@InProceedings{weissenborn-wiese-seiffe:2017:CoNLL,
  author    = {Weissenborn, Dirk  and  Wiese, Georg  and  Seiffe, Laura},
  title     = {Making Neural QA as Simple as Possible but not Simpler},
  booktitle = {Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {271--280},
  abstract  = {Recent development of large-scale question answering (QA) datasets triggered a
	substantial amount of research into end-to-end neural architectures for QA.
	Increasingly complex systems have been conceived without comparison to simpler
	neural baseline systems that would justify their complexity. In this work, we
	propose a simple heuristic that guides the development of neural baseline
	systems for the extractive QA task. We find that there are two ingredients
	necessary for building a high-performing neural QA system: first, the awareness
	of question words while processing the context and second, a composition
	function that goes beyond simple bag-of-words modeling, such as recurrent
	neural networks. Our results show that FastQA, a system that meets these two
	requirements, can achieve very competitive performance compared with existing
	models. We argue that this surprising finding puts results of previous systems
	and the complexity of recent QA datasets into perspective.},
  url       = {http://aclweb.org/anthology/K17-1028}
}