Language Model-Based Document Clustering Using Random Walks

We propose a new document vector representation specifically designed for the document clustering task. Instead of the traditional termbased vectors, a document is represented as an -dimensional vector, where is the number of documents in the cluster. The value at each dimension of the vector is closely related to the generation probability based on the language model of the corresponding document. Inspired by the recent graph-based NLP methods, we reinforce the generation probabilities by iterating random walks on the underlying graph representation. Experiments with k-means and hierarchical clustering algorithms show significant improvements over the alternative vector representation.