@InProceedings{kuncoro-EtAl:2017:EACLlong,
  author    = {Kuncoro, Adhiguna  and  Ballesteros, Miguel  and  Kong, Lingpeng  and  Dyer, Chris  and  Neubig, Graham  and  Smith, Noah A.},
  title     = {What Do Recurrent Neural Network Grammars Learn About Syntax?},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {1249--1258},
  abstract  = {Recurrent neural network grammars (RNNG) are a recently proposed probablistic
	generative modeling family for natural language. They show state-of-the-art
	language modeling and parsing performance. We investigate what information they
	learn, from a linguistic perspective, through various ablations to the model
	and the data, and by augmenting the model with an attention mechanism (GA-RNNG)
	to enable closer inspection. We find that explicit modeling of composition is
	crucial for achieving the best performance. Through the attention mechanism, we
	find that headedness plays a central role in phrasal representation (with the
	model's latent attention largely agreeing with predictions made by hand-crafted
	head rules, albeit with some important differences). By training grammars
	without nonterminal labels, we find that phrasal representations depend
	minimally on nonterminals, providing support for the endocentricity hypothesis.},
  url       = {http://www.aclweb.org/anthology/E17-1117}
}