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

17 篇 会议
2 篇 期刊文献

馆藏范围

19 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

17 篇 工学
- 16 篇 计算机科学与技术...
- 14 篇 软件工程
- 4 篇 生物工程
- 2 篇 控制科学与工程
8 篇 管理学
- 7 篇 图书情报与档案管...
- 1 篇 管理科学与工程(可...
- 1 篇 工商管理
5 篇 理学
- 4 篇 生物学
- 2 篇 数学
- 1 篇 统计学（可授理学、...
1 篇 法学
- 1 篇 社会学

主题

3 篇 text processing
1 篇 knowledge based ...
1 篇 merging
1 篇 formal languages
1 篇 learning algorit...
1 篇 taxonomies
1 篇 benchmarking
1 篇 social networkin...
1 篇 pipelines
1 篇 word processing
1 篇 supervised learn...
1 篇 engines
1 篇 intelligent syst...

机构

2 篇 qualitative reas...
1 篇 eecs department ...
1 篇 school for mathe...
1 篇 univ rostock ros...
1 篇 boeing research ...
1 篇 tetherless world...
1 篇 computer science...
1 篇 ibm res europe d...
1 篇 1211 university ...
1 篇 irobot corporati...
1 篇 computer science...
1 篇 pacific northwes...
1 篇 information scie...
1 篇 school ot intera...
1 篇 usc information ...
1 篇 adaptive systems...
1 篇 school of comput...
1 篇 social software ...
1 篇 university of ma...
1 篇 computer science...

作者

3 篇 forbus kenneth d...
2 篇 carlson andrew
2 篇 oates tim
2 篇 lockwood kate
2 篇 hovy eduard
2 篇 tomai emmett
2 篇 nirenburg sergei
2 篇 sharma abhishek
1 篇 mcnamee paul
1 篇 condoravdi cleo
1 篇 mohammad saif
1 篇 garera nikesh
1 篇 greaves mark
1 篇 stefan woelfl
1 篇 dorr bonnie
1 篇 porter bruce
1 篇 vasile flavian
1 篇 li ding
1 篇 bernhard nebel
1 篇 wang sophie h.

语言

19 篇 英文

检索条件"任意字段=Learning by Reading and Learning to Read - Papers from the AAAI Spring Symposium"

共 19 条记录，以下是1-10 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：

Symbol Description reading 38

Symbol Description Reading

引用

38th aaai Conference on Artificial Intelligence (aaai) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th symposium on Educational Advances in Artificial Intelligence

作者： Lynch, Karol Eck, Bradley Ploennigs, Joern IBM Res Europe Dublin Ireland Univ Rostock Rostock Germany

ISBN: (纸本)1577358872

Mathematical formulas give concise representations of a document's key ideas in many natural sciences and engineering domains. The symbols that make up formulas carry semantic meaning that may differ by document or equation. What does x mean in a given paper? Interpreting the symbols that comprise formulas requires identifying descriptions from the surrounding text. We approach this task of symbol description reading as an application of current AI technologies targeting the tuning of large language models for particular domains and automation of machine learning. Our pipeline integrates AI question answering and natural language processing to read symbol descriptions. We consider extractive and generative AI model variations and apply our pipeline on two example tasks of symbol description reading. Promising results provide motivation for wider deployment for which we describe a microservice architecture and related challenges.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

learning by reading and learning to read - papers from the aaai spring symposium

Learning by Reading and Learning to Read - Papers from the A...

