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

14,463 篇 会议
653 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

15,257 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

10,943 篇 工学
- 10,283 篇 计算机科学与技术...
- 5,409 篇 软件工程
- 1,461 篇 信息与通信工程
- 953 篇 电气工程
- 879 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
2,417 篇 管理学
- 1,748 篇 图书情报与档案管...
- 758 篇 管理科学与工程(可...
- 240 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

3,534 篇 natural language...
1,768 篇 natural language...
952 篇 computational li...
741 篇 semantics
680 篇 machine learning
609 篇 deep learning
520 篇 natural language...
347 篇 computational mo...
336 篇 training
333 篇 accuracy
331 篇 sentiment analys...
329 篇 large language m...
320 篇 feature extracti...
311 篇 data mining
290 篇 speech processin...
261 篇 speech recogniti...
252 篇 transformers
235 篇 neural networks
217 篇 iterative method...
212 篇 support vector m...

机构

85 篇 carnegie mellon ...
51 篇 university of ch...
45 篇 tsinghua univers...
45 篇 carnegie mellon ...
43 篇 zhejiang univers...
43 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...
27 篇 language technol...
27 篇 peking universit...
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

14,663 篇 英文
481 篇 其他
105 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 15258 条记录，以下是4801-4810 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：

Dialogue Act Recognition Based on Self-supervised Act Denoising

Dialogue Act Recognition Based on Self-supervised Act Denois...

引用

International Joint conference on Neural Networks (IJCNN)

作者： Haitao Gui Zhongqing Wang College of Computer Science and Technology Soochow University Suzhou China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Dialogue act (DA) recognition is crucial in many natural language processing tasks. In dialogues, speakers aim to express their acts, which may be conveyed implicitly or explicitly. Therefore, DA serves as a semantic label for utterances and is essential for understanding the speaker’s action. With the widespread application of pre-trained language models in text recognition tasks, methods based on pre-trained language models can learn feature information from texts. However, most current methods do not consider the structural features of previous and subsequent dialogue utterances. The T5 model has recently performed excellently in various natural language processing tasks. This paper proposes a model that uses the T5 language model to recognize DA. Moreover, considering the unique characteristics of dialogue text, we add a self-supervised pre-training task before fine-tuning. By combining dialogue text and DA, using continuous multiple utterances as input to learn the structural features of dialogue text and assist in fine-tuning tasks, we utilize a generative approach for DA recognition during the fine-tuning phase. Experimental results show that on the DailyDialog dataset, the proposed model achieved an F1 score of 84.1%, which is 2.8 percentage points higher than the T5 model, thus validating the superiority of the proposed model.

关键词： Text recognition Noise reduction Semantics Neural networks natural language processing Character recognition

来源：评论

学校读者我要写书评

暂无评论

Learning ChineseWord Embeddings by Discovering Inherent Semantic Relevance in Sub-characters 22

Learning ChineseWord Embeddings by Discovering Inherent Sema...

引用

31st ACM International conference on Information and Knowledge Management (CIKM)

作者： Lu, Wei Zhang, Zhaobo Yuan, Pingpeng Jin, Hai Hua, Qiangsheng Huazhong Univ Sci & Technol Serv Comp Technol & Syst Lab Natl Engn Res Ctr Big Data Technol & Syst Cluster & Grid Comp LabSch Comp Sci & Technol Wuhan Peoples R China

ISBN: (纸本)9781450392365

Learning Chinese word embeddings is important in many tasks of Chinese language information processing, such as entity linking, entity extraction, and knowledge graph. A Chinese word consists of Chinese characters, which can be decomposed into sub-characters (radical, component, stroke, etc). Similar to roots in English words, sub-characters also indicate the origins and basic semantics of Chinese characters. So, many researches follow the approaches designed for learning embeddings of English words to improve Chinese word embeddings. However, some Chinese characters sharing the same sub-characters have different meanings. Furthermore, with more cultural interaction and the popularization of the Internet and web, many neologisms, such as transliterated loanwords and network terms, are emerging, which are only close to the pronunciation of their characters, but far from their semantics. Here, a tripartite weighted graph is proposed to model the semantic relationship among words, characters, and sub-characters, in which the semantic relationship is evaluated according to the Chinese linguistic information. So, the semantic relevance hidden in lower components (sub-characters, characters) can be used to further distinguish the semantics of corresponding higher components (characters, words). Then, the tripartite weighted graph is fed into our Chineseword embedding model insideCC to reveal the semantic relationship among different language components, and learn the embeddings of words. Extensive experimental results on multiple corpora and datasets verify that our proposed methods outperform the state-of-the-art counterparts by a significant margin.

