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

116 篇 会议
1 篇 期刊文献

馆藏范围

117 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

115 篇 工学
- 109 篇 计算机科学与技术...
- 45 篇 软件工程
- 12 篇 信息与通信工程
- 6 篇 生物工程
- 2 篇 机械工程
- 2 篇 化学工程与技术
- 2 篇 交通运输工程
- 1 篇 电气工程
- 1 篇 电子科学与技术（可...
- 1 篇 控制科学与工程
- 1 篇 生物医学工程（可授...
- 1 篇 安全科学与工程
17 篇 理学
- 6 篇 数学
- 6 篇 物理学
- 6 篇 生物学
- 3 篇 统计学（可授理学、...
- 2 篇 化学
- 1 篇 系统科学
13 篇 管理学
- 13 篇 图书情报与档案管...
- 1 篇 管理科学与工程(可...
2 篇 医学
- 2 篇 基础医学(可授医学...
- 2 篇 临床医学
- 1 篇 公共卫生与预防医...
- 1 篇 药学(可授医学、理...
1 篇 法学
- 1 篇 社会学
1 篇 文学
- 1 篇 外国语言文学

主题

7 篇 sentiment analys...
7 篇 neural machine t...
6 篇 long short-term ...
6 篇 semantics
5 篇 chinese word seg...
3 篇 deep learning
3 篇 large dataset
3 篇 abstractive summ...
3 篇 question answeri...
3 篇 chinese zero pro...
3 篇 natural language...
2 篇 short text
2 篇 knowledge base
2 篇 transformer
2 篇 ensemble learnin...
2 篇 news headline
2 篇 lstm
2 篇 deep neural netw...
2 篇 learning algorit...
2 篇 speech recogniti...

机构

4 篇 soochow univ sch...
4 篇 soochow univ sch...
4 篇 microsoft res as...
4 篇 school of comput...
3 篇 cas ctr excellen...
3 篇 chinese acad sci...
3 篇 univ chinese aca...
3 篇 harbin inst tech...
3 篇 beijing univ pos...
3 篇 univ chinese aca...
3 篇 university of ch...
3 篇 peking univ moe ...
2 篇 institute for in...
2 篇 natural language...
2 篇 chinese acad sci...
2 篇 peking univ inst...
2 篇 fudan univ sch c...
2 篇 laboratory of la...
2 篇 baidu inc.
2 篇 northeastern uni...

作者

8 篇 zhou guodong
4 篇 li shoushan
3 篇 kong fang
3 篇 zhang jiajun
3 篇 zong chengqing
3 篇 zan hongying
3 篇 jiang shengyi
3 篇 wang houfeng
2 篇 shi yabing
2 篇 liu hang
2 篇 yan qian
2 篇 dai qiong
2 篇 he wei
2 篇 li sujian
2 篇 chen yufeng
2 篇 zhang kunli
2 篇 yu kai
2 篇 li rui
2 篇 gao guanglai
2 篇 zhang dongdong

语言

117 篇 英文

检索条件"任意字段=6th CCF International Conference on Natural Language Processing and Chinese Computing, NLPCC 2017"

共 117 条记录，以下是81-90 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：

Abstractive Summarization Improved by WordNet-Based Extractive Sentences 7th

Abstractive Summarization Improved by WordNet-Based Extracti...

引用

7th ccf international conference on natural language processing and chinese computing, nlpcc

作者： Xie, Niantao Li, Sujian Ren, Huiling Zhai, Qibin Peking Univ MOE Key Lab Computat Linguist Beijing Peoples R China Chinese Acad Med Sci Inst Med Informat Beijing Peoples R China Peking Univ Sch Software & Microelectron MOE Informat Secur Lab Beijing Peoples R China

