检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Liang, Yudong Yang, Ze Zhang, Kai He, Yihui Wang, Jinjun Zheng, Nanning Key Laboratory of Computational Intelligence Chinese Information Processing of Ministry of Education School of Computer and Information Technology Shanxi University 92 Wucheng Road Taiyuan Shanxi Province030006 China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Harbin Institute of Technology

Recent years have witnessed great success of con-volutional neural network (CNN) for various problems both in low and high level visions. Especially noteworthy is the residual network which was originally proposed to handle high-level vision problems and enjoys several merits. This paper aims to extend the merits of residual network, such as skip connection induced fast training, for a typical low-level vision problem, i.e., single image super-resolution. In general, the two main challenges of existing deep CNN for supper-resolution lie in the gradient exploding/vanishing problem and large numbers of parameters or computational cost as CNN goes deeper. Correspondingly, the skip connections or identity mapping shortcuts are utilized to avoid gradient exploding/vanishing problem. In addition, the skip connections have naturally centered the activation which led to better performance. To tackle with the second problem, a lightweight CNN architecture which has carefully designed width, depth and skip connections was proposed. In particular, a strategy of gradually varying the shape of network has been proposed for residual network. Different residual architectures for image super-resolution have also been compared. Experimental results have demonstrated that the proposed CNN model can not only achieve state-of-the-art PSNR and SSIM results for single image super-resolution but also produce visually pleasant results. This paper has extended the mmm 2017 oral conference paper with a considerable new analyses and more experiments especially from the perspective of centering activations and ensemble behaviors of residual network. Copyright © 2017, The Authors. All rights reserved.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Architectures and key DSP Techniques of Next Generation Passive Optical Network (PON)

Architectures and Key DSP Techniques of Next Generation Pass...

引用

Optical Fiber Communication Conference, OFC 2016

作者： Li, Fan Luo, Zhibin Yin, Mingzhu Wang, Xiaowu Li, Zhaohui Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems School of Electronics and Information Technology Sun Yat-Sen University Guangzhou510275 China Zhuhai519080 China

Passive optical network (PON) is continuously explored for new architectures and effective DSP techniques to adapt to the next generation communication. In this paper, we summarize our work and discuss the challenges ...

ISBN: (纸本)9781943580071

关键词：

来源：评论

学校读者我要写书评

暂无评论

Combining Event-level and Cross-event Semantic information for Event-Oriented Relation Classification by SCNN

Combining Event-level and Cross-event Semantic Information f...

引用

第十五届全国计算语言学学术会议(CCL2016)暨第四届基于自然标注大数据的自然语言处理国际学术研讨会(NLP-NABD-2016)

作者： Siyuan Ding Yu Hong Shanshan Zhu Jianmin Yao Qiaoming Zhu Provincial Key Laboratory of Computer Information Processing Technology Soochow UniversitySuzhouChina

Previous researches on event relation classification primarily rely on lexical and syntactic *** this paper,we use a Shallow Convolutional Neural Network(SCNN)to extract event-level and cross-event semantic features for event relation *** the one hand,the shallow structure alleviates the over-fitting problem caused by the lack of diverse relation *** the other hand,the utilization and combination of event-level and cross-event semantic information help improve relation *** experimental results show that our approach outperforms the state of the art.

关键词： Event Relation Classification Semantic information Frame Embedding SCNN

来源：评论

学校读者我要写书评

暂无评论

SG++: Word representation with sentiment and negation for twitter sentiment classification 16

SG++: Word representation with sentiment and negation for tw...

引用

39th International ACM SIGIR Conference on Research and Development in information Retrieval, SIGIR 2016

作者： Hu, Qinmin Pei, Yijun Chen, Qin He, Liang Shanghai Key Laboratory of Multidimensional Information Processing Department of Computer Science and Technology East China Normal University Shanghai200241 China

ISBN: (纸本)9781450342902

Here we propose an advance Skip-gram model to incorporate both word sentiment and negation information. In particular, there is aa softmax layer for the word sentiment polarity upon the Skip-gram model. Then, two paralleled embedding layers are set up in the same embedding space, one for the affirmative context and the other for the negated context, followed by their loss functions. We evaluate our proposed model on the 2013 and 2014 SemEval data sets. The experimental results show that the proposed approach achieves better performance and learns higher dimensional word embedding informatively on the large-scale data. © 2016 ACM.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

ECNU at SemEval-2016 Task 6: Relevant or not? Supportive or not? A two-step learning system for automatic Detecting Stance in Tweets 10

ECNU at SemEval-2016 Task 6: Relevant or not? Supportive or ...

引用

10th International Workshop on Semantic Evaluation, SemEval 2016

作者： Zhang, Zhihua Lan, Man Department of Computer Science and Technology East China Normal University Shanghai China Shanghai Key Laboratory of Multidimensional Information Processing China

ISBN: (纸本)9781941643952

This paper describes our submissions to Task 6, i.e., Detecting Stance in Tweets, in SemEval 2016, which aims at detecting the stance of tweets towards given target. There are three stance labels: Favor (directly or indirectly by supporting given target), Against (directly or indirectly by opposing or criticizing given target), and None (none of the above). To address this task, we present a two-step learning system, which performs two steps, i.e., relevance detection and orientation detection, in a pipeline-based processing procedure. Our system ranked the 5th among 19 teams. © 2016 Association for Computational Linguistics.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A mean shift assisted differential evolution algorithm 11th

A mean shift assisted differential evolution algorithm

引用

11th International Conference on Bio-inspired Computing – Theories and Applications, BIC-TA 2016

