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

54 篇 会议
2 册 图书

馆藏范围

56 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

51 篇 工学
- 51 篇 计算机科学与技术...
- 25 篇 软件工程
- 7 篇 信息与通信工程
- 3 篇 电气工程
- 2 篇 生物工程
- 1 篇 机械工程
- 1 篇 控制科学与工程
- 1 篇 农业工程
- 1 篇 生物医学工程（可授...
13 篇 管理学
- 12 篇 图书情报与档案管...
- 1 篇 管理科学与工程(可...
12 篇 理学
- 9 篇 数学
- 5 篇 统计学（可授理学、...
- 3 篇 物理学
- 2 篇 生物学
3 篇 文学
- 3 篇 外国语言文学
1 篇 农学
- 1 篇 作物学
1 篇 医学
- 1 篇 基础医学(可授医学...
- 1 篇 临床医学
- 1 篇 公共卫生与预防医...

主题

8 篇 sentiment analys...
4 篇 semantics
4 篇 natural language...
2 篇 statistical mach...
2 篇 data mining
2 篇 computers
2 篇 emotion recognit...
2 篇 neural machine t...
1 篇 multi-label clas...
1 篇 knowledge based ...
1 篇 machine translat...
1 篇 deep learning
1 篇 regression analy...
1 篇 statistical test...
1 篇 computer aided l...
1 篇 linguistic diver...
1 篇 character repres...
1 篇 question generat...
1 篇 weighted alignme...
1 篇 long short-term ...

机构

4 篇 national laborat...
4 篇 fudan univ sch c...
3 篇 peking universit...
2 篇 soochow univ sch...
2 篇 natural language...
2 篇 school of comput...
1 篇 key laboratory o...
1 篇 school of comput...
1 篇 peking univ mini...
1 篇 soochow univ lab...
1 篇 collaborat innov...
1 篇 dept. of compute...
1 篇 key laboratory o...
1 篇 univ chinese aca...
1 篇 shanghai univ sh...
1 篇 peking univ sch ...
1 篇 department of co...
1 篇 department of co...
1 篇 ministry of educ...
1 篇 technology pekin...

作者

4 篇 qiu xipeng
3 篇 zhou guodong
3 篇 sui zhifang
3 篇 huang xuanjing
2 篇 kong fang
2 篇 liu qun
2 篇 qian peng
2 篇 xie jun
2 篇 xu ruifeng
2 篇 xu jinan
2 篇 zong chengqing
2 篇 shi zhan
2 篇 zhao jun
2 篇 zhang yujie
2 篇 zhou yu
2 篇 xiong deyi
2 篇 zhao dongyan
2 篇 hao hongwei
2 篇 sha lei
2 篇 chang baobao

语言

56 篇 英文

检索条件"任意字段=3rd CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2014"

共 56 条记录，以下是11-20 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：

Negation and speculation target identification 3

Negation and speculation target identification

引用

3rd ccf conference on natural language processing and chinese computing, nlpcc 2014

作者： Zou, Bowei Zhou, Guodong Zhu, Qiaoming Natural Language Processing Lab School of Computer Science and Technology Soochow University Suzhou215006 China

ISBN: (纸本)9783662459232

Negation and speculation are common in natural language text. Many applications, such as biomedical text mining and clinical information extraction, seek to distinguish positive/factual objects from negative/speculative ones (i.e., to determine what is negated or speculated) in biomedical texts. This paper proposes a novel task, called negation and speculation target identification, to identify the target of a negative or speculative expression. For this purpose, a new layer of the target information is incorporated over the BioScope corpus and a machine learning algorithm is proposed to automatically identify this new information. Evaluation justifies the effectiveness of our proposed approach on negation and speculation target identification in biomedical texts. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A novel rule refinement method for SMT through simulated post-editing 3

A novel rule refinement method for SMT through simulated pos...

引用

3rd ccf conference on natural language processing and chinese computing, nlpcc 2014

作者： Yang, Sitong Yu, Heng Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China CNGL School of Computing Dublin City University Ireland

ISBN: (纸本)9783662459232

Post-editing has been successfully applied to correct the output of MT systems to generate better translation, but as a downstream task its positive feedback to MT has not been well studied. In this paper, we present a novel rule refinement method which uses Simulated Post-Editing (SiPE) to capture the errors made by the MT systems and generates refined translation rules. Our method is system-independent and doesn’t entail any additional resources. Experimental results on largescale data show a significant improvement over both phrase-based and syntax-based baselines. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A fast and effective method for clustering large-scale chinese question dataset 3

A fast and effective method for clustering large-scale Chine...