ISBN: (纸本)9783319994956;9783319994949

Recently, the seq2seq abstractive summarization models have achieved good results on the CNN/Daily Mail dataset. Still, how to improve abstractive methods with extractive methods is a good research direction, since extractive methods have their potentials of exploiting various efficient features for extracting important sentences in one text. In this paper, in order to improve the semantic relevance of abstractive summaries, we adopt the WordNet based sentence ranking algorithm to extract the sentences which are most semantically to one text. then, we design a dual attentional seq2seq framework to generate summaries with consideration of the extracted information. At the same time, we combine pointer-generator and coverage mechanisms to solve the problems of out-of-vocabulary (OOV) words and duplicate words which exist in the abstractive models. Experiments on the CNN/Daily Mail dataset show that our models achieve competitive performance with the state-of-the-art ROUGE scores. Human evaluations also show that the summaries generated by our models have high semantic relevance to the original text.

关键词： Abstractive summarization Seq2seq model Dual attention Extractive summarization WordNet

来源：评论

学校读者我要写书评

暂无评论

Joint Modeling of Recognizing Macro chinese Discourse Nuclearity and Relation Based on Structure and Topic Gated Semantic Network 8th

Joint Modeling of Recognizing Macro Chinese Discourse Nuclea...

引用

8th ccf international conference on natural language processing and chinese computing, nlpcc 2019

作者： Jiang, Feng Li, Peifeng Zhu, Qiaoming School of Computer Science and Technology Soochow University Suzhou China

ISBN: (纸本)9783030322359

Nowadays, in the natural language processing field, with the object of research gradually shifting from the word to sentence, paragraph and higher semantic units, discourse analysis is one crucial step toward a better understanding of how these articles are structured. Compared with micro-level, this has rarely been investigated in macro chinese discourse analysis and faces tremendous challenges. First, it is harder to grasp the topic and recognize the relationship between macro discourse units due to their longer length and looser relation between them. Second, how to mine the relationship between nuclearity and relation recognition effectively is another challenge. To address these challenges, we propose a joint model of recognizing macro chinese discourse nuclearity and relation based on Structure and Topic Gated Semantic Network (STGSN). It makes the semantic representation of a discourse unit can change with its position and the topic by Gated Linear Unit (GLU). Moreover, we analyze the results of our models in nuclearity and relation recognition and explore the potential relationship between them. Conducted experiments show the effectiveness of the proposed approach. © 2019, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Constructing the Image Graph of Tang Poetry 8th

Constructing the Image Graph of Tang Poetry

引用

8th ccf international conference on natural language processing and chinese computing, nlpcc 2019

作者： Wang, Bihua Hu, Renfen Yang, Lijiao Institute of Chinese Information Processing Beijing Normal University Beijing China Ultra Power-BNU Joint Laboratory for Artificial Intelligence Beijing China

ISBN: (纸本)9783030322359

Images are the soul of poetry. the usage of images enables poetry to express its deepest emotions in very concise expression. While the structured language of poetry bring convenience to computer processing, the accumulation of a large number of images also brings difficulty to deep semantic understanding. Starting from the definition of object imagery, this paper selects 304 Tang poems as experimental samples, extracts the object images from poems. then it calculates the emotional tendency of object images according to the emotion system. Finally, it calculates the similarity between images to achieve the relevancy between the images and establishes the map of image relationship. this paper presents the relationship between images using visualization methods, which would help poetry learners understand the images intuitively, and provide reference for correlation study of Tang poetry. © 2019, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Multi-pattern Matching Algorithm for chinese-Hmong Mixed Strings 8th

A Multi-pattern Matching Algorithm for Chinese-Hmong Mixed S...

引用

8th ccf international conference on natural language processing and chinese computing, nlpcc 2019

作者： He, Shun-Ping Mo, Li-Ping Kang, Di-Wen College of Information Science & Engineering Jishou University JishouHunan416000 China

