With the rapid advancement of optical remote sensing (RS) satellites, RS video has replaced RS image as the main way to obtain information in orbit environment. However, the storage and transmission of on-orbit RS vid...
详细信息
With the fast development of World Wide Web, the quantity of web information is increasing in an unprecedented pace, a great many of which are generated dynamically from background databases, and can't be indexed ...
详细信息
With the fast development of World Wide Web, the quantity of web information is increasing in an unprecedented pace, a great many of which are generated dynamically from background databases, and can't be indexed by traditional search engine, so we call them Deep Web. For the heterogeneous and dynamic features of Deep Web sources, classifying the Deep Web source by domain effectively is a significant precondition of Deep Web sources integration. In this paper, we consider the visible features of Deep Web and Maximum Entropy approach, and then on the basis of binary classification, we propose a new multivariate classification approach based on Maximum Entropy towards Deep Web sources. In addition, we propose a Feedback algorithm to improve the accuracy of classification. An experimental evaluation over real Web data shows that, our approach could provide an effective and general solution to the multivariate classification of Deep Web sources.
Independent component analysis (ICA), instead of the traditional discrete cosine transform (DCT), is often used to project log Mel spectrum in robust speech feature extraction. The paper proposed using symmetric ortho...
详细信息
This paper proposes a unified dynamic relation tree (DRT) span for tree kernel-based semantic relation extraction between entity names. The basic idea is to apply a variety of linguistics-driven rules to dynamically p...
详细信息
This paper proposes a unified dynamic relation tree (DRT) span for tree kernel-based semantic relation extraction between entity names. The basic idea is to apply a variety of linguistics-driven rules to dynamically prune out noisy information from a syntactic parse tree and include necessary contextual information. In addition, different kinds of entity-related semantic information are unified into the syntactic parse tree. Evaluation on the ACE RDC 2004 corpus shows that the unified DRT span outperforms other widely-used tree spans, and our system achieves comparable performance with the state-of-the-art kernel-based ones. This indicates that our method can not only well model the structured syntactic information but also effectively capture entity-related semantic information.
This paper explores protein-protein interaction extraction from biomedical literature using support vector machines (SVM). Besides common lexical features, various overlap features and base phrase chunking information...
详细信息
This paper explores protein-protein interaction extraction from biomedical literature using support vector machines (SVM). Besides common lexical features, various overlap features and base phrase chunking information are used to improve the performance. Evaluation on the AIMed corpus shows that our feature-based method achieves very encouraging performances of 68.6 and 51.0 in F-measure with 10-fold pair-wise cross-validation and 10-fold document-wise cross-validation respectively, which are comparable with other state-of-the-art feature-based methods.
Ant colony optimization (ACO for short) has been proved a successful meta-heuristic by a huge of empirical studies. This paper discusses the termination criteria of ACO and therefore provides research ideas to other m...
详细信息
Ant colony optimization (ACO for short) has been proved a successful meta-heuristic by a huge of empirical studies. This paper discusses the termination criteria of ACO and therefore provides research ideas to other meta-heuristics. A general discussion about four types of termination criteria has been firstly discussed in this article. Then some measures of convergence based on pheromone have been introduced. And a new termination criterion based on Bayesian approach is presented. Finally a new convergence proof for a class of ACO algorithms is presented.
This paper presents a topic-driven framework for generating a generic summary from multi-documents. Our approach is based on the intuition that, from the statistical point of view, the summary's probability distri...
详细信息
This paper presents a topic-driven framework for generating a generic summary from multi-documents. Our approach is based on the intuition that, from the statistical point of view, the summary's probability distribution over the topics should be consistent with the multi-documents' probability distribution over the inherent topics. Here, the topics are defined as weighted “bag-of-words” and derived by Latent Dirichlet Allocation from a collection of documents, either the given multi-documents or a related large-scale corpus. In this sense, we could represent various kinds of text units, such as word, sentence, summary, document and multi-documents, using a single vector space model via their corresponding probability distributions over the derived topics. Therefore, we are able to extract a sentence or summary by calculating the similarity between a sentence/summary and the given multi-documents via their topic probability distributions. In particular, we propose two methods in similarity measurement: the static method and the dynamic method. While the former is employed to detect the salience of information in a static way, the later further controls redundancy in a dynamic way. In addition, we integrate various popular features to improve the performance. Evaluation on the TAC 2008 update summarization task shows encouraging results.
The tradition standby mechanism can't carry out the dynamic Disaster Recovery of database between distributed isomeric storage systems, accordingly, research the method of allopatric isomeric backup based on grid ...
详细信息
The challenges of road network segmentation demand an algorithm capable of adapting to the sparse and irregular shapes, as well as the diverse context, which often leads traditional encoding-decoding methods and simpl...
详细信息
With the rapid development of the mobile Internet,users generate massive data in different forms in social network every day,and different characteristics of users are reflected by these social media *** to integrate ...
详细信息
With the rapid development of the mobile Internet,users generate massive data in different forms in social network every day,and different characteristics of users are reflected by these social media *** to integrate multiple heterogeneous information and establish user profiles from multiple perspectives plays an important role in providing personalized services,marketing,and recommendation *** this paper,we propose Multi-source&Multi-task Learning for User Profiles in Social Network which integrates multiple social data sources and contains a multi-task learning framework to simultaneously predict various attributes of a ***,we design their own feature extraction models for multiple heterogeneous data ***,we design a shared layer to fuse multiple heterogeneous data sources as general shared representation for multi-task ***,we design each task’s own unique presentation layer for discriminant output of ***,we design a weighted loss function to improve the learning efficiency and prediction accuracy of each *** experimental results on more than 5000 Sina Weibo users demonstrate that our approach outperforms state-of-the-art baselines for inferring gender,age and region of social media users.
暂无评论