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

1,280 篇 会议
27 册 图书
10 篇 期刊文献

馆藏范围

1,317 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,059 篇 工学
- 1,001 篇 计算机科学与技术...
- 502 篇 软件工程
- 139 篇 信息与通信工程
- 68 篇 电气工程
- 68 篇 生物工程
- 49 篇 控制科学与工程
- 44 篇 化学工程与技术
- 31 篇 生物医学工程（可授...
- 20 篇 机械工程
- 18 篇 仪器科学与技术
- 17 篇 电子科学与技术（可...
- 5 篇 动力工程及工程热...
259 篇 理学
- 89 篇 数学
- 72 篇 生物学
- 51 篇 物理学
- 48 篇 系统科学
- 44 篇 化学
- 32 篇 统计学（可授理学、...
181 篇 管理学
- 146 篇 图书情报与档案管...
- 47 篇 管理科学与工程(可...
- 18 篇 工商管理
172 篇 文学
- 162 篇 外国语言文学
- 8 篇 中国语言文学
35 篇 医学
- 31 篇 临床医学
- 24 篇 基础医学(可授医学...
- 15 篇 药学(可授医学、理...
- 9 篇 公共卫生与预防医...
22 篇 法学
- 19 篇 社会学
13 篇 教育学
- 10 篇 教育学
6 篇 农学
- 6 篇 作物学
4 篇 经济学
3 篇 艺术学
1 篇 哲学

主题

120 篇 natural language...
89 篇 natural language...
78 篇 semantics
57 篇 sentiment analys...
42 篇 deep learning
38 篇 large language m...
29 篇 computational mo...
26 篇 artificial intel...
24 篇 machine learning
23 篇 training
21 篇 large language m...
20 篇 feature extracti...
20 篇 neural machine t...
19 篇 task analysis
18 篇 machine translat...
18 篇 knowledge graph
18 篇 information retr...
17 篇 long short-term ...
17 篇 data mining
16 篇 syntactics

机构

40 篇 university of ch...
31 篇 univ chinese aca...
22 篇 institute of com...
15 篇 soochow univ sch...
14 篇 key laboratory o...
12 篇 laboratory of la...
11 篇 chinese acad sci...
11 篇 univ chinese aca...
10 篇 chinese univ hon...
10 篇 institute of inf...
9 篇 shenyang institu...
9 篇 chinese acad sci...
8 篇 microsoft res as...
8 篇 guangdong univ f...
8 篇 peking univ moe ...
7 篇 research center ...
7 篇 chinese acad sci...
6 篇 collaborat innov...
6 篇 univ sci & techn...
6 篇 peking univ inst...

作者

17 篇 zhou guodong
16 篇 liu qun
12 篇 zhang jiajun
12 篇 zong chengqing
10 篇 liu ting
9 篇 kong fang
9 篇 xu jinan
9 篇 wang zhongqing
9 篇 zan hongying
9 篇 yu dong
9 篇 meng helen
8 篇 chen yufeng
8 篇 liu yang
8 篇 yang liu
8 篇 huang xuanjing
8 篇 li shoushan
8 篇 liu wuying
7 篇 cheng xueqi
7 篇 xu bo
7 篇 che wanxiang

语言

1,297 篇 英文
17 篇 其他
5 篇 中文

检索条件"任意字段=13th International Conference on Natural Language Processing and Chinese Computing"

共 1317 条记录，以下是51-60 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：

Essay Coherence Evaluation and Feedback Enhanced by Semi-supervised Learning and Auxiliary Information 13th

Essay Coherence Evaluation and Feedback Enhanced by Semi-sup...

引用

13th international conference on natural language processing and chinese computing

作者： Li, Chenyang Zhang, Long Guo, Hui Zheng, Qiusheng Cent China Normal Univ Fac Artificial Intelligence Educ Wuhan Peoples R China Zhongyuan Univ Technol Sch Cyberspace Secur Zhengzhou Peoples R China

ISBN: (纸本)9789819794423;9789819794430

According to the grading standards for middle school examinations, thought content and structural coherence are critical indicators of essay quality. Evaluating an essay's coherence requires not only analyzing the semantic connections between sentences but also understanding the logical relationships between sentences and the overall structural layout of the essay. this understanding is essential for grasping the logical framework of long texts and generating complex documents. this paper presents our approach used in the NLPCC 2024 competition for evaluating essay sentence logic and generating feedback. For different tasks, we applied both traditional classification models and advanced large language models, leveraging pseudo-labels generated through semi-supervised learning and information provided by large models as auxiliary data, significantly enhancing overall model performance. Experimental results demonstrate that our method achieves state-of-the-art results.

