 篇 化学
2,201 篇 医学
- 1,244 篇 基础医学(可授医学...
- 1,075 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
1,390 篇 管理学
- 1,266 篇 管理科学与工程(可...
- 111 篇 图书情报与档案管...
1,235 篇 教育学
- 713 篇 教育学
- 507 篇 心理学(可授教育学...
- 15 篇 体育学
63 篇 法学
- 62 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
14 篇 经济学
1 篇 农学
1 篇 军事学

主题

1,255 篇 artificial intel...
1,104 篇 machine learning
972 篇 deep learning
919 篇 data mining
781 篇 multi agent syst...
726 篇 semantics
526 篇 classification
510 篇 reinforcement le...
475 篇 learning systems
462 篇 clustering
434 篇 neural networks
413 篇 ontology
342 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 wu bin

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：

MMHS: Multimodal Model for Hate Speech Intensity Prediction 26th

MMHS: Multimodal Model for Hate Speech Intensity Prediction

引用

26th International Conference on Speech and Computer

作者： Goel, Aman Poswal, Abhishek Carnegie Mellon Univ 5000 Forbes Ave Pittsburgh PA 15213 USA Hong Kong Univ Sci & Technol Kowloon Hong Kong Peoples R China

ISBN: (纸本)9783031780134;9783031780141

This paper presents a novel multimodal model that integrates both image and large language model capabilities to enhance hate intensity prediction, traditionally a purely text-based task. Accurately assessing hate speech intensity is crucial for moderating and regulating vast online communities by normalizing hate speech [1], while ensuring a balance between free expression and responsible communication. Our approach leverages insights from both the visual and language domains, resulting in the novel Multimodal Model for Hate Speech (MMHS). We demonstrate that MMHS achieves state-of-the-art performance on the NACL dataset, surpassing previous benchmarks by scoring 0.350 lower in Root Mean Squared Error (RMSE) and 0.132, and 0.012 higher in Pearson, and Cosine metrics, respectively. Additionally, user preference surveys indicate a significant favoring of our predictions over those of Masud et al. [1] by 16.67%. This work advances the technical landscape of hate speech detection and enriches our understanding of online discourse, enabling more effective moderation strategies. (Disclaimer: This paper includes examples of hate speech which contain some profane words. These examples are only included for contextual understanding. We tried our best to censor vulgar, offensive, or hateful words. We assert that we do not support these views in any way.)

关键词： Online hate speech Multimodal Hate intensity Information fusion

来源：评论

学校读者我要写书评

暂无评论

Exploring Multimodal Information Fusion in Spoken Off-Topic Degree Assessment 13th

Exploring Multimodal Information Fusion in Spoken Off-Topic ...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Cong, Fan Shen, Guo Wumaier, Aishan Xinjiang Univ Sch Comp Sci & Technol Urumqi Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Currently, most research methods for spoken off-topic detection are based on the results of upstream speech recognition tasks. However, upstream speech recognition tasks may introduce issues such as homophones, text recognition errors, and semantic confusion. Therefore, this study aims to explore the impact of integrating audio features into text information on off-topic degree assessment. To achieve this goal, we collected a dataset consisting of 2652 responses in question-answering scenarios from public competitions. The data was annotated according to the evaluation guidelines for farmers and herdsmen, creating a dataset named ASAG-TD for assessing off-topic degree in question-answering scenarios. In addition, we conducted research using the pre-trained language model RoBERTa, combined with commonly used neural network models, exploring two aspects: audio features and self-supervised pre-trained acoustic model. Experimental results demonstrate the effectiveness of our method, with the mean absolute error (MAE) of off-topic degree in spoken responses reduced to 0.414 and a Pearson correlation coefficient of 0.95.

关键词： off-topic degree assessment cross-modal attention semantic fusion multimodal

来源：评论

学校读者我要写书评

暂无评论

Multi-hop Reading Comprehension Model Based on Abstract Meaning Representation and Multi-task Joint Learning 13th

Multi-hop Reading Comprehension Model Based on Abstract Mean...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Zhao, Peiyu Zhang, Zhujian Liu, Bo Jinan Univ Coll Informat Sci & Technol Guangzhou 510632 Peoples R China

ISBN: (纸本)9789819794300;9789819794317

In recent years, the issue of document-based extractive reading comprehension has been widely studied. Multi-hop reading comprehension requires obtaining supporting facts from multiple paragraphs in the document and reasoning to get the answer. But some problems have not been well solved: during the process of extracting the answer, it is often disturbed by the non-real answer (i.e. similar answer) in the document;the lack of a related expression mechanism for multiple scattered evidences in the paragraph affects the extraction of the answer. To address these issues, this paper proposes a multi-hop reading comprehension method based on Abstract Meaning Representation (AMR) and contrastive learning, which combines graph neural network (GNN) and answer verification for multi-task joint learning to reduce the interference of confusing information and enhance the robustness of the model. Experiments were conducted on datasets including HotpotQA and MuSiQue. The results show that the method proposed in this paper performs better than some competitive baselines in terms of exact match (EM) and F1 score evaluation.