关键词： natural language processing Chinese word embeddings Knowledge processing

来源：评论

学校读者我要写书评

暂无评论

Word Sense Disambiguation Model based on Bi-LSTM 14

Word Sense Disambiguation Model based on Bi-LSTM

引用

14th International conference on Measuring Technology and Mechatronics Automation, ICMTMA 2022

作者： Zhang, Liwei College of Communication and Information Engineering Xi'an University of Science and Technology Shaanxi710600 China

ISBN: (纸本)9781665499781

Word sense disambiguation is a very important task in natural language processing, and it is also a basic work in this field. There are many polysemous words in Chinese vocabulary. Using the word sense disambiguation model can determine the correct meaning of polysemous words in different contexts according to the context of polysemous words, so as to eliminate the ambiguity caused by polysemous words in Chinese. This paper proposes a neural sequence learning model based on Bi-LSTM (bidirectional long short memory) to realize word sense disambiguation. The word vector of the sentence is input into the neural network to train the similarity model, and the different sense items are classified, and the ambiguity is determined by the similarity comparison. The correct sense item of the word thus realizes the disambiguation of the word sense. Experiments show that the disambiguation model proposed in this paper has higher disambiguation accuracy than traditional methods. © 2022 IEEE

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Guided Reinforcement Learning for Low-Resource Unsupervised Syllabification

Knowledge-Guided Reinforcement Learning for Low-Resource Uns...

引用

International Joint conference on Neural Networks (IJCNN)

作者： Wenjun Wang Ling Dong Zhengtao Yu Yuxin Huang Junjun Guo Shengxiang Gao School of Information Engineering and Automation Kunming University of Science and Technology Kunming China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Syllabification is a crucial task in natural language processing, and syllables also play a significant role as modeling units in speech processing. While deep learning methods have shown remarkable progress in syllabification, they face challenges in low-resource languages where ready-made segmentation datasets or rules are lacking. Large language models (LLMs) are mostly unsuitable for these low-resource languages as well. To address these challenges, this paper proposes an unsupervised syllabification approach that incorporates logical reasoning into the reinforcement learning training process, achieving knowledge-guided syllabification. By introducing logical reasoning knowledge and modeling the interaction between the Agent and the knowledge base (KB), the model gains a better understanding of language structures and patterns. The study primarily focuses on low-resource Lao language, with experiments conducted on a publicly available English dataset to validate the effectiveness of the proposed method.

关键词： Training Deep learning Large language models Knowledge based systems Neural networks Reinforcement learning natural language processing

来源：评论

学校读者我要写书评

暂无评论

A Study on Sentiment Analysis of Twitter Data in Marathi language for Measuring Depression 1st

A Study on Sentiment Analysis of Twitter Data in Marathi Lan...

引用

1st International conference on Intelligent Systems and Applications

作者： Jakate, Mrunmayee Lavangare, Snehal Bhoir, Nirmiti Das, Aarushi Kadam, Deepali Datta Meghe Coll Engn Airoli Informat Technol Navi Mumbai India

ISBN: (纸本)9789811965814;9789811965807

Sentiment analysis is nothing but an information retrieval system based on natural language processing (NLP). It is a machine learning algorithm. The rudimentary prototype of sentiment analysis comes under the classifier problem where the negative, positive, and neutral are the classes we would be expecting as an output, given text (tweets in our case) as an input. Feature selection methods (information gain and chi square) and feature extraction will be performed to get the output sentiment. After studying three classifiers, support vector machine (SVM), K-nearest neighbour (KNN), and Naive Bayes, the latter algorithm, i.e. Naive Bayes being most accurate among them would be considered for implementation. As mentioned, we would be focusing on major three output sentiment classes: positive, negative, and neutral. Further, we are getting into a detailed analysis of tweets reflecting a depressive state of mind due to sadness. Though our ultimate goal is to predict the mental health of a user by observing the consistency and frequency of tweets along with its sentiment analysis, for now, we are just dealing with one tweet per user at a time.