ISBN: (纸本)9783030322359

To solve the problem of rapid retrieval of chinese-Hmong mixed text, a multi-pattern matching algorithm in double-bytes unit combined with the idea of AC algorithm and the mismatch processing strategy of Horspool algorithm is proposed for the chinese-Hmong mixed strings. In this algorithm, a deterministic finite automaton is constructed based on the pattern-set according to the idea of AC algorithm, and the moving distance of the pattern is calculated by the bad-character rule of the Horspool algorithm, and the text is only traversed once to complete the quick search task of all patterns by using the finite automata. the experimental results show that the proposed algorithm has a good performance in multi-pattern matching for chinese-Hmong mixed texts in different scale, even for the mixed texts containing more than 100,000 characters, the matching efficiency is also significantly higher than the AC algorithm. © 2019, Springer Nature Switzerland AG.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Aggressive language Detection with Joint Text Normalization via Adversarial Multi-task Learning 9th

Aggressive Language Detection with Joint Text Normalization ...

引用

9th ccf international conference on natural language processing and chinese computing, nlpcc 2020

作者： Wu, Shengqiong Fei, Hao Ji, Donghong Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China

ISBN: (纸本)9783030604493

Aggressive language detection (ALD), detecting the abusive and offensive language in texts, is one of the crucial applications in NLP community. Most existing works treat ALD as regular classification with neural models, while ignoring the inherent conflicts of social media text that they are quite unnormalized and irregular. In this work, we target improving the ALD by jointly performing text normalization (TN), via an adversarial multi-task learning framework. the private encoders for ALD and TN focus on the task-specific features retrieving, respectively, and the shared encoder learns the underlying common features over two tasks. During adversarial training, a task discriminator distinguishes the separate learning of ALD or TN. Experimental results on four ALD datasets show that our model outperforms all baselines under differing settings by large margins, demonstrating the necessity of joint learning the TN with ALD. Further analysis is conducted for a better understanding of our method. © 2020, Springer Nature Switzerland AG.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Event Factuality Detection in Discourse 8th

Event Factuality Detection in Discourse

引用

8th ccf international conference on natural language processing and chinese computing, nlpcc 2019

作者： Huang, Rongtao Zou, Bowei Wang, Hongling Li, Peifeng Zhou, Guodong Natural Language Processing Lab Soochow University Suzhou China Institute for Infocomm Research Singapore Singapore

ISBN: (纸本)9783030322359

Event factuality indicates whether an event occurs or the degree of certainty described by authors in context. Correctly identifying event factuality in texts can contribute to a deep understanding of natural language. In addition, event factuality detection is of great significance to many natural language processing applications, such as opinion detection, emotional reasoning, and public opinion analysis. Existing studies mainly focus on identifying event factuality by the features in the current sentence (e.g. negation or modality). However, there might be many different descriptions of factuality in a document, corresponding to the same event. It leads to conflict when identifying event factuality only on sentence level. To address such issues, we come up with a document-level approach on event factuality detection, which employs Bi-directional Long Short-Term Memory (BiLSTM) neural networks to learn contextual information of the event in sentences. Moreover, we utilize a double-layer attention mechanism to capture the latent correlation features among event sequences in the discourse, and identify event factuality according to the whole document. the experimental results on both English and chinese event factuality detection datasets demonstrate the effectiveness of our approach. the performances of the proposed system achieved 86.67% and 86.97% of F1 scores, yielding improvements of 3.24% and 4.78% over the state-of-the-art on English and chinese datasets, respectively. © 2019, Springer Nature Switzerland AG.

关键词： Social aspects

来源：评论

学校读者我要写书评

暂无评论

Question Generation Based Product Information 8th

Question Generation Based Product Information

引用

8th ccf international conference on natural language processing and chinese computing, nlpcc 2019

作者： Xiao, Kang Zhou, Xiabing Wang, Zhongqing Duan, Xiangyu Zhang, Min Natural Language Processing Lab School of Computer Science and Technology Soochow University Suzhou China

ISBN: (纸本)9783030322359

With the continuous development of the Internet, the field of e-commerce generates many comments on products. It is of great significance for both merchants and customers to generate product-related questions by utilizing a large amount of review information of products. In order to get rid of the traditional constraints of generating models based on artificial rules and make the question generation more accurate, this paper proposes a question generation model based on product information. Compared with the existing approaches, this model can generate questions more relevant to the products, and more fluent. In particular, the model can not only avoid the problem that the vocabulary exceeds the dictionary, but also extract the vocabulary needed for question generation from the original text and the dictionary. the experimental results show that in the task of generating short text based on comments, compared with the existing neural network model, the effectiveness has been greatly improved. © 2019, Springer Nature Switzerland AG.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Multi-layer Joint Learning of chinese Nested Named Entity Recognition Based on Self-attention Mechanism 9th

Multi-layer Joint Learning of Chinese Nested Named Entity Re...