关键词： Essay Quality Assessment Semi-Supervised Learning Large language Models Auxiliary Data

来源：评论

学校读者我要写书评

暂无评论

Classifiers Guided Controllable Text Generation for Discrete Diffusion language Models 13th

Classifiers Guided Controllable Text Generation for Discrete...

引用

13th international conference on natural language processing and chinese computing

作者： Jiang, Hang Cai, Guoyong Li, Sihui Guilin Univ Elect Technol Guilin Peoples R China

ISBN: (纸本)9789819794362;9789819794379

the classifier-guided method is a simple yet effective technique for controllable text generation. However, its application to the discrete diffusion model, a promising non-autoregressive language model, remains unexplored. In this paper, controllable generation is achieved through multiple iterations of conditional backward diffusion, each iteration comprising two key steps: conditional prediction and masking. the conditional prediction distribution is approximated by the product of classifier probabilities and language model probabilities. Two distinct algorithms, Largest-M and gradient search, are introduced to sample from this joint distribution. Largest-M operates within the discrete token sequence space, while gradient search functions within the continuous hidden state space. Both algorithms aim to identify texts that maximize the joint probability. Experiments across four fine-grained controllable tasks demonstrate the effectiveness of the proposed algorithms, achieving success rates up to 99% on certain tasks. Furthermore, the inherent multi-modality problem in discrete diffusion models is mitigated by framing multi-modality suppression as a controllable generation task. the experiment result indicates that integrating multi-modality classifiers effectively enhances the performance of discrete diffusion models.

关键词： classifiers guided generation controllable text generation discrete diffusion language model

来源：评论

学校读者我要写书评

暂无评论

Overview of the NLPCC 2024 Shared Task: chinese Essay Discourse Logic Evaluation and Integration 13th

Overview of the NLPCC 2024 Shared Task: Chinese Essay Discou...

引用

13th international conference on natural language processing and chinese computing

作者： Zhou, Yuhao Wu, Hongyi Shen, Xinshu Lan, Man Wu, Yuanbin Bai, Xiaopeng Mao, Shaoguang Ge, Tao Xia, Yan East China Normal Univ Sch Comp Sci & Technol Shanghai Peoples R China East China Normal Univ Shanghai Inst AI Educ Shanghai Peoples R China East China Normal Univ Dept Chinese Language & Literature Shanghai Peoples R China Microsoft Res Asia Beijing Peoples R China

ISBN: (纸本)9789819794423;9789819794430

this paper presents an overview of the second chinese Essay Discourse Logic Evaluation and Integration (CEDLEI) competition, which is organized as NLPCC 2024 Shared Task 4. As the second edition of the competition, this task expands and improves upon the success of the first edition. Based on the foundation of inter-sentence and inter-paragraph logical relation identification in the first edition, this year's competition introduces the addition of discourse coherence feedback generation. these improvements aim to reduce the burden of essay marking on teachers while providing students with more consistent and objective assessments. through these tracks, participants will explore and apply the latest natural language processing techniques to enhance the accuracy and efficiency of chinese composition assessment. Task information is available at https://***/cubenlp/NLPCC-2024-Shared-Task4.

关键词： Discourse Logic Relation Discourse Coherence Feedback Generation

来源：评论

学校读者我要写书评

暂无评论

Chain of Stance: Stance Detection with Large language Models 13th

Chain of Stance: Stance Detection with Large Language Models

引用

13th international conference on natural language processing and chinese computing

作者： Ma, Junxia Wang, Changjiang Xing, Hanwen Zhao, Dongming Zhang, Yazhou Zhengzhou Univ Light Ind Coll Software Engn Zhengzhou Peoples R China UCL London England China Mobile Commun Grp Tianjin Co Ltd Artificial Intelligence Lab Tianjin Peoples R China Tianjin Univ Tianjin Peoples R China

ISBN: (纸本)9789819794423;9789819794430

Stance detection is an active task in natural language processing (NLP) that aims to identify the author's stance towards a particular target within a text. Given the remarkable language understanding capabilities and encyclopedic prior knowledge of large language models (LLMs), how to explore the potential of LLMs in stance detection has received significant attention. Unlike existing LLM-based approaches that focus solely on fine-tuning with large-scale datasets, we propose a new prompting method, called Chain of Stance (CoS). In particular, it positions LLMs as expert stance detectors by decomposing the stance detection process into a series of intermediate, stance-related assertions that culminate in the final judgment. this approach leads to significant improvements in classification performance. We conducted extensive experiments using four SOTA LLMs on the SemEval 2016 dataset, covering the zero-shot and few-shot learning setups. the results indicate that the proposed method achieves state-of-the-art results with an F1 score of 79.84 in the few-shot setting.

