We introduce a globally normalized transition-based neural network model that achieves state-of-the-art part-of-speech tagging, dependency parsing and sentence compression results. Our model is a simple feed-forward neural network that operates on a task-specific transition system, yet achieves comparable or better accuracies than recurrent models. We discuss the importance of global as opposed to local normalization: a key insight is that the label bias problem implies that globally normalized models can be strictly more expressive than locally normalized models.
@article{arxiv.1603.06042,
title = {Globally Normalized Transition-Based Neural Networks},
author = {Daniel Andor and Chris Alberti and David Weiss and Aliaksei Severyn and Alessandro Presta and Kuzman Ganchev and Slav Petrov and Michael Collins},
journal= {arXiv preprint arXiv:1603.06042},
year = {2016}
}