Title: Structured Training for Neural Network Transition-Based Parsing
Authors: David Weiss, Chris Alberti, Michael Collins, Slav Petrov
Published: 19th June 2015 (Friday) @ 21:05:01
Link: http://arxiv.org/abs/1506.06158v1
Abstract
We present structured perceptron training for neural network transition-based dependency parsing. We learn the neural network representation using a gold corpus augmented by a large number of automatically parsed sentences. Given this fixed network representation, we learn a final layer using the structured perceptron with beam-search decoding. On the Penn Treebank, our parser reaches 94.26% unlabeled and 92.41% labeled attachment accuracy, which to our knowledge is the best accuracy on Stanford Dependencies to date. We also provide in-depth ablative analysis to determine which aspects of our model provide the largest gains in accuracy.