关键词： stance detection CoS LLM

来源：评论

学校读者我要写书评

暂无评论

Span-Based chinese Few-Shot NER with Contrastive and Prompt Learning 13th

Span-Based Chinese Few-Shot NER with Contrastive and Prompt ...

引用

13th international conference on natural language processing and chinese computing

作者： Ye, Feiyang Lai, Peichao Yang, Sanhe Zhang, Zhengfeng Wang, Yilei Fuzhou Univ Coll Comp & Data Sci Fuzhou Peoples R China

ISBN: (纸本)9789819794331;9789819794348

For chinese Named Entity Recognition (NER) tasks, achieving better performance with fewer training samples remains a challenge. Previous works primarily focus on enhancing model performance in NER by incorporating additional knowledge to construct entity features. these approaches neglect the semantic information of entity labels and the information of entity boundaries. Moreover, conventional methods typically treat NER as a sequence labeling task, which makes them inadequate for addressing the issue of nested entities. We propose a new span-based approach by using contrastive learning and prompt learning to address these problems. By pulling similar entities closer together, pushing dissimilar entities further apart, and leveraging entity label information, we improve model performance in few-shot scenarios effectively. Experimental results demonstrate that our method achieves significant performance improvements on a sampled chinese nested medical dataset and several other flattened datasets, providing a new insight into addressing challenges in few-shot NER tasks.

关键词： Named Entity Recognition Contrastive Learning Few-shot Learning

来源：评论

学校读者我要写书评

暂无评论

Literature Hunter: Literature Reading Aided by Large language Models 13th

Literature Hunter: Literature Reading Aided by Large Languag...

引用

13th international conference on natural language processing and chinese computing

作者： Lai, Yahao Chen, Xiang Du, Yunchen Liu, Bo Zhao, Shaofeng Beijing Informat Sci & Technol Univ Beijing 100192 BJ Peoples R China Zhengzhou Univ Zhengzhou 450001 HN Peoples R China Henan Univ Econ & Law Zhengzhou 450001 HN Peoples R China

ISBN: (纸本)9789819794423;9789819794430

Literature reading is an indispensable process for understanding a research field, but it often involves a significant investment of time. To enable researchers to quickly understand the advancements in a particular research field, we leverage the writing capabilities of large language models (LLMs) and propose an end-to-end survey paper writing system that can complete a paper using only a few keywords. Specifically, we closely mimic the human writing process by (1) generating an outline from multiple perspectives, (2) selecting the best one from the generated candidate content, and (3) refining the selected content. Furthermore, to evaluate the generated content, we curate SurGen, a dataset of recent high-quality survey articles, and conduct tests. Experimental results demonstrate that our method significantly improves both automated metrics and human evaluations compared to direct generation. To the best of our knowledge, we are the first to attempt generating survey papers using large language models and to release the corresponding dataset.

关键词： Large language models Literature generation Chain of thought

来源：评论

学校读者我要写书评

暂无评论

Sparse Mixture of Experts language Models Excel in Knowledge Distillation 13th

Sparse Mixture of Experts Language Models Excel in Knowledge...

引用

13th international conference on natural language processing and chinese computing

作者： Xu, Haiyang Liu, Haoxiang Gong, Wei Wang, Hai Deng, Xianjun Univ Sci & Technol China Hefei 230026 Anhui Peoples R China Alibaba Grp Hangzhou Peoples R China Huazhong Univ Sci & Technol Sch Cyber Sci & Engn Wuhan Peoples R China Southeast Univ Sch Comp Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9789819794362;9789819794379

Knowledge distillation is an effective method for reducing the computational overhead of large language models. However, recent optimization efforts in distilling large language models have primarily focused on loss functions and training methodologies, with limited attention given to structural improvements of student models. this is largely due to the challenges posed by cross-architecture distillation and the substantial computational resources required for modifying model structures. To address these issues, we introduce a novel method that integrates a sparse mixture of experts (MoE) architecture with low-rank adaptation (LoRA). this combination not only bolsters the capabilities of the student model but also facilitates knowledge distillation using MoE without the necessity of continued pretraining. Experimental results indicate that our approach enhances the model's capabilities compared to dense model distillation, achieving superior performance across a multitude of tasks. We will release our code at https://***/sprogxhy/***.

