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101-110 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：

Outperforming Larger Models on Text Classification Through Continued Pre-training 13th

Outperforming Larger Models on Text Classification Through C...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Zheng, Yu Liu, Ming Ao, Zou Hao, Wenning Zhang, Hui Sun, Yi Army Engn Univ PLA Coll Command & Control Engn Nanjing 210007 Peoples R China Natl Univ Def Technol Res Inst 63 Nanjing 210007 Peoples R China Natl Univ Def Technol Lab Big Data & Decis Changsha 410073 Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Generative large language models (LLMs), such as GPT-4, have demonstrated remarkable performance across a wide range of NLP tasks. The increased number of LLMs' parameters enhances their generalization capabilities, but it also results in a higher computational burden and slower inference speed. Addressing these concern, through continued pre-training, we have enhanced the BERT model (based on MLM and NSP pre-training tasks) to achieve performance comparable to that of the large Qwen-1.5 series models in zero-shot and few-shot text classification tasks, demonstrating that non-generative pre-trained models like BERT are still relevant. Additionally, by using LLMs to expand topic words related to downstream tasks and employing word density methods to retrieve corresponding subsets from large corpora, we have obtained better pre-training results.

关键词： PLMs Continued Pre-training Corpus

来源：评论

学校读者我要写书评

暂无评论

Chinese Personalized Commonsense Understanding and Reasoning Based on Curriculum-Learning 13th

Chinese Personalized Commonsense Understanding and Reasoning...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Yang, Yong Li, Weijie Fan, Xiaochao Deng, Wenjun Liu, Jiapeng Diao, Yufeng Tuerxun, Palidan Xinjiang Univ Sch Software Urumqi Xinjiang Peoples R China Xinjiang Normal Univ Coll Comp Sci & Technol Urumqi Xinjiang Peoples R China Inner Mongolia Minzu Univ Coll Comp Sci & Technol Tongliao Inner Mongolia Peoples R China

ISBN: (纸本)9789819794331;9789819794348

The development of general-purpose artificial intelligence that can understand and reason with common sense is a significant challenge. However, there has been a lack of research on fully considering personality traits in common sense understanding and reasoning tasks. To address this, we create a personalized commonsense knowledge comprehension and reasoning dataset. This dataset organizes reasoning knowledge with typed if-then relations and variables, while also introducing personality traits as constraints. We adopt a two-stage training framework based on curriculum-learning to gradually improve the model's personalized commonsense knowledge comprehension and reasoning ability. Additionally, We compare pre-trained language models such as BERT, GPT2, and BART with different structures. The experimental results show that the models trained using the curriculum-learning training framework are able to generate more diversified and personality-trait-compliant commonsense reasoning results.

关键词： Personality traits Commonsense knowledge base Pre-trained language models Personalized common sense understanding and reasoning

来源：评论

学校读者我要写书评

暂无评论

Harnessing Knowledge Distillation for Enhanced Text-to-Text Translation in Low-Resource Languages 26th

Harnessing Knowledge Distillation for Enhanced Text-to-Text ...

引用

26th International Conference on Speech and Computer

作者： Ahmed, Manar Ouled Ming, Zuheng Othmani, Alice Declic AI Res Riyadh Saudi Arabia Deck AI Res Melbourne Vic Australia Univ Sorbonne Paris Nord L2TI Villetaneuse France Univ Paris Est UPEC LISSI Vitry Sur Seine France

ISBN: (纸本)9783031780134;9783031780141

Text-to-text translation is crucial for effective communication and understanding across different languages. In this paper, we present a deep learning-based approach for text-to-text translation. Our method leverages knowledge distillation from a high-performing teacher model, specifically the BART model, to train a smaller and more efficient student model, the mBART model. For that, we minimize the cross-entropy between the model distribution and a learned teacher distribution rather than the observed data, to achieve effective knowledge distillation. Our approach mitigates catastrophic forgetting, especially in low-resource languages, by utilizing the complementary knowledge provided by the teacher model. Extensive experimentation and evaluation demonstrate that our model outperforms state-of-the-art methods, achieving superior BLEU scores on benchmark datasets for French-to-Russian, English-to-Dutch, and Russian-to-Vietnamese translations. An ablation study further shows that the combination of fine-tuning and knowledge distillation enhances the student model's ability to capture linguistic nuances and produce more accurate translations.

