Toward a multi-sensor-based approach to automatic text classification

摘要

Many automatic text indexing and retrieval methods use a term-document matrix that is automatically derived from the text in question. Latent Semantic Indexing is a method, recently proposed in the Information Retrieval (IR) literature, for approximating a large and sparse term-document matrix with a relatively small number of factors, and is based on a solid mathematical foundation. LSI appears to be quite useful in the problem of text information retrieval, rather than text classification. In this report, we outline a method that attempts to combine the strength of the LSI method with that of neural networks, in addressing the problem of text classification. In doing so, we also indicate ways to improve performance by adding additional (open quotes)logical sensors(close quotes) to the neural network, something that is hard to do with the LSI method when employed by itself. The various programs that can be used in testing the system with TIPSTER data set are described. Preliminary results are summarized, but much work remains to be done.