关键词： AMR Contrastive Learning Multi-hop Reading Comprehension Graph Neural Network Expected Calibration Error

来源：评论

学校读者我要写书评

暂无评论

Retrieval Augmented Tree of Thoughts 13th

Retrieval Augmented Tree of Thoughts

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Liu, Xuemin Liu, Jie Nankai Univ Coll Artificial Intelligence Engn Res Ctr Trusted Behav Intelligence Natl Key Lab Intelligent Tracking & Forecasting I Tianjin Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Large language models (LLMs) are able to answer reasoning questions through generating reasoning processes, such as Chains of Thoughts (CoT) and Trees of Thoughts (ToT). To retrieve external documents effectively for knowledge-intensive multi-step question answering (QA), we propose Retrieval Augmented Tree of Thoughts (RAToT), a retrieval framework which performs retrieval and locally optimal reasoning iteratively. RAToT inspires LLM to explore diverse reasoning paths via separating retrieved documents and selects the most promising one for each step. RAToT, which uses gpt-3.5-turbo-instruct as backbone LLM, retrieves documents with less noise than IRCoT on three open-domain multi-step QA datasets, HotpotQA, 2WikiMultihopQA and MuSiQue, and further enhances the performance of LLM QA on MuSiQue. RAToT can retrieve documents wisely and flexibly to mitigate the hallucinations in open-domain multi-step QA tasks (Code and data are available at https://***/XMLAleph/RAToT).

关键词： Retrieval Augmented Generation Tree of Thoughts Hallucination

来源：评论

学校读者我要写书评

暂无评论

Multiword Units in Russian Everyday Speech: Empirical Classification and Corpus-Based Studies 26th

Multiword Units in Russian Everyday Speech: Empirical Classi...

引用

26th International Conference on Speech and Computer

作者： Bogdanova-Beglarian, Natalia, V Blinova, Olga, V Khokhlova, Maria, V Sherstinova, Tatiana Y. Popova, Tatiana, I St Petersburg State Univ St Petersburg Russia HSE Univ St Petersburg Russia

ISBN: (纸本)9783031779602;9783031779619

The article is dedicated to the results of a research project describing the classes and functioning of multiword units in contemporary Russian everyday speech. The concept of multiword units encompasses quite diverse linguistic phenomena, making the creation of a working typology one of the project's central tasks. This typology is necessary for annotating corpus material and obtaining statistical characteristics. The identified classes of multiword units include the following units: 1) non-phraseologized collocations, 2) phraseologized collocations, 3) occasional collocations, 4) idiom forms, 5) constructions, 6) precedent texts and their elements, 7) multi-word pragmatic markers, and 8) speech formulas. The article describes the methods for annotating these units using the ORD corpus of everyday spoken Russian and presents the results of a quantitative analysis of their functioning within the annotated subcorpus. The obtained data can be used to address both theoretical tasks in the field of lexical and grammatical description of Russian everyday speech and numerous tasks related to processing or generating live spoken Russian.

关键词： Modern Russian Everyday Speech Oral Discourse Multiword Units Collocations Syntax Statistical Analysis Speech Corpus Corpus Linguistics Speech Technologies

来源：评论

学校读者我要写书评

暂无评论

Retrieval-Enhanced Template Generation for Template Extraction 13th

Retrieval-Enhanced Template Generation for Template Extracti...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Wang, Renyu Xiang, Wei Wang, Zhenhua Wang, Bang Huazhong Univ Sci & Technol HUST Sch Elect Informat & Commun Wuhan Peoples R China Cent China Normal Univ Fac Artificial Intelligence Educ Wuhan Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Template extraction tasks, such as role-filler entity extraction (REE) and template filling (TF), are classic problems in information extraction. Previous works usually simplify the TF task and focus only on the REE task. Few works attempt to tackle the more challenging template filling task. However, they design sophisticated models for individual REE or TF that can hardly tackle those two tasks concurrently. In this work, we formulate those two tasks as a template sequence generation problem, which can be solved by a unified generation framework. Specifically, we leverage the template to guide the model to extract event entities from a document and fill them into the predefined template. Furthermore, to enhance the model's understanding of the input document and capture the dependency between similar templates, we employ a retrieval-enhanced approach. The most semantically similar template is retrieved from the training data and augments the current context with similar structures and semantic information captured in the retrieved demonstration. Extensive experiments on the MUC-4 dataset demonstrate the generality and effectiveness of our proposed model. (The source code is available at https://***/luwry/RTG4TE).

