Titlebook: Social Media Processing; 4th National Confere Xichun Zhang,Maosong Sun,Xuanjing Huang Conference proceedings 2015 Springer Science+Business

咽下

Magisterial

不成比例

Nugget-Based First Story Detection in Twitter Stream,k in twitter event detection. However, the number of comparisons is too large in traditional online detection methods and there is a lack of global information of each event during detection process. To deal with the shortcomings above, we propose a novel FSD method based on nugget, which can descri

NADIR

音樂學(xué)者

Approaches to Detect Micro-Blog User Interest Communities Through the Integration of Explicit User icro-blog user interest community detection approach is proposed. First, we analyze the follow relationship between the users to construct the user follow-ship network. Second, we construct the user interest feature vectors based on the concept of feature mapping to build a user-tag based interest r

總

Employee

破譯密碼

Systematic Comparison of Question Target Classification Taxonomies Towards Question Answering,argets can help understand questions for retrieving relevant passages and assist answer extraction and ranking for improving answer retrieval accuracy and user satisfaction with return answers. This paper presents a systematic analysis on question target classification taxonomy. We investigate exist

mortgage

Combining Convolutional Neural Network and Support Vector Machine for Sentiment Classification, tasks. However, the CNN-based model simply uses a fully connected layer for classification and it cannot perform a non-linear classification efficiently compared to the support vector machine (SVM) classifier. Target to this problem, in this paper, we combine CNN and SVM for sentiment classificatio

Ventricle

A Novel Cross Modal Hashing Algorithm Based on Multi-modal Deep Learning,here is a latent space shared by multi-modal features, and embed the heterogeneous data into a joint abstraction space by linear projections. However, these approaches are sensitive to the noise of data, and unable to make use of unlabelled data and multi-modal data with missing values in the real-w