关键词： Text-to-text BART Low-resource languages

来源：评论

学校读者我要写书评

暂无评论

Leveraging Two-Stream Cause-Effect Relation for Emotion-Cause Analysis 13th

Leveraging Two-Stream Cause-Effect Relation for Emotion-Caus...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Ran, Junfeng Tian, Zailong Luo, Weiyao Li, Sujian Peking Univ MOE Key Lab Computat Linguist Beijing Peoples R China

ISBN: (纸本)9789819794393;9789819794409

Emotion Cause Analysis (ECA) is a task to analyze corresponding causes for emotions expressed in a text, utilizing explicit or implicit cause-effect relations between them. Previous research typically focused on sequence labeling methods to extract emotions and their corresponding causes, or clause pairing matrix methods to extract emotion-cause pairs directly. However, the sequence labeling methods fail to build mutual interactions between emotions and the causes, and the clause pairing matrix methods may confuse whether emotions are effects of the causes or reasons of other events. To address these limitations, we propose a method that enables the model to consider "how emotions are affected by the causes" and "How the causes lead to emotions", namely the emotion-cause stream (ECS) and the cause-emotion stream (CES). We leverage discourse conjunctions as a bridge between these two streams, incorporating their discourse information to recognize two-way cause-effect relations, thereby enhancing the reasoning ability of our model. Further, we employ the conjunctions predicted by ChatGPT to assist our model in achieving better results, and our research demonstrates that our model achieves SOTA results in ECA and proves the superiority of our model.

关键词： Emotion-Cause Analysis Cause-Effect Relation Two-Stream Analysis

来源：评论

学校读者我要写书评

暂无评论

RAVL: A Retrieval-Augmented Visual Language Model Framework for Knowledge-Based Visual Question Answering 13th

RAVL: A Retrieval-Augmented Visual Language Model Framework ...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Chai, Naiquan Zou, Dongsheng Liu, Jiyuan Wang, Hao Yang, Yuming Song, Xinyi Chongqing Univ Sch Comp Sci Chongqing Peoples R China

ISBN: (纸本)9789819794362;9789819794379

Knowledge-based visual question answering (VQA) requires external knowledge in addition to the image content to answer questions. Recent studies convert images to text descriptions and then generate answers or acquire implicit knowledge using a large language model (LLM). These methods achieve encouraging results with the strong knowledge retrieval and reasoning capabilities of LLMs. However, methods that incorporate LLMs are limited by the discrepancies between images and their text descriptions presented to LLMs. To address this challenge, we present RAVL, a retrieval-augmented visual language model (VLM) framework for knowledge-based VQA. Specifically, we first fine-tune a VLM on the knowledge-based VQA task with inputs consisting of retrieved knowledge and image-question pairs to adapt the VLM to inputs with retrieved knowledge. After that, we adapt the retrieval module to the fine-tuned VLM using supervision signals provided by the VLM, enabling the retrieved knowledge to improve the VLM perplexity. RAVL overcomes the limitation of visual information loss and improves the effectiveness of VLMs with external knowledge. We conduct experiments on OK-VQA dataset and our method achieves 65.73% accuracy, surpassing the previous state-of-the-art method (+3.63%).

关键词： Knowledge-based visual question answering Retrieval augmentation Visual language model

来源：评论

学校读者我要写书评

暂无评论

CKF: Conditional Knowledge Fusion Method for CommonSense Question Answering 13th

CKF: Conditional Knowledge Fusion Method for CommonSense Que...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Xie, Minghui Hao, Chuzhan Zhang, Peng Ma, XinDian Tianjin Univ Coll Intelligence & Comp Tianjin Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Augmenting pretrained language model (PLM) with knowledge graph (KG) has demonstrated superior performance for commonsense question answering (CSQA). In the knowledge fusion process, existing KG-augmented methods ignore (i) exploiting the knowledge of PLM and (ii) the supervisory role of PLM. As a result, the noise of KG cannot be filtered effectively in the knowledge fusion process. In this paper, we propose a Conditional Knowledge Fusion method (CKF) (https:// ***/Xie-Minghui/CKF/). to enhance the commonsense reasoning ability of PLM. First, we apply the prompt learning method to exploit the knowledge of PLM which can provide a better semantic supervision signal for the knowledge fusion process. Second, we design a conditional fusion module to filter out the noise of KG. To further improve performance, we design a re-attention mechanism to supplement PLM with commonsense knowledge. Experimental results demonstrate the superior effectiveness of CKF through considerable performance gains across three popular benchmark datasets.

关键词： Conditional knowledge fusion Commonsense reasoning Question answering

来源：评论

学校读者我要写书评

暂无评论

Pre-training and Adverse Audio Samples for Data-Efficient Wake Word Detection 26th

Pre-training and Adverse Audio Samples for Data-Efficient Wa...

引用

26th International Conference on Speech and Computer

作者： Torralbo, Manuel Mendez, Ariane Agirre, Maia Del Pozo, Arantza Vicomtech Fdn Basque Res & Technol Alliance BRTA Mikeletegi 57 Donostia San Sebastian 20009 Spain

ISBN: (纸本)9783031779602;9783031779619

This work investigates the impact of pre-training and the use of adverse audio samples on both the data efficiency and performance of end-to-end neural Wake Word Detection systems. Alongside intensive data augmentation, the proposed methodology involves pre-training Keyword Spotting models, followed by fine-tuning to recognize specific wake words by leveraging their foundational capabilities. The study also examines the inclusion of adverse audio samples resembling the target wake word. Experiments evaluate various state-of-the-art architectures to assess the effects of model size, amount of training data, model pre-training, and the incorporation of adverse audio samples on system performance. Results demonstrate that pre-training improves performance, with fine-tuned models consistently outperforming those trained from scratch, especially with limited data. Additionally, training with adverse samples resembling the wake word also enhances results by reducing false acceptance rates. These findings provide valuable insights for developing data-efficient Wake Word Detection systems.

