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201-210 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：

Comparison of Well and Lower-Resourced Self-training in ASR 26th

Comparison of Well and Lower-Resourced Self-training in ASR

引用

26th International Conference on Speech and Computer

作者： Luo, Yue Mihajlik, Peter Budapest Univ Technol & Econ Departure Telecommun & Artificial Intelligence Budapest Hungary SpeechTex Ltd Budapest Hungary HUN REN Hungarian Res Ctr Linguist Budapest Hungary

ISBN: (纸本)9783031779602;9783031779619

In this paper, we present a case study of self-training for end-to-end Hungarian and Mandarin speech recognition. We demonstrate that self-training methods can significantly improve the accuracy of the baseline model for both languages. We trained a supervised baseline model which achieved a 20.13% WER on the BEA-Base eval-spont set. The self-trained Hungarian model, combining pseudo-labels generated by the baseline seed model with labeled data, achieved a WER of 15.93% on the BEA-Base eval-spont set, representing a 20.84% relative reduction compared to the baseline, and reduced WER by relative 15.28% on the independent Common Voice test set. The Mandarin model, which relied solely on pseudo-labels from the Whisper large-V2 model and used no labeled data, reduced CER by 45.31% on the AISHELL-2018A-EVAL test set, improving from 13.00% to 7.11%, and by relative 32.42% on the external Common Voice test set. We find that for spontaneous, low-resource Hungarian ASR tasks, pseudo-labels from domain-specific models are more effective than those from large general models like Whisper large-V2.

关键词： Automatic speech recognition Self-training Semi-supervised training Hungarian Mandarin

来源：评论

学校读者我要写书评

暂无评论

CouBRE: Counterfactual NLI For Low-Resource Biomedical Relation Extraction 13th

CouBRE: Counterfactual NLI For Low-Resource Biomedical Relat...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Zhong, Jin Liu, Yongbin Ouyang, Chunping Ren, Lin Zhu, Chi He, Yidong Univ South China Hengyang Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Biomedical relation extraction is a core problem in biomedical natural language processing, whose goal is to classify the relations between entity mentions within a classified given text, being modeled as a classification method. There has been some recent work on converting biomedical RE to other auxiliary tasks to deal with it. However, they have all neglected the fact that this form of RE is subject to the inherent bias of the auxiliary task, resulting in the inability to make truly reasonable predictions. In this paper, we propose the CouBRE method, which excludes the direct influence of premise-only and hypothesis-only branches in the NLI task when converting biomedical RE to NLI task from a causal perspective on the RE results, allowing the NLI model to make valid predictions based on the combined information of premise and hypothesis rather than based on shortcut paths. Also by removing sample selection bias and label bias in the dataset, CouBRE can make unbiased prediction results more clearly. Comprehensive experiments demonstrate the effectiveness of our approach in low-resource scenarios, outperforming previous state-of-the-art models and remaining competitive even in full-shot scenarios.

关键词： Biomedical Relation Extraction Natural Language Inference Counterfactual Inference Debias

来源：评论

学校读者我要写书评

暂无评论

ESC Corpus of Spoken Russian: Everyday Student Conversations Captured Through Continuous Speech Recording in Natural Communicative Environments 26th

ESC Corpus of Spoken Russian: Everyday Student Conversations...

引用

26th International Conference on Speech and Computer

作者： Sherstinova, Tatiana Y. Petrova, Irina HSE Univ St Petersburg Russia

ISBN: (纸本)9783031779602;9783031779619

This article describes the methodology for creating a new resource of everyday Russian speech, based on audio recordings made by student volunteers over the course of an entire day in natural communication settings (at home, in the university, at the cafe, in the fitness club, etc.). The precursor to this corpus is the well-knownORDcorpus, or the "One Day of Speech" corpus, for which recordings were made from 2007 to 2016. Since the ORD recordings were made, certain changes have occurred in Russian spoken language, particularly noticeable in the speech of young people at the lexical level. The creation of the newspeech resource aims to capture this linguistic snapshot to identify new colloquial vocabulary, as well as new meanings and connotations of known language units. The new recordings of everyday spoken language will supplement the empirical material of the ORD corpus and provide a foundation for various scientific, theoretical, and practical endeavors. The article details the methodology for creating the Everyday Student Conversations (ESC) corpus, highlights its differences from the ORD corpus, and provides current ESC corpus statistics.

