Predictive Top-Down Knowledge Improves Neural Exploratory Bottom-Up Clustering

@inproceedings{Hung2004PredictiveTK,
  title={Predictive Top-Down Knowledge Improves Neural Exploratory Bottom-Up Clustering},
  author={Chihli Hung and Stefan Wermter and Peter Smith},
  booktitle={ECIR},
  year={2004}
}
In this paper, we explore the hypothesis that integrating symbolic top-down knowledge into text vector representations can improve neural exploratory bottom-up representations for text clustering. By extracting semantic rules from WordNet, terms with similar concepts are substituted with a more general term, the hypernym. This hypernym semantic relationship supplements the neural model in document clustering. The neural model is based on the extended significance vector representation approach… CONTINUE READING