关键词： Wake word detection Pre-training Adverse audio samples Data-efficient

来源：评论

学校读者我要写书评

暂无评论

Investigating Data Requirements for Hindi Speaker Recognition: A Comparative Study with English 26th

Investigating Data Requirements for Hindi Speaker Recognitio...

引用

26th International Conference on Speech and Computer

作者： Khadse, Parth Chandra, Sabyasachi Bharati, Puja Pramanik, Debolina Prasad, G. Satya Aitawade, Aniket Das Mandal, Shyamal Kumar Indian Inst Technol Kharagpur W Bengal India

ISBN: (纸本)9783031780134;9783031780141

Speaker recognition is a method that assigns a distinct identity to each individual voice. For developing these systems generally, a large amount of data is required which should have a large number of speakers usually in thousands and a moderate amount of utterances per speaker. For under-resourced indo-aryan languages like Hindi such large datasets with a huge number of speakers are not freely available yet. This paper aims to study of how much data is required (in terms of number of speakers and amount of data in terms of hours) to train speaker recognition models for the under-resourced languages. To find the answer to this question, this paper presents the results of adapting the d-vector speaker verification model which is pre-trained on English data to the Hindi language. The results of the model are shown in terms of Equal Error Rate (EER) and Detection Cost Function (DCF) when the model is trained from scratch as well as after the adaption of the pre-trained English model. The EER of 4.46% was observed when the English model was finetuned using the Hindi data which was only around 35% of the English data in terms of a number of hours and the performance of this model is pretty close to the performance of the model trained in the English Language.

关键词： D-vector Speaker recognition Speaker verification Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Overview of the NLPCC 2024 Shared Task 2: Nominal Compound Chain Extraction 13th

Overview of the NLPCC 2024 Shared Task 2: Nominal Compound C...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Li, Bobo Fei, Hao Li, Fei Ji, Donghong Wuhan Univ Sch Cyber Sci & Engn Key Lab Aerosp Informat Secur & Trusted Comp Minist Educ Wuhan Peoples R China Natl Univ Singapore Sch Comp Singapore Singapore

ISBN: (纸本)9789819794423;9789819794430

Nominal compound chain extraction (NCCE) represents an emerging task within the domain of natural language processing, exhibiting significant potential for application in various downstream tasks, including relation extraction and summarization, etc. This task involves analyzing a document to identify and categorize all nominal compounds into distinct clusters based on semantic relatedness. Consequently, NCCE presents greater challenges than traditional coreference resolution tasks due to its reliance on semantic associations. In response to these challenges, we initiated a shared task at NLPCC 2024, attracting 15 teams to register, of which 5 submitted their final results. We introduced a baseline system to benchmark performance in this area. This paper provides a comprehensive overview of the NCCE task, detailing the task's framework, dataset characteristics, evaluation protocols, and metrics, alongside a summary of the submission results. We anticipate that the task will significantly aid in corpus construction and enhance the semantic understanding of the Chinese language.

关键词： Nominal Compound Chain Extraction Coreference Resolution Information Extraction

来源：评论

学校读者我要写书评

暂无评论

HTCSI: A Hierarchical Text Classification Method Based on Selection-Inference 13th

HTCSI: A Hierarchical Text Classification Method Based on Se...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Xu, Yiming Feng, Jianzhou Gu, Chenghan Qin, Haonan Xue, Kehan Yanshan Univ Sch Informat Sci & Engn Qinhuangdao 066000 Hebei Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Hierarchical Text Classification (HTC) is a complex task that involves categorizing text within a hierarchical labeling system. Current methodologies primarily focus on integrating hierarchical information into encoding models to achieve enhanced text representations. However, the intricate nature of the process obtaining representation often diminishes the model's interpretability, leaving researchers uncertain about the model's effective utilization of hierarchical information and the rationale behind its results. In this paper, we introduce a novel Hierarchical Text Classification method based on Selection-Inference(HTCSI) using large language models (LLMs) to enhance interpretability. Specifically, we leverage classification paths within the labeling hierarchy as cue information to guide LLM reasoning. Additionally, we develop a path selection module to identify the most probable classification paths, thereby minimizing the impact of irrelevant information on LLM reasoning. We employ the Parameter-Efficient Fine-Tuning (PEFT) method to bolster the reasoning capabilities of LLMs, thus improving the accuracy of hierarchical text classification while ensuring a more reliable reasoning process. Experiments conducted on several standard datasets demonstrate that HTCSI not only enhances credible classification reasoning but also surpasses other advanced HTC methods.

关键词： Hierarchical Text Classification Large Language Models Chain of Thought

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 << < 7 8 9 10 11 12 13 14 15 16 > >>

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：