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121-130 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 End-to-End Speech Translation with Progressive Dual Encoding 13th

Improving End-to-End Speech Translation with Progressive Dua...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Zhang, Runlai Chen, Saihan Zhang, Yuhao Du, Yangfan Chen, Hao Xiao, Tong Zhu, Jingbo Northeastern Univ Sch Comp Sci & Engn Shenyang Peoples R China NiuTrans Res Shenyang Peoples R China

ISBN: (纸本)9789819794362;9789819794379

In end-to-end speech translation (E2E ST), multi-task learning is often applied due to the scarcity of labeled ST data. However, the modality gap between speech and source text poses a significant challenge for transferring knowledge from machine translation (MT) models to speech translation models. Currently, one of the main approaches to address this problem focuses on utilizing a powerful self-supervised pre-trained speech encoder to learn the text embeddings from the MT model. This method involves cross-modal representation learning and heavily relies on the capability of the speech encoder. However, pretraining such a speech encoder is expensive and difficult to replicate. To this end, we propose the Progressive Dual Encoding (PDE) method, which aims to provide a lightweight, pretraining-free approach for E2E ST encoding. This is achieved by introducing an additional text encoder that collaborates with the speech encoder to progressively explore a shared representation space under a novel multi-scale constraint. In this way, our method allows the dual-modality encoders to naturally output similar representations, thereby avoiding the challenges of cross-modal representation learning and alleviating the burden on the speech encoder. We evaluate our method on the MuST-C dataset. The experimental results demonstrate that our method achieves competitive performance with other methods while using fewer parameters in the speech encoder. Moreover, it surpasses other methods by 0.6-1.8 average BLEU score when the number of parameters is increased.

关键词： End-to-End Speech Translation Progressive Dual Encoding Multi-scale Constraint

来源：评论

学校读者我要写书评

暂无评论

The Benefits in Shallow: Merge Decoding Across Large Language Model Layers 13th

The Benefits in Shallow: Merge Decoding Across Large Languag...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Zhou, Yuechi Zhou, Chuyue Xie, Wenjing Wang, Xinrui Chen, Jiuchang Ni, Zhenghua Li, Juntao Soochow Univ Inst Comp Sci & Technol Suzhou Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Large language models (LLMs) have become foundational to numerous natural language processing tasks;however, decoding coherent and contextually relevant text remains a complex challenge. In openended generation, maximizing probability is often not the appropriate objective, as with sampling methods, the continuation tends to be incoherent and repetitive in various degrees. We propose Merge Decoding, merging information in the shallow layer, such as sequential information, with the final task-specific layer, thereby generating coherent and rich text. MD works across three scales of the LLaMA family(7B, 13B, 30B), achieving higher quality text in open-ended text generation (Wiki-Text, WikiNews, BookCorpus) and enhancing reasoning capabilities in downstream tasks (Gsm8k, StrategyQA) https://***/YcChou/MergeDecoding.

关键词： Large language model Decoding strategy Text generation

来源：评论

学校读者我要写书评

暂无评论

AQLoRA: An Adaptive Quantization-Based Efficient Fine-Tuning Method for LLMs 13th

AQLoRA: An Adaptive Quantization-Based Efficient Fine-Tuning...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Huang, Xingchen Hu, Yujia Wong, Derek F. Wang, Yao Cal, Liqiong Jiang, Yonghong Guizhou Minzu Univ Sch Data Sci & Informat Engn Guiyang Peoples R China Univ Macau NLP2CT Lab Macau Peoples R China Univ Macau Dept Comp & Informat Sci Macau Peoples R China Guizhou SiSo Elect Co LTD Guiyang Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Large language models (LLMs) have shown exceptional performance in the domain of composite artificial intelligence tasks, offering a preliminary insight into the potential of general artificial intelligence. The fine-tuning process for LLMs necessitates significant computational resources, often surpassing those available from standard consumer-grade GPUs. To this end, we introduce the Adaptive Quantization Low-Rank Adaptation fine-tuning (AQLoRA), a method that reduces memory demands during fine-tuning by utilizing quantization coupled with pruning techniques. This dual strategy not only reduces memory usage but also preserves accuracy. AQLoRA refines the original Low-Rank Adaptation fine-tuning (LoRA) method by efficiently quantizing LLMs weights, prioritizing computational resource allocation based on weight importance, and effectively integrating the quantized model with auxiliary weights post fine-tuning. Applying AQLoRA to the ChatGLM2-6B model, we demonstrate its effectiveness in both natural language generation (NLG) and natural language understanding (NLU) across diverse fine-tuning datasets and scenarios. Our findings reveal that AQLoRA achieves balance between performance and memory efficiency, reducing memory consumption by 25% in NLG tasks. For NLU tasks, it enhances performance by 10% and reduces memory consumption by 10% compared to state-of-the-art methods.

关键词： Large Language Model Fine-tuning LoRA

来源：评论

学校读者我要写书评

暂无评论

In Pursuit for the Best Error Metric for Optimisation of Articulatory Vowel Synthesis 26th

In Pursuit for the Best Error Metric for Optimisation of Art...

