@InProceedings{maillard-clark:2018:W18-29,
  author    = {Maillard, Jean  and  Clark, Stephen},
  title     = {Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing},
  booktitle = {Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {13--18},
  abstract  = {Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the composition order. This work contributes (a) a new latent tree learning model based on shift-reduce parsing, with competitive downstream performance and non-trivial induced trees, and (b) an analysis of the trees learned by our shift-reduce model and by a chart-based model.},
  url       = {http://www.aclweb.org/anthology/W18-2903}
}