引用

learning by reading and learning to read - papers from the aaai spring symposium

ISBN: (纸本)9781577354147

The proceedings contain 16 papers. The topics discussed include: toward never ending language learning;learning a named entity tagger from gazetteers with the partial perceptron;a study of machine reading from multiple texts;methods of rule acquisition in the textlearner system;using Wikitology for cross-document entity co reference resolution;steps towards a second generation learning by reading system;resolving references and identifying existing knowledge in a memory based parser;lexical inference and the problem of the long tail;discovering causal and temporal relations in biomedical texts;leveraging lexical resources for the detection of event relations;and language understanding as recognition and transduction of numerous overlaid patterns.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sifu: Interactive crowd-assisted language learning

Sifu: Interactive crowd-assisted language learning

引用

2012 aaai spring symposium

作者： Chan, Cheng-Wei Hsu, Jane Yung-Jen Computer Science and Information Engineering National Taiwan University Taiwan

ISBN: (纸本)9781577355557

This paper introduces SIFU, a system that recruits in real time native speakers as online volunteer tutors to help answer questions from Chinese language learners in reading news articles. SIFU integrates the strengths of two effective online language learning methods: reading online news and communicating with online native speakers. SIFU recruits volunteers from an online social network rather than recruits workers from Amazon Mechanical Turk. Initial experiments showed that the proposed approach is able to effectively recruit online volunteer tutors, adequately answer the learners' questions, and efficiently obtain an answer for the learner. Our field deployment illustrates that SIFU is very useful in assisting Chinese learners in reading Chinese news articles and online volunteer tutors are willing to help Chinese learners when they are on social network service. Copyright © 2012, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

learning by reading: Normalizing complex linguistic s tructures onto a hnowledge representation

Learning by reading: Normalizing complex linguistic s tructu...

引用

learning by reading and learning to read - papers from the aaai spring symposium

作者： Bobrow, Daniel G. Condoravdi, Cleo Karttunen, Lauri Zaenen, Annie Palo Alto Research Center 3333 Coyote Hill Road Palo Alto CA 94304 United States

ISBN: (纸本)9781577354147

To make learning by reading easier, one strategy is to map language that is read onto a normalized knowledge representation. The normalization maps alternative expressions of the same content onto essentially identical representations. This brief position paper illustrates the power of this approach in PARC,s Bridge system through examples of textual inference.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Steps towards a second generation learning by reading system

Steps towards a second generation learning by Reading system

引用

learning by reading and learning to read - papers from the aaai spring symposium

作者： Forbus, Kenneth D. Lockwood, Kate Sharma, Abhishek Tomai, Emmett Qualitative Reasoning Group Northwestern University 2133 Sheridan Road Evanston IL 60208 United States

ISBN: (纸本)9781577354147

learning by reading is an important scientific problem because it requires modeling a wide range of human abilities. It also could break the knowledge engineering bottleneck, enabling the bootstrapping of intelligent systems via interaction with people using natural language. This paper outlines our progress on creating a 2nd generation learning by reading system, focusing on three main areas: Multimodal knowledge capture, reasoning for NL understanding and learning, and analogical dialogue acts.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Kleo: A bootstrapping learning-by-reading system

Kleo: A bootstrapping learning-by-reading system

引用

learning by reading and learning to read - papers from the aaai spring symposium

作者： Kim, Doo Soon Porter, Bruce Computer Science Department University of Texas at Austin United States

ISBN: (纸本)9781577354147

Kleo is a bootstrapping learning-by-reading system that builds a knowledge base in a fully automated way by reading texts for a domain. KLEO,s initial knowledge base is a small knowledge base that consists of domain independent knowledge and Kleo expands the knowledge base with the information extracted from texts. A key facility in KLEO is knowledge integration which combines new information gleaned from individual sentences of the texts, along with prior knowledge, to form a comprehensive and computationally useful knowledge base. This paper introduces the architecture of Kleo, especially the knowledge integration facility, and presents our evaluation plan. © 2009, Association for the Advancement of Artificial Intelligence.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Toward never ending language learning

Toward never ending language learning

引用

learning by reading and learning to read - papers from the aaai spring symposium

作者： Betteridge, Justin Carlson, Andrew Hong, Sue Ann Hruschka Jr., Estevam R. Law, Edith L.M. M.mitchell, Tom Wang, Sophie H. School of Computer Science Carnegie Mellon University Pittsburgh PA 15213 United States Federal University of Sao Carlos Sao Carlos SP Brazil

ISBN: (纸本)9781577354147

We report research toward a never-ending language learning system, focusing on a first implementation which learns to classify occurrences of noun phrases according to lexical categories such as "city" and "university." Our experiments suggest that the accuracy of classifiers produced by semi-supervised learning can be improved by coupling the learning of multiple classes based on background knowledge about relationships between the classes (e.g., "university" is mutually exclusive of "company", and is a subset of "organization").