引用

26th International Conference on Speech and Computer

作者： Gerazov, Branislav Krug, Paul Konstantin van Niekerk, Daniel Xu, Anqi Birkholz, Peter Xu, Yi Ss Cyril & Methodius Univ Skopje Fac Elect Engn & Informat Technol Skopje North Macedonia Tech Univ Dresden Inst Acoust & Speech Commun Dresden Germany UCL Dept Speech Hearing & Phonet Sci London England

ISBN: (纸本)9783031780134;9783031780141

The way infants use auditory cues to learn to speak despite the acoustic mismatch of their vocal apparatus is a hot topic of scientific debate. The simulation of early vocal learning using articulatory speech synthesis offers a way towards gaining a deeper understanding of this process. One of the crucial parameters in these simulations is the choice of features and a metric to evaluate the acoustic error between the synthesised sound and the reference target. We contribute with evaluating the performance of a set of 40 feature-metric combinations for the task of optimising the production of static vowels with a high-quality articulatory synthesiser. Towards this end we assess the usability of formant error and the projection of the feature-metric error surface in the normalised F1-F2 formant space. We show that this approach can be used to evaluate the impact of features and metrics and also to offer insight to perceptual results.

关键词： Vocal learning Speech features Distance metrics Formant space VocalTractLab

来源：评论

学校读者我要写书评

暂无评论

Finetuning LLMs for Text-to-SQL with Two-Stage Progressive Learning 13th

Finetuning LLMs for Text-to-SQL with Two-Stage Progressive L...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Ling, Xiao Liu, Jialin Liu, Jindu Wu, Jianhua 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

With the widespread usage of large language model (LLMs), LLM-based method has become the mainstream approach for Text-to-SQL tasks, achieving leading performance on Text-to-SQL leaderboards. However, generating complex SQL queries correctly has always been a main challenge. Current LLM-based models primarily utilize prompting-based methods on large scale closed-source LLMs (e.g., GPT-4 and ChatGPT), which may cause concerns of usage costs and data privacy. For fine-tuning based methods, it is difficult to generate complex SQL accurately in only one fine-tuning step. Focusing on this, we propose TSPSQL, a Two-Stage Progressive learning method for Text-to-SQL. TSPSQL decomposes Text-to-SQL task into two stages: SQL elements generation auxiliary task, and SQL query generation main task. The two tasks are progressively fine-tuned on a single model, effectively reducing the difficulty of SQL generation and improving accuracy. TSP-SQL achieves state-of-the-art performance among open-source fine-tuning based methods on Spider dev set, and surpasses most of the methods based on large scale closed-source LLMs.

关键词： Text-to-SQL Large Languages Models Progressive Learning

来源：评论

学校读者我要写书评

暂无评论

LasQ: Largest Singular Components Fine-Tuning for LLMs with Quantization 13th

LasQ: Largest Singular Components Fine-Tuning for LLMs with ...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Zhao, Xiang Lin, Beining Song, You Beihang Univ Sch Software Beijing 100191 Peoples R China

ISBN: (纸本)9789819794362;9789819794379

Large language models (LLMs) have demonstrated strong capabilities in various industries, but as the model parameters increase, the computational cost of fine-tuning the entire model becomes extremely high. To address this challenge, we focus on applying quantization and LoRA fine-tuning together in pre-training scenarios and propose an efficient parameter fine-tuning (PEFT) method, the LasQ (Largest Singular Components Fine-tuning for LLMs with Quantization) framework. Performs singular value decomposition on the pre-trained weights after quantization, using high-order singular value components to initialize the low rank adapter. We evaluate our method in natural language understanding, question answering, summarization, and natural language generation tasks. The experiments show that our method can significantly outperform existing methods with fewer training parameters. Compared with LoftQ and QLoRA methods, it has a 2%-15% improvement, and it can even achieve equivalent LoRA fine-tuning effects and full parameter fine-tuning effects.

关键词： LLMs Finetune Quantization

来源：评论

学校读者我要写书评

暂无评论

PROMPTIST: Automated Prompt Optimization for Text-to-Image Synthesis 13th

PROMPTIST: Automated Prompt Optimization for Text-to-Image S...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Li, WeiJie Wane, Jin Zhang, Xuejie Yunnan Univ Kunming Yunnan Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Recent advancements in text-to-image synthesis (TIS) models, such as DALL-E 3 and stable diffusion XL, have significantly improved image quality. However, these models typically require experts with artistic and photographic expertise to create model-preferred prompts for high-quality image generation, a requirement that challenges non-experts in real-world applications. This study proposes PROMPTIST, an automated framework that optimizes user-original prompts into model-preferred prompts, thereby enabling TIS models to produce more aesthetically pleasing images. We employ the retrieval augmented generation (RAG) technique with Large Language Models (LLMs) to automatically refine prompts, ensuring that the proposed framework is broadly applicable and extends beyond the specific models' styles like stable diffusion or DALL-E. Furthermore, to ensure the LLMs generate visually appealing images, we fine-tuned a quality assessment model to analyze prompt quality and provide necessary feedback to the LLMs. The proposed prompt engineering method for LLMs can significantly enhance the quality of both prompts and images. Extensive experimental results consistently demonstrate PROMPTIST's superiority over strong baselines.