关键词： Template filling Role-filler entity extraction Retrieval-enhanced template generation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Complex Causality Extraction via Improved Subtask Interaction and Knowledge Fusion 13th

Enhancing Complex Causality Extraction via Improved Subtask ...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Gao, Jinglong Lu, Chen Ding, Xiao Li, Zhongyang Liu, Ting Qin, Bing Harbin Inst Technol Res Ctr Social Comp & Informat Retrieval Harbin Peoples R China Natl Key Lab Informat Syst Engn Nanjing Peoples R China Huawei Cloud Shenzhen Peoples R China

ISBN: (纸本)9789819794393;9789819794409

Event Causality Extraction (ECE) aims at extracting causal event pairs from texts. Despite ChatGPT's recent success, fine-tuning small models remains the best approach for the ECE task. However, existing fine-tuning based ECE methods cannot address all three key challenges in ECE simultaneously: 1) Complex Causality Extraction, where multiple causal-effect pairs occur within a single sentence;2) Subtask Interaction, which involves modeling the mutual dependence between the two subtasks of ECE, i.e., extracting events and identifying the causal relationship between extracted events;and 3) Knowledge Fusion, which requires effectively fusing the knowledge in two modalities, i.e., the expressive pretrained language models and the structured knowledge graphs. In this paper, we propose a unified ECE framework (UniCE) to address all three issues in ECE simultaneously. Specifically, we design a subtask interaction mechanism to enable mutual interaction between the two ECE subtasks. Besides, we design a knowledge fusion mechanism to fuse knowledge in the two modalities. Furthermore, we employ separate decoders for each subtask to facilitate complex causality extraction. Experiments on three benchmark datasets demonstrate that our method achieves state-of-the-art performance and outperforms ChatGPT with a margin of at least 30% F1-score. More importantly, our model can also be used to effectively improve the ECE performance of ChatGPT via in-context learning.

关键词： Event Causality Extraction Knowledge Graph Structured Attention ChatGPT

来源：评论

学校读者我要写书评

暂无评论

Integrating Hierarchical Key Information and Semantic Difference Features for Long Text Matching 13th

Integrating Hierarchical Key Information and Semantic Differ...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Wang, Chunnian Li, Junliang Zhang, Hu Shanxi Univ Sch Big Data Sch Comp & Informat Technol Taiyuan Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Long text matching refers to the process of matching two pieces of text at the document level. Current methods struggle to effectively capture the key information scattered throughout long texts, and are insensitive to the semantic differences of identical words and the semantic similarities of different words. Therefore, this paper proposes the integrating hierarchical key information and semantic difference features for long text matching (HKIDF). Firstly, at the sentence level, we use information entropy to extract key sentences with a large amount of information, and then at the word level, we use an improved TextRank algorithm integrated with Transformer for word-level filtering of key sentences;Secondly, we use the improved Diff Transformer in BERT to learn difference features from the filtered key information;Finally, through a gate mechanism, we selectively fuse the semantic representations of key information and difference features to determine the matching relationship between long texts. Experimental results on the Chinese datasets CNSE and CNSS and the English dataset PAN demonstrate that our model outperforms existing baseline models.

关键词： Long text matching Information entropy Difference feature

来源：评论

学校读者我要写书评

暂无评论

Exploring MetaConformer for Speech Enhancement 26th

Exploring MetaConformer for Speech Enhancement

引用

26th International Conference on Speech and Computer

作者： Foerner, Lukas Dauner, Maximilian Univ Hosp Augsburg Dept Diagnost & Intervent Radiol & Neuroradiol Clin Computat Med Imaging Res Augsburg Germany Hsch Munchen Univ Appl Sci Munich Ctr Digital Sci & AI Munich Germany

ISBN: (纸本)9783031780134;9783031780141

The convolution-augmented Transformer (Conformer) has emerged as a promising architecture in the field of speech enhancement (SE), capable of capturing both local and global dependencies in speech signals. Recent studies have shown that replacing the self-attention mechanism with unparameterized token mixers yields results that are similar to or superior to those of traditional Transformers, with significantly reduced computational and memory requirements. This has led to the development of the Metaformer architecture, which consists of normalization, residual connections, channel mixers, and token mixers. The fundamental architecture comprising these components is primarily responsible for the strong performance of the models, rather than the specific choice of token mixer. So far, Metaformers have mainly been tested in the domains of language modeling, document-grounded dialogue generation, image classification, object detection and instance segmentation. In this paper, we transfer the Metaformer concept to the field of speech enhancement. We combine the Metaformer andConformer architectures, resulting in the MetaConformer model, which utilizes token mixers instead of self-attention. By substituting the Conformer block in a state-of-the-art speech enhancement model with our MetaConformer concept, we demonstrate that even the simplest token mixers can achieve 95% of the PESQ score of the vanilla model on the VoiceBank+DEMAND dataset, while requiring only 57% of the training time and 63% less memory. The introduced MetaConformer could serve as a baseline for future speech enhancement models.

关键词： Speech enhancement Transformer Metaformer Token mixer Metaconformer

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

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：