@InProceedings{madan-joshi:2017:I17-1,
  author    = {Madan, Dhiraj  and  Joshi, Sachindra},
  title     = {Finding Dominant User Utterances And System Responses in Conversations},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {723--732},
  abstract  = {There are several dialog frameworks which allow manual specification of intents
	and rule based dialog flow. The rule based framework provides good control to
	dialog designers at the expense of being more time consuming and laborious. The
	job of a dialog designer can be reduced if we could identify pairs of user
	intents and corresponding responses automatically from prior conversations
	between users and agents. In this paper we propose an approach to find these
	frequent user utterances (which serve as examples for intents) and
	corresponding agent responses. We propose a novel SimCluster algorithm that
	extends standard K-means algorithm to simultaneously cluster user utterances
	and agent utterances by taking their adjacency information into account. The
	method also aligns these clusters to provide pairs of intents and response
	groups. We compare our results with those produced by using simple Kmeans
	clustering on a real dataset and observe upto 10% absolute improvement in
	F1-scores. Through our experiments on synthetic dataset, we show that our
	algorithm gains more advantage over K-means algorithm when the data has large
	variance.},
  url       = {http://www.aclweb.org/anthology/I17-1073}
}