关键词： Corpus Linguistics Everyday Spoken Russian Oral Discourse Speech Corpus Student Speech Field Linguistics Day-long Recording

来源：评论

学校读者我要写书评

暂无评论

Enhancing Emotional Support Conversation with Cognitive Chain-of-Thought Reasoning 13th

Enhancing Emotional Support Conversation with Cognitive Chai...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Cao, Yaru Chen, Zhuang Bi, Guanqun Feng, Yulin Chen, Min Wan, Fucheng Huang, Minlie Yu, Hongzhi Northwest Minzu Univ Dept Chinese Language & Literature Lanzhou 730030 Peoples R China Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Northwest Minzu Univ Key Lab Linguist & Cultural Comp Minist Educ Lanzhou 730030 Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Emotional support conversation can reduce mental stress and provide social benefits. However, the help seeker's mental state often lies beneath the surface utterance in conversation, making it difficult to understand the seeker's deep status and provide effective emotional support through mere dialogue modeling. To address this challenge, we propose CogChain, a cognitive chain-of-thought (CoT) reasoning framework that mimics a human supporter's cognitive process for emotional support conversation. Specifically, CogChain employs a chained structure to analyze the seeker's issues, infer internal thoughts, determine behavioral intentions, and select appropriate strategies to achieve support goals. We further design an in-context learning pipeline using large language models to efficiently generate CogChain for any given dialogue content. To validate the effectiveness of CogChain, we incorporate it in the frequently used ESConv dataset and accordingly train enhanced machine supporters with CoT reasoning ability. Extensive automatic and human evaluations show that, CogChain not only improves the machine supporter's performance for in-domain seen scenarios but also enhances its generalizability to out-of-domain unseen scenarios, demonstrating the importance of cognitive reasoning for emotional support conversation (Our resources are available at https://***/YaruCao-AI/CogChain).

关键词： Emotional Support Conversation Chain-of-Thought Reasoning Large Language Models

来源：评论

学校读者我要写书评

暂无评论

Human and Machine Keyphrase Perception in Russian Text and Speech 26th

Human and Machine Keyphrase Perception in Russian Text and S...

引用

26th International Conference on Speech and Computer

作者： Guseva, Dania Mitrofanova, Olga Dolgushin, Mikhail St Petersburg State Univ Univ Skaya Embankment 7-9 St Petersburg 199034 Russia Russian Acad Sci SPC RAS St Petersburg Fed Res Ctr 14th Line39 St Petersburg 199178 Russia

ISBN: (纸本)9783031779602;9783031779619

The article examines the perception and extraction of keyphrases in both written and spoken text. Experiments were performed on the dataset including transcripts and audio recordings of lectures by Russian-speaking participants of the project "Postnauka". The results showthat automated methods for keyphrase extraction have limited accuracy, with statistical algorithms performing the worst and generative AI models, such as ChatGPT, showing a closer resemblance to human perception. Additionally, while there is some overlap between keyphrases extracted from written and oral texts, spoken text presents greater variability. Experiments using synthesized speech indicate that listeners rely heavily on content, rather than acoustic cues, when understanding spoken text. Acoustic analysis reveals that keyphrases are distinguished by longer duration, wider pitch range, and higher energy, aligning with previous findings in other languages.

关键词： Keyphrase Extraction Perception Russian Language Expert Annotation Acoustic Analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cross-Lingual Topic-Essay Generation with Knowledge and Topic Consistency Constraints 13th

Enhancing Cross-Lingual Topic-Essay Generation with Knowledg...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Gu, Huailing Huang, Yuxin Yu, Zhengtao Mao, Cunli Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming 650504 Yunnan Peoples R China Kunming Univ Sci & Technol Yunnan Key Lab Artificial Intelligence Kunming 650504 Yunnan Peoples R China

ISBN: (纸本)9789819794393;9789819794409

The cross-lingual topic-essay generation task (CTEG) aims to generate sentence-level text in a target language based on input topic words from a source language. Recently, research on the generation of essays from topic words has primarily focused on monolingual settings. Extending this to cross-language scenarios requires overcoming challenges related to cross-language alignment and mitigating topic drift in the generated text. To address these challenges, we propose a novel cross-lingual topic-essay generation approach based on knowledge and topic consistency constraints. This approach extracts semantic alignment knowledge from a source language essay to a target language essay using a translation teacher model, which builds cross-lingual semantic alignment and guides the generation in the student model. Additionally, a cosine similarity-based topic consistency loss enhances the generated essays' topic consistency relative to the input topic words. To validate the effectiveness of the proposed model, we constructed a dataset of 160,000 Chinese topic-Vietnamese essay pairs and a dataset of 350,000 Chinese topic-English essay pairs. Experimental results show that our model outperforms various baseline models in terms of various evaluation metrics on both the Chinese-Vietnamese and Chinese-English datasets.

关键词： Cross-lingual topic-essay generation Knowledge constraints Topic consistency constraints

来源：评论

学校读者我要写书评

暂无评论

AutoMode-ASR: Learning to Select ASR Systems for Better Quality and Cost 26th

AutoMode-ASR: Learning to Select ASR Systems for Better Qual...

