TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Dependency Parsing	Penn Treebank	Weiss et al.	POS	97.3	# 5
Dependency Parsing	Penn Treebank	Weiss et al.	UAS	94.01	# 19
Dependency Parsing	Penn Treebank	Weiss et al.	LAS	92.06	# 18

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/structured-training-for-neural-network/dependency-parsing-on-penn-treebank)](https://paperswithcode.com/sota/dependency-parsing-on-penn-treebank?p=structured-training-for-neural-network)`

Structured Training for Neural Network Transition-Based Parsing

IJCNLP 2015 · David Weiss, Chris Alberti, Michael Collins, Slav Petrov ·

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.