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

14,082 篇 会议
98 册 图书
64 篇 期刊文献
1 篇 资讯

馆藏范围

14,245 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

9,383 篇 工学
- 8,572 篇 计算机科学与技术...
- 6,863 篇 软件工程
- 1,927 篇 信息与通信工程
- 1,310 篇 控制科学与工程
- 1,209 篇 电气工程
- 906 篇 生物工程
- 418 篇 生物医学工程（可授...
- 417 篇 电子科学与技术（可...
- 413 篇 网络空间安全
- 307 篇 化学工程与技术
- 288 篇 仪器科学与技术
- 281 篇 机械工程
- 266 篇 光学工程
- 211 篇 安全科学与工程
- 196 篇 交通运输工程
3,131 篇 理学
- 1,227 篇 数学
- 932 篇 生物学
- 887 篇 物理学
- 486 篇 统计学（可授理学、...
- 460 篇 系统科学
- 355 篇 化学
2,812 篇 管理学
- 1,831 篇 图书情报与档案管...
- 1,191 篇 管理科学与工程(可...
- 463 篇 工商管理
567 篇 医学
- 408 篇 临床医学
- 365 篇 基础医学(可授医学...
- 312 篇 公共卫生与预防医...
- 163 篇 药学(可授医学、理...
450 篇 法学
- 418 篇 社会学
217 篇 教育学
- 213 篇 教育学
194 篇 文学
155 篇 经济学
98 篇 农学
11 篇 艺术学
9 篇 军事学
1 篇 哲学

主题

2,893 篇 natural language...
873 篇 natural language...
822 篇 natural language...
817 篇 semantics
552 篇 deep learning
537 篇 machine learning
514 篇 sentiment analys...
508 篇 data mining
390 篇 knowledge engine...
360 篇 computational mo...
358 篇 training
356 篇 large language m...
315 篇 speech recogniti...
310 篇 feature extracti...
302 篇 speech processin...
272 篇 signal processin...
261 篇 accuracy
239 篇 neural networks
235 篇 knowledge based ...
234 篇 transformers

机构

55 篇 institute of inf...
50 篇 school of cyber ...
50 篇 school of commun...
40 篇 maharishi school...
38 篇 chitkara univers...
35 篇 lovely professio...
34 篇 university of ch...
34 篇 school of comput...
32 篇 school of comput...
31 篇 xi'an university...
30 篇 faculty of engin...
27 篇 department of el...
23 篇 school of inform...
22 篇 school of comput...
22 篇 department of co...
20 篇 centre of interd...
20 篇 beijing universi...
18 篇 pune
17 篇 zhejiang univers...
17 篇 college of compu...

作者

38 篇 ren fuji
27 篇 wan wanggen
17 篇 liu yang
16 篇 yixin zhong
14 篇 wu jin
14 篇 lei li
14 篇 shingo kuroiwa
13 篇 zhang tao
13 篇 wang lei
13 篇 sabetzadeh mehrd...
13 篇 zheng dequan
13 篇 liu jie
12 篇 tiejun zhao
12 篇 f. ren
11 篇 li sheng
11 篇 yang yang
11 篇 tao zhang
11 篇 li ying
11 篇 arora chetan
11 篇 wang wei

语言

11,805 篇 英文
2,409 篇 其他
49 篇 中文
3 篇 土耳其文

检索条件"任意字段=IEEE International Conference on Natural Language Processing and Knowledge Engineering"

共 14245 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：

Effective Compression of language Models by Combining Pruning and knowledge Distillation 48

Effective Compression of Language Models by Combining Prunin...

引用

48th Annual ieee international Computers, Software, and Applications conference (COMPSAC) - Digital Development for a Better Future

作者： Chiu, Chi-Yu Hong, Ding-Yong Liu, Pangfeng Wu, Jan-Jan Natl Taiwan Univ Grad Inst Networking & Multimedia Taipei Taiwan Acad Sinica Inst Informat Sci Taipei Taiwan Natl Taiwan Univ Grad Inst Networking & Multimedia Dept Comp Sci & Informat Engn Taipei Taiwan

