Collective Document Classification with Implicit Inter-document Semantic Relationships
Clint Burford, Steven Bird, Timothy J. Baldwin · 2015
This paper addresses the question of how document classifiers can exploit implicit information about document similarity to improve document classifier accuracy.We infer document similarity using simple n-gram overlap, and demonstrate that this improves overall document classification performance over two datasets.As part of this, we find that collective classification based on simple iterative classifiers outperforms the more complex and computationally-intensive dual classifier approach.