引用

26th International Conference on Speech and Computer

作者： Gunduz, Ahmet Kim, Yunsu Yuksel, Kamer Ali Al-Badrashiny, Mohamed Ferreira, Thiago Castro Sawaf, Hassan AiXplain Inc San Jose CA 95128 USA

ISBN: (纸本)9783031779602;9783031779619

We present AutoMode-ASR, a novel framework that effectively integrates multiple ASR systems to enhance the overall transcription quality while optimizing cost. The idea is to train a decision model to select the optimal ASR system for each segment based solely on the audio input before running the systems. We achieve this by ensembling binary classifiers determining the preference between two systems. These classifiers are equipped with various features, such as audio embeddings, quality estimation, and signal properties. Additionally, we demonstrate how using a quality estimator can further improve performance with minimal cost increase. Experimental results show a relative reduction in WER of 16.2%, a cost saving of 65%, and a speed improvement of 75%, compared to using a single-best model for all segments. Our framework is compatible with commercial and open-source black-box ASR systems as it does not require changes in model codes.

关键词： Automatic speech recognition Quality estimation Cost optimization

来源：评论

学校读者我要写书评

暂无评论

EDNER: Edge Detection for Named Entity Recognition 13th

EDNER: Edge Detection for Named Entity Recognition

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Gao, Liangyu Yang, Zhihao Luo, Ling Liu, Wenfei Lin, Hongfei Wang, Jian Dalian Univ Technol Coll Comp Sci & Technol Dalian Peoples R China

ISBN: (纸本)9789819794331;9789819794348

The task of Named Entity Recognition (NER) is an important component of information extraction tasks. Currently, span-based approaches are receiving widespread research attention. Despite their success in many aspects, these approaches also suffer from insufficient utilization of non-entity information. In this work, we view the span-based NER task as an edge detection task and propose EDNER (Edge Detection for Named Entity Recognition). In this method, we define the edge representation of text and generate deep representations through a specially designed edge interaction layer, while auxiliary edge contrastive learning and global edge detection task allow the model to fully adapt to the task of edge detection. Our carefully designed convolutional layers and prediction layers extract entity spans by detecting entity edges. Experimental results show that our method outperforms existing state-of-the-art methods and achieves highest F1 scores on four benchmark NER datasets.

关键词： Named Entity Recognition Edge detection Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Identifying Speakers and Addressees of Quotations in Novels with Prompt Learning 13th

Identifying Speakers and Addressees of Quotations in Novels ...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Yan, Yuchen Zhao, Lianjie Zhu, Senbin Liu, Hongde Zhang, Zhihong Jia, Yuxiang Zhengzhou Univ Sch Comp & Artificial Intelligence Zhengzhou Peoples R China

ISBN: (纸本)9789819794393;9789819794409

Quotations in literary works, especially novels, are important to create characters, reflect character relationships, and drive plot development. Current research on quotation extraction in novels primarily focuses on quotation attribution, i.e., identifying the speaker of the quotation. However, the addressee of the quotation is also important to construct the relationship between the speaker and the addressee. To tackle the problem of dataset scarcity, we annotate the first Chinese quotation corpus with elements including speaker, addressee, speaking mode and linguistic cue. We propose prompt learning-based methods for speaker and addressee identification based on fine-tuned pre-trained models. Experiments on both Chinese and English datasets show the effectiveness of the proposed methods, which outperform methods based on zero-shot and few-shot large language models.

关键词： Quotations in Novels Speaker and Addressee Identification Corpus Prompt Learning

来源：评论

学校读者我要写书评

暂无评论

Learning to Generate Style-Specific Adapters for Stylized Dialogue Generation 13th

Learning to Generate Style-Specific Adapters for Stylized Di...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Li, Jinpeng Chen, Yuhang Wu, Pengfei Xia, Yingce Xie, Shufang Zhao, Dongyan Yan, Rui Peking Univ Wangxuan Inst Comp Technol Beijing Peoples R China Microsoft Res Beijing Peoples R China Natl Key Lab Gen Artificial Intelligence Beijing Peoples R China Renmin Univ China Gaoling Sch Artif Intelligence Beijing Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Stylized dialogue generation is capable of producing highly creative and engaging responses, making it an indispensable feature of intelligent dialogue systems. However, a major challenge to this task is the paucity of supervised data, resulting in suboptimal performance. Although some unsupervised methods have emerged, they tend to handle only a limited range of dialogue styles simultaneously. Retraining becomes necessary when new dialogue styles are introduced, leading to increased training overhead and model redundancy. Furthermore, the large language model shows exciting performance, it still falls short on some specific tasks. To address the data limitations and training overhead, we propose a Multi-Stylized Adapter Dialogue Generation (MultiSADG) model, which generates multiple stylized adapters by using representations from different stylized corpora. Specifically, we generate style-specific adapters for modeling both contexts and stylized responses. These style-specific adapters are generated by a hypernetwork trained on multiple stylized corpora. In addition, for unseen stylized texts, MultiSADG uses the stylized corpus to generate style-specific adapters through the hypernetwork to deal with the zero-shot scenario. MultiSADG is evaluated on five stylized dialogue data, and the experimental results show its satisfactory performance in both automatic and manual evaluation.

关键词： Stylized dialogue generation Adapter Hypernetwork

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 << < 17 18 19 20 21 22 23 24 25 26 > >>

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：