ISBN: (纸本)9798350376975;9798350376968

In recent years, Transformer has become an important architecture in language models and has achieved high performance in many natural language processing tasks. However, deploying Transformer architectures efficiently faces challenges because of their large model size and high inference time. Weight pruning is a prominent model compression technique that removes some weights in a model. However, after pruning, Transformer models require repeating the whole training process, including pre-training on a large generalized dataset and finetuning on a small downstream dataset, to recover the accuracy. The whole training process takes a long time and requires many computation resources. To address the challenge, this work proposes a pruning method that combines with knowledge distillation to avoid a long re-training time while recovering the accuracy. We use the N:M pruning method that is extended from NVIDIA's 2:4 pruning to compress the Transformer model. After pruning, we retrain the model by leveraging knowledge distillation to make the pruned model learn from the dense model. With this method, the pruned model can achieve comparable accuracy by using only downstream datasets and take much less time than traditional retraining. The experimental results show that DistilBERT in a 1:4 structure can achieve comparable accuracy on the SQuAD v1.1 and v2.0 datasets and a 1.7x speedups in inference time compared to the original dense model.

关键词： Model Compression knowledge Distillation Weight Pruning Transformer natural language processing

来源：评论

学校读者我要写书评

暂无评论

Designing and Evaluating a Comprehensive Benchmark for Deep Learning Algorithms in Medical natural language processing 15

Designing and Evaluating a Comprehensive Benchmark for Deep ...

引用

15th international conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Gill, Amandeep Shreenidhi, H.S. Shrivastav, Amit Kumar Vivekananda Global University Department of R&d Jaipur India School of Engineering and Technology Department of Computer Science and Engineering Karnataka Bangalore India Arka Jain University Office of Registrar Jharkhand Jamshedpur India

ISBN: (纸本)9798350370249

This paper gives a way for the comprehensive benchmarking of deep getting to know algorithms for scientific natural language processing (NLP). The authors suggest a benchmarking technique that includes both shallow and deep gaining knowledge of algorithms that cover a number of medical NLP responsibilities. Moreover, they examine the overall performance of algorithms on diverse clinical datasets and examine the overall performance of the algorithms via extraordinary assessment metrics. Furthermore, they present the effects in their proposed benchmarking on a number of datasets and describe how their consequences can assist practitioners in choosing appropriate algorithms to assess clinical NLP packages. Finally, the authors speak their destiny paintings in phrases of improving the benchmarking process. © 2024 ieee.

关键词： Algorithms Benchmarking Extraordinary language Performance Responsibilities

来源：评论

学校读者我要写书评

暂无评论

CTSP: Chinese Text Semantic Similarity Prediction 5

CTSP: Chinese Text Semantic Similarity Prediction

引用

5th international conference on Computer engineering and Application (ICCEA)

作者： He, Sirui Dalian Polytech Univ Dept Big Data Management & Applicat Dalian Liao Ning Peoples R China

ISBN: (纸本)9798350386783;9798350386776

Text Similarity (TS) is a fundamental natural language processing (NLP) task with widespread applications, such as information retrieval, question answering, and dialogue systems. Among the various methods to address Text Similarity, pre-training and fine-tuning paradigm is a promising solution. However, despite its prevalence, current fine-tuned TS model relies heavily on pre-training without domain-specific knowledge, which may result in neglecting word-level information in the language without explicit word segmentation such as Chinese. Moreover, insufficient contextual information learning would result in poor semantic disambiguation in short texts. To address the challenges, We propose a framework named CTSP (Chinese Text Similarity Prediction) that enhances Chinese Text Similarity (TS) through the integration of Word Input, Self-Attention Interference, and Sentence Pairs Classification. In particular, our framework has demonstrated a notable 2% F1 score improvement on the ATEC dataset.

关键词： chinese text similarity prediction language model

来源：评论

学校读者我要写书评

暂无评论

Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting 11

Beyond Simple Averaging: Improving NLP Ensemble Performance ...

引用

ieee 11th international conference on Data Science and Advanced Analytics (DSAA)

作者： Proskura, Polina Zaytsev, Alexey Inst Informat Transmiss Problems Moscow Russia Skolkovo Inst Sci & Technol Risk Management Sber Moscow Russia

ISBN: (纸本)9798350364941;9798350364958

In machine learning, ensembles are important tools for improving the model performance. In natural language processing specifically, ensembles boost the performance of a method due to multiple large models available in open source. However, existing approaches mostly rely on simple averaging of predictions by ensembles with equal weights for each model, ignoring differences in the quality and conformity of models. We propose to estimate weights for ensembles of NLP models using not only knowledge of their individual performance but also their similarity to each other. By adopting distance measures based on Topological Data Analysis (TDA), we improve our ensemble. The quality improves for both text classification accuracy and relevant uncertainty estimation.

