@InProceedings{wiseman-shieber-rush:2017:EMNLP2017,
  author    = {Wiseman, Sam  and  Shieber, Stuart  and  Rush, Alexander},
  title     = {Challenges in Data-to-Document Generation},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {2253--2263},
  abstract  = {Recent neural models have shown significant progress on the problem of
	generating short descriptive texts conditioned on a small number of database
	records. In this work, we suggest a slightly more difficult data-to-text
	generation task, and investigate how effective current approaches are on this
	task. In particular, we introduce a new, large-scale corpus of data records
	paired with descriptive documents, propose a series of extractive evaluation
	methods for analyzing performance, and obtain baseline results using current
	neural generation methods. Experiments show that these models produce fluent
	text, but fail to convincingly approximate human-generated documents. Moreover,
	even templated baselines exceed the performance of these neural models on some
	metrics, though copy- and reconstruction-based extensions lead to noticeable
	improvements.
	Author{2}{Affiliation}},
  url       = {https://www.aclweb.org/anthology/D17-1239}
}