关键词： Mixture of experts Knowledge distillation language models

来源：评论

学校读者我要写书评

暂无评论

Assessing Translation Quality of Hypotactic Structure for chinese-to-English Machine Translation 13th

Assessing Translation Quality of Hypotactic Structure for Ch...

引用

13th international conference on natural language processing and chinese computing

作者： Feng, Wenhe Chen, Xiao'en Li, Nan Guangdong Univ Foreign Studies Ctr Linguist & Appl Linguist Guangzhou Peoples R China Guangdong Univ Foreign Studies Lab Language Engn & Comp Guangzhou Peoples R China

ISBN: (纸本)9789819794362;9789819794379

Hypotactic structure translation, essentially a discourse-level question, is a big challenge in chinese-to-English (C-E) machine translation (MT). this paper explores the assessment of translation quality of hypotactic structure for C-E MT. We argue that translating a hypotactic structure in C-E translation is essentially transforming a chinese discoursal semantic hypotactic structure (DS-hypotactic structure) to an English syntactic hypotactic structure (S-hypotactic structure). We propose a scheme to identify the chinese DS-hypotactic structure and the corresponding English S-hypotactic structure, and formulate the assessment criteria. We then assess the translation quality of current MT systems. the results show that MT technology is still far from satisfactory in translating hypotactic structures. Finally, we discuss the criterion for identifying the chinese DS-hypotactic structure and reasons and solutions of this MT problem.

关键词： Translation Assessment Discourse Translation Hypotactic Structure Machine Translation

来源：评论

学校读者我要写书评

暂无评论

TiLTS:Tibetan Long Text Summarization Dataset 13th

TiLTS:Tibetan Long Text Summarization Dataset

引用

13th international conference on natural language processing and chinese computing

作者： Hao, Yanrong Chen, Bo Zhou, Xiaobing Minzu Univ China Sch Informat Engn Beijing Peoples R China Natl Language Resources Monitoring & Res Ctr Mino Beijing Peoples R China

ISBN: (纸本)9789819794393;9789819794409

High-quality datasets are crucial for advancing research in automatic text summarization. At present, summarization models for resource-rich languages like chinese and English have made significant progress. However, for low-resource languages such as Tibetan, the lack of large-scale publicly available summarization datasets means that related research is still in its early stages. To address this gap, this paper constructs an open Tibetan summarization dataset, TiLTS. By collecting extensive texts from Tibetan news websites and leveraging resources from other languages, it obtains 36,507 (document, summary) pairs. Compared to the only publicly available Tibetan summarization dataset, TiSUM, TiLTS has clear advantages in both data size and challenge. this paper also conducts experiments and analyses using several summarization algorithms on this dataset.

关键词： Text summarization Dataset Tibetan Low-resource

来源：评论

学校读者我要写书评

暂无评论

Local or Global Optimization for Dialogue Discourse Parsing 13th

Local or Global Optimization for Dialogue Discourse Parsing

引用

13th international conference on natural language processing and chinese computing

作者： Wang, Chengrui Ji, Shaoming Kong, Fang Soochow Univ Lab Nat Language Proc Suzhou Peoples R China Soochow Univ Sch Comp Sci & Technol Suzhou Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Dialogue Discourse Parsing aims to identify the discourse links and relations between utterances, which has attracted more interest in recent years. Previous studies either adopt local optimization to independently select one parent for each utterance or use global optimization to directly get the tree representing the dialogue structure. However, the influence of these two optimization methods remains less explored. In this paper, we aim to systematically inspect their performance. Specifically, for local optimization, we use local loss during the training stage and a greedy strategy during the inference stage. For global optimization, We implement optimization of unlabeled and labeled trees by structured losses including Max-Margin and TreeCRF, and exploit Chu-Liu-Edmonds algorithm during the inference stage. Experiments shows that the performance of these two optimization methods is closely related to the characteristics of the dataset, and global optimization can reduce the burden of identifying long-range dependency relations.

关键词： Dialogue discourse parsing Local optimization Global optimization

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132页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：