检索结果-内蒙古大学图书馆

2012 8th International Conference on Natural Computation, ICNC 2012

作者： Zhang, Wenwen Liu, Lemao Cao, Hailong Zhao, Tiejun MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin China

ISBN: (纸本)9781457721311

The training procedure is very important in statistical machine translation (SMT). It has a great influence on the final performance of a translation system. The widely used method in SMT is the minimum error rate training (MERT). It is effective to estimate the feature function weights. However, MERT does not use regularization and has been observed to over-fit. In this paper, we describe a method named softmax-margin, which is a modification of the max-margin training. This approach is simple, efficient, and easy to implement. We conduct our work using data sets from the WMT shared tasks. The results of experiment on small scale French-English translation task reach a competitive performance compared to MERT. © 2012 IEEE.

关键词： Computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

A novel self-adaptive clustering algorithm for dynamic data

A novel self-adaptive clustering algorithm for dynamic data

引用

19th International Conference on Neural Information processing, ICONIP 2012

作者： Liu, Ming Lin, Lei Shan, Lili Sun, Chengjie MOE-MS Key Laboratory of Natural Language Processing and Speech School of Computer Science and Technology Harbin Institute of Technology Harbin China

ISBN: (纸本)9783642344862

Along with the fast advance of internet technique, internet users have to deal with novel data every day. For most of them, one of the most useful knowledge exploited from web is about the transfer of the information expressed by dynamically updated data. Unfortunately, traditional algorithms often cluster novel data without considering the existent clustering model. They have to cluster input data over again, once input data are updated. Hence, they are time-consuming and inefficient. For efficiently clustering dynamic data, a novel Self-Adaptive Clustering algorithm (abbreviated as SAC) is proposed in this paper. SAC comes from Self Organizing Mapping algorithm (abbreviated as SOM), whereas, it doesn't need to make any assumption about neuron topology beforehand. Besides, when input data are updated, its topology remodels meanwhile. Experiment results demonstrate that SAC can automatically tune its topology along with the update of input data. © 2012 Springer-Verlag.

关键词： Conformal mapping

来源：评论

学校读者我要写书评

暂无评论

A tentative study on rule based metaphor identification

A tentative study on rule based metaphor identification

引用

2012 9th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2012

作者： Zhang, Yu Yang, Muyun Chen, Xi Li, Sheng Zhao, Tiejun MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology China School of Foreign Languages Harbin Institute of Technology Harbin China

ISBN: (纸本)9781467300223

As one of the challenging issues in the field of Natural language processing (NLP), metaphor has aroused substantial attention among researchers in recent years. Many models and methods have been proposed for proper understanding of metaphors. But the automatic identification of metaphor is less touched. This paper presents a tentative study on the metaphor identification based on rules, and the results on a small scale corpus are provided. © 2012 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Interpersonal trust relationship model in restricted domain of literary works

Interpersonal trust relationship model in restricted domain ...

引用

2012 IEEE International Conference on Computer Science and Automation Engineering, CSAE 2012

作者： Liu, Liqun Zheng, Dequan Zhao, Tiejun Yang, Mengda MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin China Institute for Interdisciplinary Information Science Tsinghua University Beijing China

ISBN: (纸本)9781467300865

Interpersonal trust relationship is an important dimension of interpersonal relationships. With new introduced plots of literature, we can evaluate the environment of characters and predict plot development to some extent. This paper proposes a representation of interpersonal trust relationship based on the fuzzy set theory in the restricted domain of A Dream of Red Mansions. Interpersonal trust degrees are obtained by the comprehensive evaluation based on the fuzzy analytic hierarchy process. This paper proposes a thought that solves the divergences of domain experts, and proposes an approach that establishes the initial trust degree between characters. Based on above, this paper analyzes the trust bias and overall trust degree between characters and mines the relationship between characters and content of the whole trust network of characters. The experiments show that the model is efficient in reflecting the interpersonal trust relationship of A Dream of Red Mansions. The interpersonal trust relationship of A Dream of Red Mansions is modeled and analyzed by the fuzzy set theory, which provides a novel thought on mathematical study of interpersonal trust relationship in literary works. © 2012 IEEE.

关键词： Fuzzy set theory

来源：评论

学校读者我要写书评

暂无评论

An effective approach to pedestrian detection in thermal imagery

An effective approach to pedestrian detection in thermal ima...

