Bin Zhang

From WikiPapers
Jump to: navigation, search

Bin Zhang is an author.


Only those publications related to wikis are shown here.
Title Keyword(s) Published in Language DateThis property is a special property in this wiki. Abstract R C
Keyword extraction using multiple novel features Keyword extraction
Natural Language Processing
Journal of Computational Information Systems English 2014 In this paper, we propose a novel approach for keyword extraction. Different from previous keyword extraction methods, which identify keywords based on the document alone, this approach introduces Wikipedia knowledge and document genre to extract keywords from the document. Keyword extraction is accomplished by a classification model utilizing not only traditional word based features but also features based on Wikipedia knowledge and document genre. In our experiment, this novel keyword extraction approach outperforms previous models for keyword extraction in terms of precision-recall metric and breaks through the plateau previously reached in the field. © 2014 Binary Information Press. 0 0
Annotating social acts: authority claims and alignment moves in Wikipedia talk pages LSM English 2011 0 0
Comprehensive query-dependent fusion using regression-on-folksonomies: A case study of multimodal music search Folksonomy
Multimodal search
Query-dependent fusion
MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums English 2009 The combination of heterogeneous knowledge sources has been widely regarded as an effective approach to boost retrieval accuracy in many information retrieval domains. While various technologies have been recently developed for information retrieval, multimodal music search has not kept pace with the enormous growth of data on the Internet. In this paper, we study the problem of integrating multiple online information sources to conduct effective query dependent fusion (QDF) of multiple search experts for music retrieval. We have developed a novel framework to construct a knowledge space of users' information need from online folksonomy data. With this innovation, a large number of comprehensive queries can be automatically constructed to train a better generalized QDF system against unseen user queries. In addition, our framework models QDF problem by regression of the optimal combination strategy on a query. Distinguished from the previous approaches, the regression model of QDF (RQDF) offers superior modeling capability with less constraints and more efficient computation. To validate our approach, a large scale test collection has been collected from different online sources, such as, Wikipedia, and YouTube. All test data will be released to the public for better research synergy in multimodal music search. Our performance study indicates that the accuracy, efficiency, and robustness of the multimodal music search can be improved significantly by the proposed folksonomy-RQDF approach. In addition, since no human involvement is required to collect training examples, our approach offers great feasibility and practicality in system development. Copyright 2009 ACM. 0 0