作者： Fang, Hui Zhou, Aimin Zhang, Guixu Shanghai Key Laboratory of Multidimensional Information Processing Department of Computer Science and Technology East China Normal University Shanghai200241 China

ISBN: (纸本)9789811036132

It is well known that Differential Evolution (DE) algorithm has been widely applied to solve global optimization problems during the last decades. DE is usually criticized for the slow convergence. To improve the algorithm performance, we propose an algorithm called MSDE that utilizes a local search operator based on mean shift. In MSDE, one offspring solution is generated by the mean shift based search operator, and the others are created by the DE search operator. A test suite of 12 benchmark functions with different characteristics are chosen to evaluate our approach. The experimental results suggest that MSDE can successfully improve the performance of DE and have a faster convergence rate on the given test suite. © Springer Nature Singapore Pte Ltd. 2016.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

ECNU at SemEval-2016 task 5: Extracting effective features from relevant fragments in sentence for aspect-based sentiment analysis in reviews 10

ECNU at SemEval-2016 task 5: Extracting effective features f...

引用

10th International Workshop on Semantic Evaluation, SemEval 2016

作者： Jiang, Mengxiao Zhang, Zhihua Lan, Man Department of Computer Science and Technology East China Normal University Shanghai China Shanghai Key Laboratory of Multidimensional Information Processing China

ISBN: (纸本)9781941643952

This paper describes our systems submitted to the Sentence-level and Text-level Aspect-Based Sentiment Analysis (ABSA) task (i.e., Task 5) in SemEval-2016. The task involves two phases, namely, Aspect Detection phase and Sentiment Polarity Classification phase. We participated in the second phase of both subtasks in laptop and restaurant domains, which focuses on the sentiment analysis based on the given aspect. In this task, we extracted four types of features (i.e., Sentiment Lexicon Features, Linguistic Features, Topic Model Features and Word2vec Feature) from certain fragments related to aspect rather than the whole sentence. Then the proposed features are fed into supervised classifiers for sentiment analysis. Our submissions rank above average. © 2016 Association for Computational Linguistics.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

ECNU at SemEval-2016 Task 4: An empirical investigation of traditional NLP features and word embedding features for sentence-level and topic-level sentiment analysis in twitter 10

ECNU at SemEval-2016 Task 4: An empirical investigation of t...

引用

10th International Workshop on Semantic Evaluation, SemEval 2016

作者： Zhou, Yunxiao Zhang, Zhihua Lan, Man Department of Computer Science and Technology East China Normal University Shanghai China Shanghai Key Laboratory of Multidimensional Information Processing China

ISBN: (纸本)9781941643952

This paper reports our submissions to Task 4, i.e., Sentiment Analysis in Twitter (SAT), in SemEval 2016, which consists of five subtasks grouped into two levels: (1) sentence level, i.e., message polarity classification (subtask A), and (2) topic level, i.e., tweet classification and quantification according to two-point scale (subtask B and D) or five-point scale (subtask C and E). We participated in all these five subtasks. To address these subtasks, we investigated several traditional Natural Language processing (NLP) features including sentiment lexicon, linguistic and domain specific features, and word embedding features together with supervised machine learning methods. Officially released results showed that our systems rank above average. © 2016 Association for Computational Linguistics.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Two end-to-end shallow discourse parsers for English and Chinese in CoNLL-2016 shared task 20

Two end-to-end shallow discourse parsers for English and Chi...

引用

20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016

作者： Wang, Jianxiang Lan, Man Shanghai Key Laboratory of Multidimensional Information Processing Department of Computer Science and Technology East China Normal University Shanghai200241 China

ISBN: (纸本)1932432663

This paper describes our two discourse parsers (i.e., English discourse parser and Chinese discourse parser) for submission to CoNLL-2016 shared task on Shallow Discourse Parsing. For English discourse parser, we build two separate argument extractors for single sentence (SS) case, and adopt a convolutional neural network for Non-Explicit sense classification based on (Wang and Lan, 2015b)’s work. As for Chinese discourse parser, we build a pipeline system following the annotation procedure of Chinese Discourse Treebank in (Zhou and Xue, 2015). Our English discourse parser achieves better performance than the best system of CoNLL-2015 and the Chinese discourse parser achieves encouraging results. Our two parsers both rank second on the blind datasets. © 2016 Association for Computational Linguistics.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

ECNU at SemEval-2016 task 7: An enhanced supervised learning method for Lexicon Sentiment Intensity ranking 10

ECNU at SemEval-2016 task 7: An enhanced supervised learning...

引用

10th International Workshop on Semantic Evaluation, SemEval 2016

作者： Wang, Feixiang Zhang, Zhihua Lan, Man Department of Computer Science and Technology East China Normal University Shanghai China Shanghai Key Laboratory of Multidimensional Information Processing China

ISBN: (纸本)9781941643952

This paper describes our system submissions to task 7 in SemEval 2016, i.e., Determining Sentiment Intensity. We participated the first two subtasks in English, which are to predict the sentiment intensity of a word or a phrase in English Twitter and General English domains. To address this task, we present a supervised learning-to-rank system to predict the relevant scores, i.e., the strength associated with positive sentiment, for English words or phrases. Multiple linguistic and sentiment features are adopted, e.g., Sentiment Lexicons, Sentiment Word Vectors, Word Vectors, Linguistic Features, etc. Officially released results showed that our systems rank the 1st among all submissions in English, which proves the effectiveness of the proposed method. © 2016 Association for Computational Linguistics.

关键词： Supervised learning

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：