关键词： Sentiment analysis Marathi text Depression Mental health Devanagari Information gain Chi square

来源：评论

学校读者我要写书评

暂无评论

OneBit: Towards Extremely Low-bit Large language Models 38

OneBit: Towards Extremely Low-bit Large Language Models

引用

38th conference on Neural Information processing Systems, NeurIPS 2024

作者： Xu, Yuzhuang Han, Xu Yang, Zonghan Wang, Shuo Zhu, Qingfu Liu, Zhiyuan Liu, Weidong Che, Wanxiang Research Center for Social Computing and Information Retrieval Harbin Institute of Technology Harbin China Department of Computer Science & Technology Tsinghua University Beijing China

Model quantification uses low bit-width values to represent the weight matrices of existing models to be quantized, which is a promising approach to reduce both storage and computational overheads of deploying highly anticipated LLMs. However, current quantization methods suffer severe performance degradation when the bit-width is extremely reduced, and thus focus on utilizing 4-bit or 8-bit values to quantize models. This paper boldly quantizes the weight matrices of LLMs to 1-bit, paving the way for the extremely low bit-width deployment of LLMs. For this target, we introduce a 1-bit model compressing framework named OneBit, including a novel 1-bit parameter representation method to better quantize LLMs as well as an effective parameter initialization method based on matrix decomposition to improve the convergence speed of the quantization framework. Sufficient experimental results indicate that OneBit achieves good performance (at least 81% of the non-quantized performance on LLaMA models) with robust training processes when only using 1-bit weight matrices. Code and checkpoints are available at https://***/xuyuzhuang11/OneBit. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OneRel: Joint Entity and Relation Extraction with One Module in One Step 36

OneRel: Joint Entity and Relation Extraction with One Module...

引用

36th AAAI conference on Artificial Intelligence / 34th conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence

作者： Shang, Yu-Ming Huang, Heyan Mao, Xian-Ling Beijing Inst Technol Sch Comp Sci & Technol Beijing Peoples R China Beijing Engn Res Ctr High Volume Language Informa Beijing Peoples R China

ISBN: (纸本)9781577358763

Joint entity and relation extraction is an essential task in natural language processing and knowledge graph construction. Existing approaches usually decompose the joint extraction task into several basic modules or processing steps to make it easy to conduct. However, such a paradigm ignores the fact that the three elements of a triple are interdependent and indivisible. Therefore, previous joint methods suffer from the problems of cascading errors and redundant information. To address these issues, in this paper, we propose a novel joint entity and relation extraction model, named OneRel, which casts joint extraction as a fine-grained triple classification problem. Specifically, our model consists of a scoring-based classifier and a relation-specific horns tagging strategy. The former evaluates whether a token pair and a relation belong to a factual triple. The latter ensures a simple but effective decoding process. Extensive experimental results on two widely used datasets demonstrate that the proposed method performs better than the state-of-the-art baselines, and delivers consistent performance gain on complex scenarios of various overlapping patterns and multiple triples.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Effective Use of Knowledge Graphs in a language Representation Model 14th

Effective Use of Knowledge Graphs in a Language Representati...

