@InProceedings{ramrakhiyani-EtAl:2017:EACLshort,
  author    = {Ramrakhiyani, Nitin  and  Pawar, Sachin  and  Hingmire, Swapnil  and  Palshikar, Girish},
  title     = {Measuring Topic Coherence through Optimal Word Buckets},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {437--442},
  abstract  = {Measuring topic quality is essential for scoring the learned topics and their
	subsequent use in Information Retrieval and Text classification. To measure
	quality of Latent Dirichlet Allocation (LDA) based topics learned from text, we
	propose a novel approach based on grouping of topic words into buckets
	(TBuckets). A single large bucket signifies a single coherent theme, in turn
	indicating high topic coherence. TBuckets uses word embeddings of topic words
	and employs singular value decomposition (SVD) and Integer Linear Programming
	based optimization to create coherent word buckets. TBuckets outperforms the
	state-of-the-art techniques when evaluated using 3 publicly available datasets
	and on another one proposed in this paper.},
  url       = {http://www.aclweb.org/anthology/E17-2070}
}