关键词： neural network ensembles deep Learning uncertainty estimation natural language processing topological data analysis

来源：评论

学校读者我要写书评

暂无评论

TURN-TAKING AND BACKCHANNEL PREDICTION WITH ACOUSTIC AND LARGE language MODEL FUSION 49

TURN-TAKING AND BACKCHANNEL PREDICTION WITH ACOUSTIC AND LAR...

引用

49th ieee international conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Wang, Jinhan Chen, Long Khare, Aparna Raju, Anirudh Dheram, Pranav He, Di Wu, Minhua Stolcke, Andreas Ravichandran, Venkatesh Univ Calif Los Angeles Los Angeles CA 90095 USA Amazon Alexa AI Seattle WA USA

ISBN: (纸本)9798350344868;9798350344851

We propose an approach for continuous prediction of turn-taking and backchanneling locations in spoken dialogue by fusing a neural acoustic model with a large language model (LLM). Experiments on the Switchboard human-human conversation dataset demonstrate that our approach consistently outperforms the baseline models with single modality. We also develop a novel multi-task instruction finetuning strategy to further benefit from LLM-encoded knowledge for understanding the tasks and conversational contexts, leading to additional improvements. Our approach demonstrates the potential of combined LLMs and acoustic models for a more natural and conversational interaction between humans and speech-enabled AI agents.

关键词： turn-taking backchannel large language model model fusion instruction tuning.

来源：评论

学校读者我要写书评

暂无评论

language Model Embeddings to Improve Performance in Downstream Tasks 16

Language Model Embeddings to Improve Performance in Downstre...

引用

16th ieee international conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Pawar, Abhishek Patil, Parag Hiwanj, Riya Kshatriya, Ajinkya Chikmurge, Diptee Barve, Sunita Mit Academy of Engineering Alandi Pune India Ljmu University Liverpool United Kingdom

ISBN: (纸本)9798331505264

natural language processing (NLP) has made significant breakthroughs, mainly in the creation of transformer-based language models, and has demonstrated great performance in a variety of language comprehension tasks. Despite these achievements, maximizing the possibilities for downstream applications remains an ongoing problem. While models based on transformers excel at learning contextualized representations during pretraining, they can benefit from focused modifications in downstream tasks. Our study highlights the advantages of domain-specific model embeddings over fine-tuning language models based on generalized transformers. The study methodology entails a detailed examination of textual datasets, including Marathi news corpus, medical text, and legal references. Sophisticated cleaning procedures are applied to enhance model performance. The proposed end-to-end pipeline comprises validation, classification, RoBERTa fine-tuning, and data selection for downstream processes. Through a more nuanced knowledge of the evolving field of natural language processing (NLP), this research advances our understanding of the effectiveness and adaptability of refined transformer-based language model embeddings in real-world applications. © 2024 ieee.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

GPT-Powered Elicitation Interview Script Generator for Requirements engineering Training 32

GPT-Powered Elicitation Interview Script Generator for Requi...

引用

32nd ieee international Requirements engineering conference (RE)

作者： Gorer, Binnur Aydemir, Fatma Basak Microsoft Istanbul Turkiye Univ Utrecht Utrecht Netherlands

ISBN: (纸本)9798350395129;9798350395112

Elicitation interviews are the most common requirements elicitation technique, and proficiency in conducting these interviews is crucial for requirements elicitation. Traditional training methods, typically limited to textbook learning, may not sufficiently address the practical complexities of interviewing techniques. Practical training with various interview scenarios is important for understanding how to apply theoretical knowledge in real-world contexts. However, there is a shortage of educational interview material, as creating interview scripts requires both technical expertise and creativity. To address this issue, we develop a specialized GPT agent for auto-generating interview scripts. The GPT agent is equipped with a dedicated knowledge base tailored to the guidelines and best practices of requirements elicitation interview procedures. We employ a prompt chaining approach to mitigate the output length constraint of GPT to be able to generate thorough and detailed interview scripts. This involves dividing the interview into sections and crafting distinct prompts for each, allowing for the generation of complete content for each section. The generated scripts are assessed through standard natural language generation evaluation metrics and an expert judgment study, confirming their applicability in requirements engineering training.

关键词： large language models prompt engineering elicitation interview script generation requirements engineering education

来源：评论

学校读者我要写书评

暂无评论

Enhancing knowledge Selection with Data processing Based on Multiple Turns of Dialog in knowledge-Grounded Open-Domain Conversations

Enhancing Knowledge Selection with Data Processing Based on ...