引用

14th International conference on Computer Science and its Applications, CSA 2022 and the 16th KIPS International conference on Ubiquitous Information Technologies and Applications, CUTE 2022

作者： Min, Chanwook Na, Hyungsun Song, Yeji Ahn, Jinhyun Im, Dong-Hyuk Kwangwoon University Seoul Korea Republic of Jeju National University Jeju Korea Republic of

ISBN: (纸本)9789819912513

methods such as knowledge-enabled language representation model (K-BERT) that help train models using external information, such as knowledge graphs, have recently been proposed in the field of natural language processing. However, adding knowledge that does not match the topic when external information is used may hinder training. Hence, a method is required that adds only knowledge matching the topic of the input data by partitioning the external information by topic. Topic-based knowledge graph BERT (TK-BERT), which uses the existing latent Dirichlet allocation (LDA) model to partition the knowledge, does not consider the contextual information. To compensate for this drawback and effectively use external information, this study uses the BERTopic technique to partition the knowledge graph. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

An QUIC Traffic Anomaly Detection Model Based on empirical Mode Decomposition 23

An QUIC Traffic Anomaly Detection Model Based on Empirical M...

引用

IEEE 23rd International conference on High Performance Switching and Routing (IEEE HPSR)

作者： Gang Lei Wu, Junyi Gu, Keyang Ji, Lejun Cao, Yuanlong Shao, Xun Jiangxi Normal Univ Sch Software Nanchang 330022 Jiangxi Peoples R China Kitami Inst Technol Sch Reg Innovat & Social Design Engn Kitami Hokkaido Japan

ISBN: (纸本)9781665406079

With the advent of the SG era, high-speed and secure network access services have become a common pursuit. The QUIC (Quick UDP Internet Connection) protocol proposed by Google has been studied by many scholars due to its high speed, robustness, and low latency. However, the research on the security of the QUIC protocol by domestic and foreign scholars is insufficient. Therefore, based on the self-similarity of QUIC network traffic, combined with traffic characteristics and signal processing methods, a QUIC-based network traffic anomaly detection model is proposed in this paper. The model decomposes and reconstructs the collected QUIC network traffic data through the empirical Mode Decomposition (EMD) method. In order to judge the occurrence of abnormality, this paper also intercepts overlapping traffic segments through sliding windows to calculate Hurst parameters and analyzes the obtained parameters to check abnormal traffic. The simulation results show that in the network environment based on the QUIC protocol, the Hurst parameter after being attacked fluctuates violently and exceeds the normal range. It also shows that the anomaly detection of QUIC network traffic can use the EMD method.

关键词： QUIC the empirical Mode Decomposition network traffic Hurst parameters

来源：评论

学校读者我要写书评

暂无评论

A Multi-teacher Knowledge Distillation Framework for Distantly Supervised Relation Extraction with Flexible Temperature 1

引用

7th Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) International Joint conference on Web and Big Data

作者： Fei, Hongxiao Tan, Yangying Huang, Wenti Long, Jun Huang, Jincai Yang, Liu Cent South Univ Sch Comp Sci & Engn Changsha Peoples R China Hunan Univ Sci & Technol Sch Comp Sci & Engn Xiangtan Peoples R China Cent South Univ Big Data Inst Changsha Peoples R China

ISBN: (数字)9789819723904

ISBN: (纸本)9789819723898;9789819723904

Distantly supervised relation extraction (DSRE) generates large-scale annotated data by aligning unstructured text with knowledge bases. However, automatic construction methods cause a substantial number of incorrect annotations, thereby introducing noise into the training process. Most sentence-level relation extraction methods rely on filters to remove noise instances, meanwhile, they ignore some useful information in negative instances. To effectively reduce noise interference, we propose a Multi-teacher Knowledge Distillation framework for Relation Extraction (MKDRE) to extract semantic relations from noisy data based on both global information and local information. MKDRE addresses two main problems: the deviation in knowledge propagation of a single teacher and the limitation of traditional distillation temperature on information utilization. Specifically, we utilize flexible temperature regulation (FTR) to adjust the temperature assigned to each training instance, so as to dynamically capture local relations between instances. Furthermore, we introduce information entropy of hidden layers to gain stable temperature calculations. Finally, we propose multi-view knowledge distillation (MVKD) to express global relations among teachers from various perspectives to gain more reliable knowledge. The experimental results on NYT19-1.0 and NYT19-2.0 datasets show that our proposed MKDRE significantly outperforms previous methods in sentence-level relation extraction.

关键词： Relation Extraction Knowledge Distillation Distantly Supervised Multiple Teachers 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 << < 477 478 479 480 481 482 483 484 485 486 > >>

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：