A neural network approach to topic spotting

This paper presents an application of nonlinear neural networks to topic spotting. Neural networks allow us to model higher-order interaction between document terms and to simultaneously predict multiple topics using shared hidden features. In the context of this model, we compare two approaches to dimensionality reduction in representation: one based on term selection and another based on Latent Semantic Indexing (LSI). Two diierent methods are proposed for improving LSI representations for the topic spotting task. We nd that term selection and our modiied LSI representations lead to similar topic spotting performance, and that this performance is equal to or better than other published results on the same corpus.