@InProceedings{shen-EtAl:2017:I17-1,
  author    = {Shen, Yelong  and  Liu, Xiaodong  and  Duh, Kevin  and  Gao, Jianfeng},
  title     = {An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks},
  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     = {957--966},
  abstract  = {Reading comprehension (RC) is a challenging task that requires synthesis of
	information across sentences and multiple turns of reasoning. 
	Using a state-of-the-art RC model, we empirically investigate the performance
	of single-turn and multiple-turn reasoning on the SQuAD and MS MARCO datasets.
	The RC model is an end-to-end neural network with iterative attention, and uses
	reinforcement learning to dynamically control the number of turns. 
	We find that multiple-turn reasoning outperforms single-turn reasoning for all
	question and answer types; further, we observe that enabling a flexible number
	of turns generally improves upon a fixed multiple-turn strategy. 
	%across all question types, and is particularly beneficial to questions with
	lengthy, descriptive answers. 
	We achieve results competitive to the state-of-the-art on these two datasets.},
  url       = {http://www.aclweb.org/anthology/I17-1096}
}