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Cross-document coreference resolution: A key technology for learning by reading

Cross-document coreference resolution: A key technology for ...

引用

learning by reading and learning to read - papers from the aaai spring symposium

作者： Mayfield, James Alexander, David Dorr, Bonnie Eisner, Jason Elsayed, Tamer Finin, Tim Fink, Clay Freedman, Marjorie Garera, Nikesh Mcnamee, Paul Mohammad, Saif Oard, Douglas Piatko, Christine Sayeed, Asad Syed, Zareen Weischedel, Ralph Xu, Tan Yarowsky, David Human Language Technology Center of Excellence 810 WymanParkDrive Baltimore MD United States 1211 University of Maryland Baltimore County Baltimore MD 21250 United States

ISBN: (纸本)9781577354147

Automatic knowledge base population from text is an important technology for a broad range of approaches to learning by reading. Effective automated knowledge base population depends critically upon coreference resolution of entities across sources. Use of a wide range of features, both those that capture evidence for entity merging and those that argue against merging, can significantly improve machine learning-based cross-document coreference resolution. Results from the Global Entity Detection and Recognition task of the NIST Automated Content Extraction (ACE) 2008 evaluation support this conclusion.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

A study of machine reading from multiple texts

A study of machine reading from multiple texts

引用

learning by reading and learning to read - papers from the aaai spring symposium

作者： Clark, Peter Thompson, John Boeing Research and Technology Seattle WA 98124 United States

ISBN: (纸本)9781577354147

A system that seeks to build a semantically coherent representation from multiple texts requires (at least) three things: a representation language that is sufficiently expressive to capture the information conveyed by the text;a natural language engine that can interpret text and generate semantic representations in that language with reasonable reliability;and a knowledge integration capability that can integrate information from different texts and from background knowledge into a coherent whole. In this paper we present a case study of these requirements for interpreting four different paragraphs of text (from different sources), each describing how a two-stroke combustion engine behaves. We identify the challenges involved in meeting these requirements and how they might be addressed. One key feature that emerges is the need for extensive background knowledge to guide the interpretation, disambiguate, and fill in gaps. The resulting contribution of this paper is a deeper understanding of the overall machine reading task.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

learning and evaluating the content and structure of a term taxonomy

Learning and evaluating the content and structure of a term ...

引用

learning by reading and learning to read - papers from the aaai spring symposium

作者： Kozareva, Zornitsa Hovy, Eduard Riloff, Ellen DLSI University of Alicante Campus De San Vicente Alicante 03080 Spain USC Information Sciences Institute 4676 Admiralty Way Marina del Rey CA 90292-6695 United States School of Computing University of Utah Salt Lake City UT 84112 United States

ISBN: (纸本)9781577354147

In this paper, we describe a weakly supervised boot-straping algorithm that reads Web texts and learns taxonomy terms. The bootstrapping algorithm starts with two seed words (a seed hypernym (Root concept) and a seed hyponym) that are inserted into a doubly anchored hyponym pattern. In alternating rounds, the algorithm learns new hyponym terms and new hypernym terms that are subordinate to the Root concept. We conducted an extensive evaluation with human annotators to evaluate the learned hyponym and hypernym terms for two categories: animals and people. © 2009, Association for the Advancement of Artificial Intelligence.

关键词： Taxonomies

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2页 << < 1 2 > >>

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：