YANG Zhen, FAN Kefeng, LAI Yingxu, GAO Kaiming, WANG Yong. Short Texts Classification Through Reference Document Expansion[J]. Chinese Journal of Electronics, 2014, 23(2): 315-321.
Citation: YANG Zhen, FAN Kefeng, LAI Yingxu, GAO Kaiming, WANG Yong. Short Texts Classification Through Reference Document Expansion[J]. Chinese Journal of Electronics, 2014, 23(2): 315-321.

Short Texts Classification Through Reference Document Expansion

Funds:  This work is supported by the National Natural Science Foundation of China (No.61001178, No.61172053, No.61202266), National Soft Science Research Program (No.2010GXQ5D317), Beijing Natural Science Foundation (No.4102012, No.4112009), Scientific Research Common Program of Beijing Municipal Commission of Education (No.KM201210005024), and the National High Technology Research and Development Program of China (863 Program) (No.2012AA011706).
  • Received Date: 2013-01-01
  • Rev Recd Date: 2013-01-01
  • Publish Date: 2014-04-05
  • With the rapid development of information technology, short texts arising from socialized human interaction are gradually predominant in network information streams. Accelerating demands are requiring the industry to provide more effective classification of the brief texts. However, faced with short text documents, each of which contains only a few words, traditional document classification models run into difficulty. Aggressive documents expansion works remarkably well for many cases but suffers from the assumption of independent, identically distributed observations. We formalize a view of classification using Bayesian decision theory, treat each short text as observations from a probabilistic model, called a statistical language model, and encode classification preferences with a loss function defined by the language models and the external reference document. According to Vapnik's methods of Structural risk minimization (SRM), the optimal classification action is the one that minimizes the structural risk, which provides a result that allows one to trade off errors on the training sample against improved generalization performance. We conduct experiments by using several corpora of microblog-like data, and analyze the experimental results. With respect to established baselines, results of these experiments show that applying our proposed document expansion method produces better chance to achieve the improved classification performance.
  • loading
  • L. Rocha, F. Mourao, H. Mota et al., "Temporal contexts: Effective text classification in evolving document collections", Information Systems, Vol.38, No.3, pp.388-409, 2012.
    M.T. Fardanesh, "Classification accuracy improvement of neural network classifiers by using unlabeled data", IEEE Transactions on Geoscience and Remote Sensing, Vol.36, No.3, pp.1020-1025, 1998.
    T. Joachims, "Transductive inference for text classification using support vector machines", Proc. of the Sixteenth International Conference on Machine Learning, Bled, Slovenia, pp.200-209, 1999.
    Y. Tsuruoka, J. Tsujii, "Training a naive bayes classifier via the EM algorithm with a class distribution constraint", Proc. of the Seventh Conference on Natural Language Learning, Edmonton, Canada, pp.127-134, 2003.
    R. Kothari, V. Jain, "Learning from labeled and unlabeled data using a minimal number of queries", IEEE Transaction on Neural Networks, Vol.14, No.6, pp.1496-1505, 2003.
    M. Efron, P. Organisciak, K. Fenlon, "Improving retrieval of short texts through document expansion", Proc. of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval, Portland, OR, United states, pp.911-920, 2012.
    V. Vapnik, The Nature of Statistical Learning Theory, Springer-Verlag, New York, 1999.
    S.M. Katz, "Estimation of probabilities from sparse data for the language model component of a speech recognizer", IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol.ASP-35, No.3, pp.400-401, 1987.
    C.X. Zhai, "Statistical language models for information retrieval a critical review", Foundations and Trends in Information Retrieval, Vol.2, No.3, pp.137-213, 2008.
    V. Lavrenko, W.B. Croft, "Relevance based language models", Proc. of the 24th annual international ACM SIGIR conference on Research and Development in Information Retrieval, New York, USA, pp.120-127, 2001.
    C.X. Zhai, J. Lafferty, "A risk minimization framework for information retrieval", Information Processing and Management, Vol.42, No.1, pp.31-55, 2006.
    K. Lang, "Newsweeder: Learning to filter netnews", Proc. of 12th International Conference on Machine Learning, California, USA, pp.331-339, 1995.
  • 加载中


    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (319) PDF downloads(1492) Cited by()
    Proportional views


    DownLoad:  Full-Size Img  PowerPoint