引用

2012 8th International Conference on Natural Computation, ICNC 2012

作者： Li, Wei Zheng, Dequan Zhao, Tiejun Yang, Mengda MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin China Institute for Interdisciplinary Information Science Tsinghua University Beijing China

ISBN: (纸本)9781457721311

In this paper, an integrated algorithm to detect humans in thermal imagery was introduced. In recent years, histogram of oriented gradient (HOG) is a quite popular algorithm for person detection in visible imagery. We implement the pedestrian detection in infrared imagery with this algorithm by adjusting the parameters. Simultaneously, we have increased some other geometric characteristics, such as mean contrast, which is used as features for the detection. After analyzing the property of the infrared imagery, which is designed to meet the shortfall of the HOG in infrared imagery, the combined vectors are fed to a linear SVM for object/non-object classification and we get the detector at the same time. After that, the detection window is scanned across the image at multiple positions and scales, which is followed by the combination of the overlapping detections. At last, a pedestrian is described by a final detection, and we have detected the pedestrians in the thermal imagery. Experimental results with OSU Thermal Pedestrian Database are reported to demonstrate the excellent performance of our algorithms. © 2012 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Dynamic incremental event sub-topic detection and tracking

引用

Journal of Convergence Information Technology 2012年第19期7卷 327-336页

作者： Li, Fenghuan Zheng, Dequan Zhao, Tiejun MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin 150001 China

A dynamic incremental model is presented for sub-topic detection and tracking, which borrows ideas of single-pass clustering, multi-category and dynamic incremental model. It is proposed based on time series of topic event, containing dynamic threshold selection, similarity smoothing and dynamic incremental strategy. Meanwhile, overall evaluation criteria combining with χ2 - test is served for performance analysis. The algorithm is effective for sub-topic detection, facilitating users to follow topic event explicitly. Results show that the algorithm proposed in this paper obtains satisfying performance.

关键词： Detection Incremental Sub-topic Topic event Tracking

来源：评论

学校读者我要写书评

暂无评论

Softmax-margin training for statistical machine translation

Softmax-margin training for statistical machine translation

引用

International Conference on Natural Computation (ICNC)

作者： Wenwen Zhang Lemao Liu Hailong Cao Tiejun Zhao MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin China

关键词： Training NIST Cost function Probabilistic logic Error analysis Gold

来源：评论

学校读者我要写书评

暂无评论

Syllable-based Machine Transliteration with Extra Phrase Features 12

Syllable-based Machine Transliteration with Extra Phrase Fea...

引用

Named Entity Workshop

作者： Chunyue Zhang Tingting Li Tiejun Zhao MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin China

ISBN: (纸本)9781627483476

This paper describes our syllable-based phrase transliteration system for the NEWS 2012 shared task on English-Chinese track and its back. Grapheme-based Transliteration maps the character(s) in the source side to the target character(s) directly. However, character-based segmentation on English side will cause ambiguity in alignment step. In this paper we utilize Phrase-based model to solve machine transliteration with the mapping between Chinese characters and English syllables rather than English characters. Two heuristic rule-based syllable segmentation algorithms are applied. This transliteration model also incorporates three phonetic features to enhance discriminative ability for phrase. The primary system achieved 0.330 on Chinese-English and 0.177 on English-Chinese in terms of top-1 accuracy.

关键词： English English language machine ambiguity Chinese script MAPPING(MATHEMATICAL) mapping primary system

来源：评论

学校读者我要写书评

暂无评论

Extracting Main Content of a Topic on Online Social Network by Multi-document Summarization

Extracting Main Content of a Topic on Online Social Network ...

引用

International Conference on Computational Intelligence and Security

作者： Chunyan Liu Conghui Zhu Tiejun Zhao Dequan Zheng MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin China

Online social media has become one of the most important ways people communicate, while how to find valuable information from huge amounts of data becomes a key problem. We present a novel topic extraction method that employs topic value of each words and social model attributes as additional features based on the multi-document summarization. The experimental results show that the multi-document summarization with the topic and the sociality are helpful to extract topics from social media.

关键词： Blogs Social network services Feature extraction Dictionaries Data mining Media Natural language processing

来源：评论

学校读者我要写书评

暂无评论

A tentative study on rule based metaphor identification

A tentative study on rule based metaphor identification

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Yu Zhang Muyun Yang Xi Chen Sheng Li Tiejun Zhao MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin China School of Foreign Languages Harbin Institute of Technology Harbin China

关键词： Semantics Natural language processing Computational linguistics Tin Artificial intelligence Silicon Context

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：