引用

9th ccf international conference on natural language processing and chinese computing, nlpcc 2020

作者： Li, Haoru Xu, Haoliang Qian, Longhua Zhou, Guodong School of Computer Science and Technology Soochow University Suzhou China

ISBN: (纸本)9783030604561

Nested named entity recognition attracts increasingly attentions due to their pervasiveness in general domain as well as in other specific domains. this paper proposes a multi-layer joint learning model for chinese named entities recognition based on self-attention aggregation mechanism where a series of multi-layered sequence labeling sub-models are joined to recognize named entities in a bottom-up fashion. In order to capture entity semantic information in a lower layer, hidden units in an entity are aggregated using self-attention mechanism and further fed into the higher layer. We conduct extensive experiments using various entity aggregation methods. the results on the chinese nested entity corpus transformed from the Peoples Daily show that our model performs best among other competitive methods, implying that self-attention mechanism can effectively aggregate important semantic information in an entity. © 2020, Springer Nature Switzerland AG.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

DuIE: A Large-Scale chinese Dataset for Information Extraction 8th

DuIE: A Large-Scale Chinese Dataset for Information Extracti...

引用

8th ccf international conference on natural language processing and chinese computing, nlpcc 2019

作者： Li, Shuangjie He, Wei Shi, Yabing Jiang, Wenbin Liang, Haijin Jiang, Ye Zhang, Yang Lyu, Yajuan Zhu, Yong Baidu Inc. Beijing100193 China

ISBN: (纸本)9783030322359

Information extraction is an important foundation for knowledge graph construction, as well as many natural language understanding applications. Similar to many other artificial intelligence tasks, high quality annotated datasets are essential to train a high-performance information extraction system. Existing datasets, however, are mostly built for English. To promote research in chinese information extraction and evaluate the performance of related systems, we build a large-scale high-quality dataset, named DuIE, and make it publicly available. We design an efficient coarse-to-fine procedure including candidate generation and crowdsourcing annotation, in order to achieve high data quality at a large data scale. DuIE contains 210,000 sentences and 450,000 instances covering 49 types of commonly used relations, reflecting the real-world scenario. We also hosted an open competition based on DuIE, which attracted 1,896 participants. the competition results demonstrated the potential of this dataset in promoting information extraction research. © 2019, Springer Nature Switzerland AG.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

A New Algorithm for Component Decomposition and Type Recognition of Tibetan Syllable 8th

A New Algorithm for Component Decomposition and Type Recogni...

引用

8th ccf international conference on natural language processing and chinese computing, nlpcc 2019

作者： Zhu, Jie Wang, Shugen Wu, Yanru Guan, Meijing Feng, Yang Department of Computer Science Tibetan University Lhasa China National-Local Joint Engineering Research Center for Tibetan Information Technology Lhasa China Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783030322359

In this paper, aiming at the problems including but not limited to Tibetan sorting, Tibetan syllable component attribute statistics, Tibetan speech recognition in the application field of component recognition of Tibetan syllable, we propose a new algorithm for component decomposition and type recognition of Tibetan syllable based on TSRM (Tibetan Syllable Rule Model). Experimental results on mixed-arranged complex Tibetan texts show that our newly proposed algorithm can achieve a score around 90% both accuracy rate and recall rate for Component Decomposition and Type Recognition of Tibetan Syllable. © 2019, Springer Nature Switzerland AG.

关键词： Speech recognition

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12页 << < 3 4 5 6 7 8 9 10 11 12 > >>

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：