关键词： Retrieve Augmented Generation Large Language Models Text-to-image

来源：评论

学校读者我要写书评

暂无评论

Explore the Textual Perception Ability on the Images for Multimodal Large Language Models 13th

Explore the Textual Perception Ability on the Images for Mul...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Kuang, Jiayi Ouyang, Jiarui Shen, Ying Sun Yat Sen Univ Guangzhou Guangdong Peoples R China

ISBN: (纸本)9789819794423;9789819794430

Chinese Spell Checking or Chinese Spelling Correction (CSC) in writing assistants has significantly enhanced users' text quality. Multimodal CSC expands this task into the multimodal domain and introduces a new research challenge: understanding textual information at the image level. The traditional two-stage strategy, which directly maps images to text before performing checking and correction, often faces issues such as the many-to-one mapping problem of fake characters and misrecognizing fake characters as correct ones. To address these issues, we propose a unified one-stage framework based on the emerging Multimodal Large Language Models (MLLMs) to achieve a discrete semantic understanding of text directly at the image level, thus alleviating the image-to-text mapping problem. Additionally, we introduce an adaptation strategy for MLLM in the multimodal CSC task, enhancing its few-shot learning capability through in-context learning with prompt design. We evaluate different MLLM base models and verify the effectiveness of this one-stage framework, demonstrating performance that matches or even surpasses fine-tuned baseline models without fine-tuning. Furthermore, we conduct a series of analyses that provide insights into visual perception and text correction.

关键词： Multimodal Chinese Spell Checking Multimodal Large Language Models

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for QA Dialogue Dataset Construction and Analysis in Public Services 13th

Leveraging Large Language Models for QA Dialogue Dataset Con...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Wu, Chaomin Wu, Di Pan, Yushan Wang, Hao Xidian Univ Xian 710126 Peoples R China Norwegian Univ Sci & Technol N-6009 Alesund Norway Xian Jiaotong Liverpool Univ Suzhou 215123 Peoples R China

ISBN: (纸本)9789819794300;9789819794317

This paper identifies the limitations of current AI datasets within the public service sector, specifically concerning the human-robot interaction (HRI) context. Existing datasets often lack the necessary interactive features for effective and efficient interactions, hindering the development of customized and emotionally responsive systems. As public service demands become more diverse and complex in HRI, traditional datasets fail to support high-quality interactions, necessitating significant improvements. To address this issue, we introduce a QA dialogue dataset specifically tailored for public service applications, comprising 1208 pairs generated by large language model. This dataset integrates textual and emotional data, providing detailed annotations for interaction quality and emotional accuracy. Our method includes four stages: data generation, annotation, emotion analysis, and performance evaluation. During the data generation stage, GPT-4 is employed to create a diverse set of dialogues. In the annotation stage, these dialogues are meticulously labeled for quality and emotional content. The emotion analysis stage utilizes various recognition algorithms to process the data. Finally, the performance evaluation stage involves experiments to validate the dataset's effectiveness. Comparative experiments demonstrate the dataset's efficacy in enhancing the adaptability and performance of public service robots, underscoring its potential for training AI models to effectively handle real-world dialogues.

关键词： Human-Robot Interaction Public Service Emotion Analysis QA Dialogue Datasets

来源：评论

学校读者我要写书评

暂无评论

MPPQA: Structure-Aware Extractive Multi-span Question Answering for Procedural Documents 13th

MPPQA: Structure-Aware Extractive Multi-span Question Answer...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Zhou, Bihan Ren, Haopeng Cai, Yi Lian, Zetao Zhu, Pinli Zeng, Yushi South China Univ Technol Sch Software Engn Guangzhou Peoples R China South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Procedural documents, which provide procedural knowledge with step-by-step instructions to help achieve specific goals, have shown growing popularity in both industry workflows and daily routines. Particularly, answering prerequisite associated questions facilitates thorough preparation for procedures and supports the execution of the subsequent operations. However, most prevailing researches in procedural knowledge primarily concentrate on the task of entity state tracking or "What if" reasoning, typically formulated as single-span extraction or multiple-choice question answering. Due to the limitation of single-span extraction format or disregard for leveraging the structural procedural knowledge within procedural document, existing question answering methods still struggle to accurately answer multi-span prerequisite associated questions. In this paper, we explore the problem of prerequisite associated question answering task to extract multi-span style answers from the procedural documents, and propose a key procedure concentrated question answering model SAPE integrated with structure-aware module. Additionally, a new dataset MPPQA is built and extensive experiments are conducted to evaluate the effectiveness of our proposed model.

关键词： Structural procedural knowledge Prerequisite associated question Multi-span question answering

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 << < 9 10 11 12 13 14 15 16 17 18 > >>

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：