引用

3rd ccf conference on natural language processing and chinese computing, nlpcc 2014

作者： Zhang, Xiaodong Wang, Houfeng Key Laboratory of Computational Linguistics Peking University Ministry of Education China

ISBN: (纸本)9783662459232

Question clustering plays an important role in QA systems. Due to data sparseness and lexical gap in questions, there is no sufficient information to guarantee good clustering results. Besides, previous works pay little attention to the complexity of algorithms, resulting in infeasibility on large-scale datasets. In this paper, we propose a novel similarity measure, which employs word relatedness as additional information to help calculating similarity between questions. Based on the similarity measure and k-means algorithm, semantic k-means algorithm and its extended version are proposed. Experimental results show that the proposed methods have comparable performance with state-of-the- art methods and cost less time. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Context Vector Model for Document Representation: A Computational Study 4th

Context Vector Model for Document Representation: A Computat...

引用

4th ccf International conference on natural language processing and chinese computing (nlpcc)

作者： Wei, Yang Wei, Jinmao Xu, Hengpeng Nankai Univ Coll Comp & Control Engn Weijin Rd 94 Tianjin 300071 Peoples R China Nankai Univ Coll Software Tianjin 300071 Peoples R China

ISBN: (纸本)9783319252070;9783319252063

To tackle the sparse data problem of the bag-of-words model for document representation, the Context Vector Model (CVM) has been proposed to enrich a document with the relatedness of all the words in a corpus to the document. The nature of CVM is the combination of word vectors, wherefore the representation method for words is essential for CVM. A computational study is performed in this paper to compare the effects of the newly proposed word representation methods embedded in CVM. The experimental results demonstrate that some of the newly proposed word representation methods significantly improve the performance of CVM, for they estimate the relatedness between words better.

关键词： Document representation Word vector Relatedness

来源：评论

学校读者我要写书评

暂无评论

Random walks for opinion summarization on conversations 3

Random walks for opinion summarization on conversations

引用

3rd ccf conference on natural language processing and chinese computing, nlpcc 2014

作者： Wang, Zhongqing Lin, Liyuan Li, Shoushan Zhou, Guodong Natural Language Processing Lab School of Computer Science and Technology Soochow University China

ISBN: (纸本)9783662459232

Opinion summarization on conversations aims to generate a sentimental summary for a dialogue and is shown to be much more challenging than traditional topic-based summarization and general opinion summarization, due to its specific characteristics. In this study, we propose a graph-based framework to opinion summarization on conversations. In particular, a random walk model is proposed to globally rank the utterances in a conversation. The main advantage of our approach is its ability of integrating various kinds of important information, such as utterance length, opinion, and dialogue structure, into a graph to better represent the utterances in a conversation and the relationship among them. Besides, a global ranking algorithm is proposed to optimize the graph. Empirical evaluation on the Switchboard corpus demonstrates the effectiveness of our approach. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Building Corpus with Emoticons for Sentiment Analysis 7th

Building Corpus with Emoticons for Sentiment Analysis

引用

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

作者： Li, Changliang Wang, Yongguan Li, Changsong Qi, Ji Liu, Pengyuan Kingsoft AI Lab 33 Xiaoying West Rd Beijing 100085 Peoples R China Beijing Language & Culture Univ 15 Xueyuan Rd Beijing 100083 Peoples R China Peking Univ 5 Yiheyuan Rd Beijing 100871 Peoples R China

ISBN: (纸本)9783319995014;9783319995007

Corpus is an essential resource for data driven natural language processing systems, especially for sentiment analysis. In recent years, people increasingly use emoticons on social media to express their emotions, attitudes or preferences. We believe that emoticons are a non-negligible feature of sentiment analysis tasks. However, few existing works focused on sentiment analysis with emoticons. And there are few related corpora with emoticons. In this paper, we create a large scale chinese Emoticon Sentiment Corpus of Movies (CESCM). Different to other corpora, there are a wide variety of emoticons in this corpus. In addition, we did some baseline sentiment analysis work on CESCM. Experimental results show that emoticons do play an important role in sentiment analysis. Our goal is to make the corpus widely available, and we believe that it will offer great support to sentiment analysis research and emoticon research.

关键词： Emoticon Sentiment analysis Corpus

来源：评论

学校读者我要写书评

暂无评论

Hyper-Gated Recurrent Neural Networks for chinese Word Segmentation 6th

Hyper-Gated Recurrent Neural Networks for Chinese Word Segme...