引用

international conference on Big Data and Smart Computing (BigComp)

作者： Joo, Eojin Lee, Do Kyung Youn, Junyoung Sung, Joo-Won Choi, Ho-Jin Korea Adv Inst Sci & Technol Sch Comp Daejeon South Korea KT AI2XL Seoul South Korea

ISBN: (纸本)9798350370027;9798350370034

In NLG, recent research in knowledge-Grounded Text Generation aims to refine sentence specificity and naturalness. When generating texts, considering multiple turns within a conversation is considered important because it allows models to generate sentences that reflect the context of the conversation. Addressing open-domain conversations, determining the optimal conversation history for training knowledge selection models lacks prior exploration. This study aims to improve KGTG models to effectively handle complex utterances by progressively incorporating more turns. This finding offers a foundational direction for boosting knowledge selection models in text generation.

关键词： knowledge Selection natural language Generation knowledge-Grounded Text Generation Deep Learning

来源：评论

学校读者我要写书评

暂无评论

ByteScience: Bridging Unstructured Scientific Literature and Structured Data with Auto Fine-tuned Large language Model in Token Granularity 24

ByteScience: Bridging Unstructured Scientific Literature and...

引用

24th ieee international conference on Data Mining Workshops, ICDMW 2024

作者： Xie, Tong Zhang, Hanzhi Wang, Shaozhou Wan, Yuwei Razzak, Imran Kit, Chunyu Zhang, Wenjie Hoex, Bram GreenDynamics Australia University of New South Wales School of Photovoltaic and Renewable Energy Engineering Australia University of North Texas Dept. of Computer Science and Engineering Denton United States University of New South Wales School of Computer Science and Engineering Australia City University of Hong Kong Dept. of Linguistics and Translation Hong Kong Hong Kong

ISBN: (纸本)9798331530631

natural language processing (NLP) is widely used to supply summarization ability from long context to structured information. However, extracting structured knowledge from scientific text by NLP models remains a challenge because of its domain-specific nature to complex data preprocessing and the granularity of multi-layered device-level information. To address this, we introduce ByteScience, a non-profit cloud-based auto finetuned Large language Model (LLM) platform, which is designed to extract structured scientific data and synthesize new scientific knowledge from vast scientific corpora. The platform capitalizes on DARWIN, an open-source, fine-tuned LLM dedicated to natural science. The platform was built on Amazon Web Services (AWS) and provides an automated, user-friendly workflow for custom model development and data extraction. The platform achieves remarkable accuracy with only a small amount of well-annotated articles. This innovative tool streamlines the transition from the science literature to structured knowledge and data and benefits the advancements in natural informatics. Demo Video. © 2024 ieee.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Computer-Assisted knowledge Points and Question Difficulty Classification Based on BERT

Computer-Assisted Knowledge Points and Question Difficulty C...

引用

2024 international conference on Mechatronics and Intelligent Control, ICMIC 2024

作者： Zhu, Jia Jun Yang, Zichuan Hong, Binjie Song, Jiacheng Wang, Jiwei Chen, Tianhao Yang, Shuilan Lan, Zixun Ma, Fei Department of Information and Computing Science Xi'an Jiaotong-Liverpool University Suzhou China School of Engineering Suzhou Centennial College Suzhou China Department of Applied Mathematics Xi'an Jiaotong-Liverpool University Suzhou China GROW Inc. Suzhou China EasyStack Inc. Nanjing China TAL Education Group Beijing China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

In recent years, with the increasing use of educational technology and online learning platforms, there has been a growing interest in developing intelligent systems that can automatically predict the knowledge points associated with educational questions. This paper presents a novel approach for knowledge point prediction in middle school mathematics questions. The dataset used in this study consists of a large collection of 591,379 middle school mathematics questions. To leverage the power of natural language processing techniques, the questions are preprocessed using a tokenizer and encoded into word embeddings using BERT (Bidirectional Encoder Representations from Transformers). Matrix dot production is then employed to calculate the similarity between each test question and the training set, and the top-n most similar vectors are selected for each test question. A voting mechanism is introduced to eliminate duplicate knowledge points and rank them based on their total scores in descending order, resulting in k candidate solutions. The performance of the proposed approach is evaluated using top-k accuracy as the evaluation metric and a lowest common ancestor (LCA) algorithm is used to calculate accuracy at different levels of the knowledge point tree. The results demonstrate the effectiveness of the proposed approach in predicting knowledge points for middle school mathematics questions and its potential for application in intelligent tutoring systems and educational assessment tools. © 2025 SPIE.

关键词： natural language processing systems

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：