@InProceedings{dyer:2017:CoNLL,
  author    = {Dyer, Chris},
  title     = {Should Neural Network Architecture Reflect Linguistic Structure?},
  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     = {1},
  abstract  = {I explore the hypothesis that conventional neural network models (e.g.,
	recurrent neural networks) are incorrectly biased for making linguistically
	sensible generalizations when learning, and that a better class of models is
	based on architectures that reflect hierarchical structures for which
	considerable behavioral evidence exists. I focus on the problem of modeling and
	representing the meanings of sentences. On the generation front, I introduce
	recurrent neural network grammars (RNNGs), a joint, generative model of
	phrase-structure trees and sentences. RNNGs operate via a recursive syntactic
	process reminiscent of probabilistic context-free grammar generation, but
	decisions are parameterized using RNNs that condition on the entire (top-down,
	left-to-right) syntactic derivation history, thus relaxing context-free
	independence assumptions, while retaining a bias toward explaining decisions
	via "syntactically local" conditioning contexts. Experiments show that RNNGs
	obtain better results in generating language than models that don’t exploit
	linguistic structure. On the representation front, I explore unsupervised
	learning of syntactic structures based on distant semantic supervision using a
	reinforcement-learning algorithm. The learner seeks a syntactic structure that
	provides a compositional architecture that produces a good representation for a
	downstream semantic task. Although the inferred structures are quite different
	from traditional syntactic analyses, the performance on the downstream tasks
	surpasses that of systems that use sequential RNNs and tree-structured RNNs
	based on treebank dependencies. This is joint work with Adhi Kuncoro, Dani
	Yogatama, Miguel Ballesteros, Phil Blunsom, Ed Grefenstette, Wang Ling, and
	Noah A. Smith.},
  url       = {http://aclweb.org/anthology/K17-1001}
}