引用

6th ccf International conference on natural language processing and chinese computing (nlpcc)

作者： Shi, Zhan Chen, Xinchi Qiu, Xipeng Huang, Xuanjing Fudan Univ Shanghai Key Lab Intelligent Informat Proc 825 Zhangheng Rd Shanghai Peoples R China Fudan Univ Sch Comp Sci 825 Zhangheng Rd Shanghai Peoples R China

ISBN: (纸本)9783319736181;9783319736174

Recently, recurrent neural networks (RNNs) have been increasingly used for chinese word segmentation to model the contextual information without the limit of context window. In practice, two kinds of gated RNNs, long short-term memory (LSTM) and gated recurrent unit (GRU), are often used to alleviate the long dependency problem. In this paper, we propose the hyper-gated recurrent neural networks for chinese word segmentation, which enhance the gates to incorporate the historical information of gates. Experiments on the benchmark datasets show that our model outperforms the baseline models as well as the state-of-the-art methods.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Sentiment classification of chinese contrast sentences 3

Sentiment classification of chinese contrast sentences

引用

3rd ccf conference on natural language processing and chinese computing, nlpcc 2014

作者： Li, Junjie Zhou, Yu Liu, Chunyang Pang, Lin National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing100029 China

ISBN: (纸本)9783662459232

We present the study of sentiment classification of chinese contrast sentences in this paper, which are one of the commonly used language constructs in text. In a typical review, there are at least around 6% of such sentences. Due to the complex contrast phenomenon, it is hard to use the traditional bag-of-words to model such sentences. In this paper, we propose a Two-Layer Logistic Regression (TLLR) model to leverage such relationship in sentiment classification. According to different connectives, our model can treat different clauses differently in sentiment classification. Experimental results show that TLLR model can effectively improve the performance of sentiment classification of chinese contrast sentences. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Simple Question Generation by Template-Based Seq2seq Learning 6th

Large-Scale Simple Question Generation by Template-Based Seq...

引用

6th ccf International conference on natural language processing and chinese computing (nlpcc)

作者： Liu, Tianyu Wei, Bingzhen Chang, Baobao Sui, Zhifang Peking Univ Sch Elect Engn & Comp Sci Key Lab Computat Linguist Minist Educ 5 Yiheyuan Rd Beijing 100871 Peoples R China

ISBN: (纸本)9783319736181;9783319736174

Numerous machine learning tasks achieved substantial advances with the help of large-scale supervised learning corpora over past decade. However, there's no large-scale question-answer corpora available for chinese question answering over knowledge bases. In this paper, we present a 28M chinese Q&A corpora based on the chinese knowledge base provided by nlpcc2017 KBQA challenge. We propose a novel neural network architecture which combines template-based method and seq2seq learning to generate highly fluent and diverse questions. Both automatic and human evaluation results show that our model achieves outstanding performance (76.8 BLEU and 43.1 ROUGE). We also propose a new statistical metric called DIVERSE to measure the linguistic diversity of generated questions and prove that our model can generate much more diverse questions compared with other baselines.

关键词： Question generation Template-based seq2seq Linguistic diversity

来源：评论

学校读者我要写书评

暂无评论

DialogueTRGAT: Temporal and Relational Graph Attention Network for Emotion Recognition in Conversations 11th

DialogueTRGAT: Temporal and Relational Graph Attention Netwo...

引用

11th ccf International conference on natural language processing and chinese computing (nlpcc)

作者： Kang, Junjun 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)9783031171208;9783031171192

Emotion Recognition in Conversations (ERC) is the task of identifying the emotions of utterances from speakers in a conversation, which is beneficial to a number of applications, including opinion mining over conversations, developing empathetic dialogue systems, and so on. Many approaches have been proposed to handle this problem in recent years. However, most existing approaches either focus on using RNN-based models to simulate temporal information change in the conversation or graph-based models to take the relationships between the utterances of the speakers into account. In this paper, we propose a temporal and relational graph attention network, named DialogueTRGAT, to combine the strengths of RNN-based models and graph-based models. DialogueTRGAT can better model the intrinsic structure and information flow within a conversation for better emotion recognition. We conduct experiments on two benchmark datasets(IEMOCAP, MELD), and the experimental results demonstrate the great effectiveness of our approach compared with several competitive baselines.

关键词： Emotion recognition Graph model Dialogue modeling

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6页 << < 1 2 3 4 5 6 > >>

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：